{ "schema_version": 1, "kind": "dataset", "profile_count": 66, "curated_resource_count": 86, "unit": "resource profile; count observations retain their own units and populations", "limitations": "Source-reviewed descriptions and reported or computed inventory counts. No performance ranking, independent reproduction, or global-completeness claim.", "records": [ { "id": "url:964d70c40bfc5ca8e1ee", "name": "AgentNet", "url": "https://huggingface.co/datasets/xlangai/AgentNet", "environments": [ "desktop" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/xlangai/AgentNet/raw/main/README.md", "population": "AgentNet collection", "qualifier": "approximately", "unit": "tasks", "value": 22600 } ], "evidence_urls": [ "https://huggingface.co/datasets/xlangai/AgentNet/raw/main/README.md" ], "formats": [ "JSONL", "image archives" ], "modalities": [ "screenshots", "instructions", "actions", "generated reasoning" ], "notes": "The card distinguishes human task instructions from generated summaries, reasoning, reflections, and quality fields. Generated labels are not independent human quality acceptance records.", "splits": [], "supervision": [ "computer-use trajectories", "synthesized reasoning" ] }, "licenses": { "code": null, "data": { "basis": "publisher model/dataset card", "declared": "mit", "retrieved_at": "2026-10-16T06:38:26Z", "url": "https://huggingface.co/datasets/xlangai/AgentNet" }, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T11:40:46Z", "role": "primary", "sha256": "327a77856df259db0a0c2405478f75a0d0f2bf17c51806abc7c509ad82c3ad57", "supports": [ "details.dataset_profile" ], "url": "https://huggingface.co/datasets/xlangai/AgentNet/raw/main/README.md" } ] }, { "id": "url:58a209f2b3b970916396", "name": "AgentSynth tasks and trajectories", "url": "https://huggingface.co/datasets/sunblaze-ucb/AgentSynth", "environments": [ "desktop", "web" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/sunblaze-ucb/AgentSynth/raw/9ec3f3139f9786e81aee14b7fff1eb487cc7e991/README.md", "population": "collection described in the dataset card; not an independently counted release-row total", "qualifier": "more-than", "unit": "tasks", "value": 6000 } ], "evidence_urls": [ "https://huggingface.co/datasets/sunblaze-ucb/AgentSynth/raw/9ec3f3139f9786e81aee14b7fff1eb487cc7e991/README.md", "https://huggingface.co/api/datasets/sunblaze-ucb/AgentSynth" ], "formats": [ "JSONL", "ZIP trajectory packages" ], "modalities": [ "screenshots", "task instructions", "LLM thoughts", "commands" ], "notes": "Card maps osworld/train to all_tasks.jsonl and insta/train to task_sequences.jsonl. Six difficulty levels and trajectory screenshots/thoughts/commands are documented. ZIP file labels are not trajectory counts; configurations and composed-task levels are not assumed disjoint.", "splits": [ "train (osworld configuration)", "train (insta configuration)" ], "supervision": [ "synthetic tasks", "agent trajectories" ] }, "licenses": { "code": null, "data": { "basis": "Publisher dataset-card declaration for this release; it does not establish rights to all upstream screenshots, applications or source content.", "declared": "Apache-2.0", "retrieved_at": "2026-10-18T04:35:17Z", "url": "https://huggingface.co/datasets/sunblaze-ucb/AgentSynth/raw/9ec3f3139f9786e81aee14b7fff1eb487cc7e991/README.md" }, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:35:17Z", "role": "primary", "sha256": "c1669d8e3caa27f8cd47c17b243b6a8d42807438d8a6a36074668adc57d33757", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "notes", "relations", "licenses.data", "details.dataset_profile" ], "url": "https://huggingface.co/datasets/sunblaze-ucb/AgentSynth/raw/9ec3f3139f9786e81aee14b7fff1eb487cc7e991/README.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:33:20Z", "role": "primary", "sha256": "0d3797d75dd4089ece8c8d4624f2a726024d25be255255d8770f78de21d75906", "supports": [ "identity", "release_status", "details.hub_id", "details.hub_revision", "details.gated", "details.disabled", "details.download_url", "details.dataset_profile" ], "url": "https://huggingface.co/api/datasets/sunblaze-ucb/AgentSynth" } ] }, { "id": "url:06dd5ac7917c45d48509", "name": "Aguvis stage 1 grounding data", "url": "https://huggingface.co/datasets/xlangai/aguvis-stage1", "environments": [ "cross-platform" ], "profile": { "counts": [], "evidence_urls": [ "https://huggingface.co/datasets/xlangai/aguvis-stage1/raw/main/README.md", "https://huggingface.co/api/datasets/xlangai/aguvis-stage1", "https://raw.githubusercontent.com/xlang-ai/aguvis/HEAD/README.md", "https://raw.githubusercontent.com/xlang-ai/aguvis/HEAD/data/stage1.yaml" ], "formats": [ "JSON annotations", "ZIP image packages", "multipart TAR image packages" ], "modalities": [ "GUI screenshots", "grounding annotations" ], "notes": "Stage 1 grounding release, Hub revision 5d11f8f5. JSON annotations and ZIP/multipart TAR image packages are publicly listed. The official training configuration groups web, desktop and mobile inputs and selects all rows of its configured inputs; this is a training recipe, not a release sample count or held-out split. The config names omniact.json while the Hub manifest lists omniact_fix.json, so local paths need reconciliation. No sample total is inferred from names such as webui350k. Apache-2.0 is the release card declaration; upstream source rights remain separate.", "splits": [ "training" ], "supervision": [ "GUI grounding supervised fine-tuning" ] }, "licenses": { "code": null, "data": { "basis": "publisher model/dataset card metadata; third-party assets retain their own terms", "declared": "apache-2.0", "retrieved_at": "2026-10-17T02:03:33Z", "url": "https://huggingface.co/datasets/xlangai/aguvis-stage1/raw/main/README.md" }, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T02:03:33Z", "role": "primary", "sha256": "38bda302cf741b9d2b2394b53d157b3c19d8a73e3704c01ed2f9a27c374feb77", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "details", "details.dataset_profile" ], "url": "https://huggingface.co/datasets/xlangai/aguvis-stage1/raw/main/README.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T02:03:33Z", "role": "primary", "sha256": "cb3b8ec88d811d946df3cbf38ef555db5a10d1124668765710c380e9b1988b06", "supports": [ "identity", "release_status", "details", "licenses.data", "details.dataset_profile" ], "url": "https://huggingface.co/api/datasets/xlangai/aguvis-stage1" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:00Z", "role": "primary", "sha256": "2dd9f36b818c1b7b6bd772ba8575f6c0ebab6d9e0d307edcc2f196f3e4ba502e", "supports": [ "environments", "summary", "details.dataset_profile" ], "url": "https://raw.githubusercontent.com/xlang-ai/aguvis/HEAD/README.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T14:21:11Z", "role": "primary", "sha256": "f6a9e55c5d48469e2c8f7799d917d25e7a758036f71c7c045fa92c35057d20da", "supports": [ "details.dataset_profile" ], "url": "https://raw.githubusercontent.com/xlang-ai/aguvis/HEAD/data/stage1.yaml" }, { "method": "huggingface_card", "retrieved_at": "2026-10-17T02:03:33Z", "role": "primary", "sha256": "38bda302cf741b9d2b2394b53d157b3c19d8a73e3704c01ed2f9a27c374feb77", "supports": [ "licenses.data" ], "url": "https://huggingface.co/datasets/xlangai/aguvis-stage1/raw/main/README.md" } ] }, { "id": "url:b5e2127e07f692d516b9", "name": "Aguvis stage 2 trajectory data", "url": "https://huggingface.co/datasets/xlangai/aguvis-stage2", "environments": [ "cross-platform" ], "profile": { "counts": [], "evidence_urls": [ "https://huggingface.co/datasets/xlangai/aguvis-stage2/raw/main/README.md", "https://huggingface.co/api/datasets/xlangai/aguvis-stage2", "https://raw.githubusercontent.com/xlang-ai/aguvis/HEAD/README.md", "https://raw.githubusercontent.com/xlang-ai/aguvis/HEAD/data/stage2.yaml" ], "formats": [ "JSON annotations", "ZIP image packages", "multipart TAR image packages" ], "modalities": [ "GUI screenshots", "natural-language instructions", "action trajectories" ], "notes": "Stage 2 trajectory release, Hub revision bd6f1ed4, is distinct from Stage 1 grounding. The public manifest lists source-specific JSON levels and image ZIP/multipart TAR packages. The training recipe uses all rows for some inputs and random:33% for others; several l2 paths occur twice while the manifest also contains l3 files. Recipe rows/levels are neither independent datasets nor disjoint train/test splits. No example/action/trajectory count is inferred. Apache-2.0 is the card declaration, with separate underlying source terms.", "splits": [ "training" ], "supervision": [ "GUI trajectory supervised fine-tuning", "planning and reasoning with inner monologue" ] }, "licenses": { "code": null, "data": { "basis": "publisher model/dataset card metadata; third-party assets retain their own terms", "declared": "apache-2.0", "retrieved_at": "2026-10-17T02:03:33Z", "url": "https://huggingface.co/datasets/xlangai/aguvis-stage2/raw/main/README.md" }, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T02:03:33Z", "role": "primary", "sha256": "550293f00905615e19e63ac896818f9875dad38fea0ffe196c6302a29719aa72", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "details", "details.dataset_profile" ], "url": "https://huggingface.co/datasets/xlangai/aguvis-stage2/raw/main/README.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T02:03:33Z", "role": "primary", "sha256": "f030264a7a8c7485dc7cf15ca554d84450cc492d2ac90e5965810a0207ef370b", "supports": [ "identity", "release_status", "details", "licenses.data", "details.dataset_profile" ], "url": "https://huggingface.co/api/datasets/xlangai/aguvis-stage2" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:00Z", "role": "primary", "sha256": "2dd9f36b818c1b7b6bd772ba8575f6c0ebab6d9e0d307edcc2f196f3e4ba502e", "supports": [ "environments", "summary", "details.dataset_profile" ], "url": "https://raw.githubusercontent.com/xlang-ai/aguvis/HEAD/README.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T14:21:11Z", "role": "primary", "sha256": "8c1b39e9d16067018ce845fd4e996f34e2b47346c342b2ba26b030f4a5338b66", "supports": [ "details.dataset_profile" ], "url": "https://raw.githubusercontent.com/xlang-ai/aguvis/HEAD/data/stage2.yaml" }, { "method": "huggingface_card", "retrieved_at": "2026-10-17T02:03:33Z", "role": "primary", "sha256": "550293f00905615e19e63ac896818f9875dad38fea0ffe196c6302a29719aa72", "supports": [ "licenses.data" ], "url": "https://huggingface.co/datasets/xlangai/aguvis-stage2/raw/main/README.md" } ] }, { "id": "github:yuxiangchai/amex-codebase", "name": "AMEX", "url": "https://github.com/YuxiangChai/AMEX-codebase", "environments": [ "android" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=800&max_results=100&sortBy=submittedDate&sortOrder=descending", "population": "AMEX collection described in the paper", "qualifier": "more-than", "reference_url": "https://arxiv.org/abs/2407.17490", "unit": "screenshots", "value": 104000 } ], "evidence_urls": [ "https://raw.githubusercontent.com/YuxiangChai/AMEX-codebase/HEAD/README.md", "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=800&max_results=100&sortBy=submittedDate&sortOrder=descending" ], "formats": [], "modalities": [ "screenshots", "element annotations", "functionality descriptions", "action chains" ], "notes": "The main repository contains companion training code. The scale and annotation levels here come from the paper, not an independent download or completeness audit.", "splits": [], "supervision": [ "element grounding", "UI functionality", "interaction trajectories" ] }, "licenses": { "code": { "basis": "repository LICENSE header; not a weights/data license", "declared": "Apache-2.0", "retrieved_at": "2026-10-16T06:42:02Z", "url": "https://raw.githubusercontent.com/YuxiangChai/AMEX-codebase/HEAD/LICENSE" }, "data": null, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:01Z", "role": "primary", "sha256": "3184bfd612543621e57226e9079132dc8d5695339795a60366d3f6d445e13551", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "details.dataset_profile" ], "url": "https://raw.githubusercontent.com/YuxiangChai/AMEX-codebase/HEAD/README.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:58Z", "role": "primary", "sha256": "c87e97eb397da04806d53145cf9c13be739fc657bb54dca9318c8c4ed2a36249", "supports": [ "details.dataset_profile", "relations" ], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=800&max_results=100&sortBy=submittedDate&sortOrder=descending" } ] }, { "id": "component:google-research/android_in_the_wild", "name": "Android in the Wild", "url": "https://github.com/google-research/google-research/tree/master/android_in_the_wild", "environments": [ "android" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://raw.githubusercontent.com/google-research/google-research/master/android_in_the_wild/README.md", "population": "sum of the five published AitW subsets", "qualifier": "exact", "unit": "episodes", "value": 715142 }, { "basis": "reported", "evidence_url": "https://raw.githubusercontent.com/google-research/google-research/master/android_in_the_wild/README.md", "population": "sum of the five published AitW subsets", "qualifier": "exact", "unit": "action examples", "value": 5689993 } ], "evidence_urls": [ "https://raw.githubusercontent.com/google-research/google-research/master/android_in_the_wild/README.md" ], "formats": [ "GZIP-compressed TFRecord" ], "modalities": [ "screenshots", "instructions", "actions" ], "notes": "Episodes and action examples are different units. The collection combines multi-step subsets and hindsight-labeled single-step tasks; preserve subset and split choices.", "splits": [], "supervision": [ "interaction trajectories", "action prediction" ] }, "licenses": { "code": { "basis": "repository LICENSE header; not a weights/data license", "declared": "Apache-2.0", "retrieved_at": "2026-10-16T06:42:06Z", "url": "https://raw.githubusercontent.com/google-research/google-research/HEAD/LICENSE" }, "data": null, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:38:29Z", "role": "primary", "sha256": "6d8964c95db41dada1d5867e50a5ec61f6cb90595965d0e72e010b8e4a12dcb2", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "details.sample_count", "details.sample_unit", "details.example_count", "details.modalities", "details.access", "details.download_url", "details.dataset_profile" ], "url": "https://raw.githubusercontent.com/google-research/google-research/master/android_in_the_wild/README.md" } ] }, { "id": "url:cf4d2d45a7314cb16acb", "name": "AndroidCode", "url": "https://huggingface.co/datasets/GD-ML/AndroidCode", "environments": [ "android" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://raw.githubusercontent.com/AMAP-ML/Code2World/HEAD/readme.md", "population": "AndroidCode corpus described by Code2World README; released JSON rows not recounted", "qualifier": "more-than", "unit": "screen–action pairs", "value": 80000 } ], "evidence_urls": [ "https://raw.githubusercontent.com/AMAP-ML/Code2World/HEAD/readme.md", "https://huggingface.co/api/datasets/GD-ML/AndroidCode" ], "formats": [ "HTML", "JSON", "Python extraction/loading scripts" ], "modalities": [ "GUI screenshots (described input)", "GUI actions", "HTML" ], "notes": "The manifest lists 58,953 HTML files, which are not converted into transition/example counts. The reported >80k pairs and the HTML-file inventory have different units. The card itself has no sample schema or count; archive/image completeness and JSON contents were not audited.", "splits": [ "Android-Control train file", "Android-Control test file" ], "supervision": [ "action-conditioned next-state code prediction", "generated HTML supervision" ] }, "licenses": { "code": null, "data": { "basis": "Publisher dataset-card declaration for this release; it does not establish rights to all upstream screenshots, applications or source content.", "declared": "MIT", "retrieved_at": "2026-10-18T04:35:17Z", "url": "https://huggingface.co/datasets/GD-ML/AndroidCode/raw/af316a6be79bbe08c4fc09ea588b5f80f177ed25/README.md" }, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:27:14Z", "role": "primary", "sha256": "26c14a14166d3b747454d1924ecdf6d96652ac857ae6ad488630dc843036a777", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "notes", "relations", "details.dataset_profile" ], "url": "https://raw.githubusercontent.com/AMAP-ML/Code2World/HEAD/readme.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:33:22Z", "role": "primary", "sha256": "5774a3c096264fbba58b7a16587ea65f35628edb9ca39afe8a32c74ec7fd1ce7", "supports": [ "identity", "release_status", "details.hub_id", "details.hub_revision", "details.gated", "details.disabled", "details.download_url", "details.dataset_profile" ], "url": "https://huggingface.co/api/datasets/GD-ML/AndroidCode" } ] }, { "id": "component:google-research/android_control", "name": "AndroidControl", "url": "https://github.com/google-research/google-research/tree/master/android_control", "environments": [ "android" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://raw.githubusercontent.com/google-research/google-research/master/android_control/README.md", "population": "AndroidControl collection", "qualifier": "more-than", "unit": "demonstrations", "value": 15000 }, { "basis": "reported", "evidence_url": "https://raw.githubusercontent.com/google-research/google-research/master/android_control/README.md", "population": "AndroidControl collection", "qualifier": "exact", "unit": "applications", "value": 833 } ], "evidence_urls": [ "https://raw.githubusercontent.com/google-research/google-research/master/android_control/README.md" ], "formats": [ "GZIP-compressed TFRecord" ], "modalities": [ "screenshots", "accessibility trees", "instructions", "JSON actions" ], "notes": "Step instructions can be repeated across multiple actions. Each episode has one more screenshot than action; do not count repeated step instructions as independent task goals.", "splits": [ "publisher split file" ], "supervision": [ "interaction trajectories", "high- and low-level action instruction" ] }, "licenses": { "code": { "basis": "repository LICENSE header; not a weights/data license", "declared": "Apache-2.0", "retrieved_at": "2026-10-16T06:42:06Z", "url": "https://raw.githubusercontent.com/google-research/google-research/HEAD/LICENSE" }, "data": null, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:38:29Z", "role": "primary", "sha256": "e4f8baa15441fb63cad07220cc5a4de177a1f785d4fe1fed5cfcbf3c3867faf1", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "details.sample_count", "details.sample_unit", "details.reported_scale", "details.modalities", "details.dataset_profile" ], "url": "https://raw.githubusercontent.com/google-research/google-research/master/android_control/README.md" } ] }, { "id": "url:07b65dc937756ddff4a1", "name": "Aria-UI Context-aware Data", "url": "https://huggingface.co/datasets/Aria-UI/Aria-UI_Context-aware_Data", "environments": [ "android" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://raw.githubusercontent.com/AriaUI/Aria-UI/HEAD/README.md", "population": "context-aware episode training release", "qualifier": "approximately", "unit": "instruction-output pairs", "value": 992000 } ], "evidence_urls": [ "https://raw.githubusercontent.com/AriaUI/Aria-UI/HEAD/README.md" ], "formats": [], "modalities": [ "screen observations", "instructions", "interaction history" ], "notes": "The Hub card contains only licensing metadata. The project README supports the episode-training description and rounded count; archive-level quality and exact row counts remain unverified.", "splits": [], "supervision": [ "context-aware grounding" ] }, "licenses": { "code": null, "data": { "basis": "publisher model/dataset card", "declared": "apache-2.0", "retrieved_at": "2026-10-16T11:11:53Z", "url": "https://huggingface.co/datasets/Aria-UI/Aria-UI_Context-aware_Data" }, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:00Z", "role": "primary", "sha256": "a2a3c5ad115e4e2109b56686c9e0b073bcfec6d9f052a58bc92683af44933480", "supports": [ "name", "summary", "environments", "topics", "scope", "details.dataset_profile", "relations" ], "url": "https://raw.githubusercontent.com/AriaUI/Aria-UI/HEAD/README.md" } ] }, { "id": "url:f8566bd0394d36ed4f8e", "name": "Aria-UI Data", "url": "https://huggingface.co/datasets/Aria-UI/Aria-UI_Data", "environments": [ "web", "android", "desktop", "linux" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/Aria-UI/Aria-UI_Data/raw/main/README.md", "population": "web subset", "qualifier": "approximately", "unit": "instructions", "value": 2900000 }, { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/Aria-UI/Aria-UI_Data/raw/main/README.md", "population": "web subset", "qualifier": "approximately", "unit": "images", "value": 173000 }, { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/Aria-UI/Aria-UI_Data/raw/main/README.md", "population": "mobile subset", "qualifier": "approximately", "unit": "instructions", "value": 1100000 }, { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/Aria-UI/Aria-UI_Data/raw/main/README.md", "population": "mobile subset", "qualifier": "approximately", "unit": "images", "value": 104000 }, { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/Aria-UI/Aria-UI_Data/raw/main/README.md", "population": "desktop subset", "qualifier": "approximately", "unit": "instructions", "value": 150000 }, { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/Aria-UI/Aria-UI_Data/raw/main/README.md", "population": "desktop subset", "qualifier": "approximately", "unit": "images", "value": 7800 } ], "evidence_urls": [ "https://huggingface.co/datasets/Aria-UI/Aria-UI_Data/raw/main/README.md" ], "formats": [ "JSON annotations", "image archives" ], "modalities": [ "screenshots", "instructions", "element captions" ], "notes": "The card identifies deprecated desktop files with screenshot-mapping errors and names corrected releases. Counts are rounded publisher figures for separate platform subsets; instructions and images are not interchangeable.", "splits": [], "supervision": [ "element grounding", "element descriptions" ] }, "licenses": { "code": null, "data": { "basis": "publisher model/dataset card metadata; third-party assets retain their own terms", "declared": "apache-2.0", "retrieved_at": "2026-10-16T10:42:13Z", "url": "https://huggingface.co/datasets/Aria-UI/Aria-UI_Data/raw/main/README.md" }, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T10:42:13Z", "role": "primary", "sha256": "8713ca2a6b1962d5dce7da132e1135898d467053dc6b53b4463a0d43a6433bcb", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "details.modalities", "details.download_url", "details.dataset_profile" ], "url": "https://huggingface.co/datasets/Aria-UI/Aria-UI_Data/raw/main/README.md" }, { "method": "huggingface_card", "retrieved_at": "2026-10-16T10:42:13Z", "role": "primary", "sha256": "8713ca2a6b1962d5dce7da132e1135898d467053dc6b53b4463a0d43a6433bcb", "supports": [ "licenses.data" ], "url": "https://huggingface.co/datasets/Aria-UI/Aria-UI_Data/raw/main/README.md" } ] }, { "id": "url:9a3506ca6ef034adb424", "name": "AutoDroid V2 training data", "url": "https://huggingface.co/datasets/BlitherBoom/AutoDroid-V2-Dataset", "environments": [ "android" ], "profile": { "counts": [], "evidence_urls": [ "https://huggingface.co/api/datasets/BlitherBoom/AutoDroid-V2-Dataset", "https://raw.githubusercontent.com/MobileLLM/AutoDroid-V2/HEAD/step_3_training/README.md" ], "formats": [ "JSON in ShareGPT conversation format" ], "modalities": [ "text" ], "notes": "The card has license metadata only. The project training README supplies formatting and purpose. No sample count or split inventory is inferred from the training configuration.", "splits": [], "supervision": [ "supervised conversations for AutoDroid-V2 fine-tuning" ] }, "licenses": { "code": null, "data": { "basis": "Publisher dataset-card license declaration; does not establish permissions for model weights or third-party application content.", "declared": "mit", "retrieved_at": "2026-10-17T09:15:33Z", "url": "https://huggingface.co/datasets/BlitherBoom/AutoDroid-V2-Dataset/raw/main/README.md" }, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:15:33Z", "role": "primary", "sha256": "1b300edfbf44167da71639a56f8ab668dabd33769575fb313ebef5220fc1bddb", "supports": [ "name", "kind", "identity", "release_status", "details.hub_id", "details.gated", "details.disabled", "details.release_revision", "details.availability", "details.download_url", "details.dataset_profile.modalities" ], "url": "https://huggingface.co/api/datasets/BlitherBoom/AutoDroid-V2-Dataset" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T09:14:58Z", "role": "primary", "sha256": "8ba37983a2c2da53d96a52696c07e4bdbea4e987a1a07b557935d614c3be46d2", "supports": [ "summary", "topics", "scope", "notes", "details.dataset_profile", "relations" ], "url": "https://raw.githubusercontent.com/MobileLLM/AutoDroid-V2/HEAD/step_3_training/README.md" } ] }, { "id": "url:79287058342289aa5d45", "name": "AutoGUI v1 training data", "url": "https://huggingface.co/datasets/AutoGUI/AutoGUI-v1-702k", "environments": [ "web", "cross-platform" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/AutoGUI/AutoGUI-v1-702k/raw/main/README.md", "population": "default/train in the dataset card metadata", "qualifier": "exact", "unit": "training rows", "value": 701864 } ], "evidence_urls": [ "https://huggingface.co/datasets/AutoGUI/AutoGUI-v1-702k/raw/main/README.md" ], "formats": [], "modalities": [ "screenshots", "instructions", "functionality labels", "bounding boxes" ], "notes": "Rows are not unique screenshots. The card documents image-downscaling conventions that affect coordinates; preserve the device and original image-size fields.", "splits": [ "train" ], "supervision": [ "element grounding", "functionality captioning" ] }, "licenses": { "code": null, "data": { "basis": "publisher model/dataset card metadata; third-party assets retain their own terms", "declared": "cc-by-4.0", "retrieved_at": "2026-10-16T10:42:13Z", "url": "https://huggingface.co/datasets/AutoGUI/AutoGUI-v1-702k/raw/main/README.md" }, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T10:42:13Z", "role": "primary", "sha256": "c73b46acc2ff034a443fb8dbde327de1888535267199c9fb1819adf66898f1d7", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "details.sample_count", "details.sample_unit", "details.modalities", "details.download_url", "details.dataset_profile" ], "url": "https://huggingface.co/datasets/AutoGUI/AutoGUI-v1-702k/raw/main/README.md" }, { "method": "huggingface_card", "retrieved_at": "2026-10-16T10:42:13Z", "role": "primary", "sha256": "c73b46acc2ff034a443fb8dbde327de1888535267199c9fb1819adf66898f1d7", "supports": [ "licenses.data" ], "url": "https://huggingface.co/datasets/AutoGUI/AutoGUI-v1-702k/raw/main/README.md" } ] }, { "id": "url:eadc6cba9ea46c38dd1d", "name": "Dreamer V1 Data", "url": "https://huggingface.co/datasets/osunlp/Dreamer-V1-Data", "environments": [ "web" ], "profile": { "counts": [], "evidence_urls": [ "https://huggingface.co/datasets/osunlp/Dreamer-V1-Data/raw/main/README.md" ], "formats": [], "modalities": [ "images", "prompts", "actions", "responses" ], "notes": "The card reports a cleaned size of 3.12M without defining the counting unit, so no sample total is inferred. The data card declares noncommercial share-alike terms, separately from the model-weight license.", "splits": [], "supervision": [ "web-world-model prediction" ] }, "licenses": { "code": null, "data": { "basis": "publisher model/dataset card metadata; third-party assets retain their own terms", "declared": "cc-by-nc-sa-4.0", "retrieved_at": "2026-10-16T11:09:28Z", "url": "https://huggingface.co/datasets/osunlp/Dreamer-V1-Data/raw/main/README.md" }, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T11:09:28Z", "role": "primary", "sha256": "e656246f09340fed08136cf41a8b79880e19e1397ddd176410688ddee4e6365c", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "details.modalities", "details.download_url", "details.dataset_profile" ], "url": "https://huggingface.co/datasets/osunlp/Dreamer-V1-Data/raw/main/README.md" }, { "method": "huggingface_card", "retrieved_at": "2026-10-16T11:09:28Z", "role": "primary", "sha256": "e656246f09340fed08136cf41a8b79880e19e1397ddd176410688ddee4e6365c", "supports": [ "licenses.data" ], "url": "https://huggingface.co/datasets/osunlp/Dreamer-V1-Data/raw/main/README.md" } ] }, { "id": "url:a13a187bc058fbb4f6af", "name": "Go-Browse-WA processed data", "url": "https://huggingface.co/datasets/apurvaga/go-browse-wa", "environments": [ "web" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/apurvaga/go-browse-wa/raw/main/README.md", "population": "train split", "qualifier": "exact", "unit": "step records", "value": 164533 } ], "evidence_urls": [ "https://huggingface.co/datasets/apurvaga/go-browse-wa/raw/main/README.md", "https://raw.githubusercontent.com/ApGa/Go-Browse/HEAD/README.md" ], "formats": [ "Parquet" ], "modalities": [ "text", "accessibility-tree observations", "actions" ], "notes": "The card count is flattened step records, not trajectories or independent tasks. Both successful and unsuccessful trajectories are included according to the project README; no license is declared.", "splits": [ "train" ], "supervision": [ "action completion", "trajectory outcome" ] }, "licenses": { "code": null, "data": null, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T02:44:50Z", "role": "primary", "sha256": "18ab64833acf31113a83b2463359f1c7e37c4aaabfe11c33db2ba3e7d32818c6", "supports": [ "details" ], "url": "https://huggingface.co/datasets/apurvaga/go-browse-wa/raw/main/README.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T02:44:04Z", "role": "primary", "sha256": "0d4b28c993ccb977c7910ff3fecb5de29db364a7a7ad55523c8e052c9bae2566", "supports": [ "summary", "environments", "relations" ], "url": "https://raw.githubusercontent.com/ApGa/Go-Browse/HEAD/README.md" } ] }, { "id": "url:4e71dc456c4112eed727", "name": "GroundGUI RL Dataset", "url": "https://huggingface.co/datasets/PrentisAI/GroundGUI_RL", "environments": [ "desktop" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/PrentisAI/GroundGUI_RL/raw/main/README.md", "population": "RL training corpus", "qualifier": "exact", "unit": "prompts", "value": 12600 }, { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/PrentisAI/GroundGUI_RL/raw/main/README.md", "population": "RL training corpus", "qualifier": "exact", "unit": "screenshots", "value": 11205 }, { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/PrentisAI/GroundGUI_RL/raw/main/README.md", "population": "RL training corpus", "qualifier": "exact", "unit": "desktop applications", "value": 87 } ], "evidence_urls": [ "https://huggingface.co/datasets/PrentisAI/GroundGUI_RL/raw/main/README.md" ], "formats": [ "Parquet" ], "modalities": [ "screenshots", "text", "coordinates" ], "notes": "Publisher-reported counts cover a selection and reformatting of GroundCUA, not a new disjoint image collection. No independent image-overlap audit was performed.", "splits": [ "train" ], "supervision": [ "instruction-to-click grounding", "target bounding boxes" ] }, "licenses": { "code": null, "data": { "basis": "publisher model/dataset card metadata; third-party assets retain their own terms", "declared": "mit", "retrieved_at": "2026-10-17T01:48:10Z", "url": "https://huggingface.co/datasets/PrentisAI/GroundGUI_RL/raw/main/README.md" }, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T01:48:10Z", "role": "primary", "sha256": "34f0025f686d0e48e2baa5244056a4362018aaad77ac54abea7f1f6eb25c4276", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "details" ], "url": "https://huggingface.co/datasets/PrentisAI/GroundGUI_RL/raw/main/README.md" }, { "method": "huggingface_card", "retrieved_at": "2026-10-17T01:48:10Z", "role": "primary", "sha256": "34f0025f686d0e48e2baa5244056a4362018aaad77ac54abea7f1f6eb25c4276", "supports": [ "licenses.data" ], "url": "https://huggingface.co/datasets/PrentisAI/GroundGUI_RL/raw/main/README.md" } ] }, { "id": "github:showlab/gui-action-narrator", "name": "GUI-Action Narrator", "url": "https://github.com/showlab/GUI-Action-Narrator", "environments": [ "cross-platform" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://export.arxiv.org/api/query?id_list=2406.12814%2C2406.13719%2C2406.14056%2C2406.14250%2C2406.14314%2C2406.18082%2C2406.19263%2C2407.00993%2C2407.01476%2C2407.01489%2C2407.01511%2C2407.01558%2C2407.03037%2C2407.03913%2C2407.04346%2C2407.05291%2C2407.07061%2C2407.08850%2C2407.09018%2C2407.09295%2C2407.10956%2C2407.13032%2C2407.13063%2C2407.15673%2C2407.15711%2C2407.16741%2C2407.17490%2C2407.18901%2C2407.19056%2C2407.20183%2C2408.00203%2C2408.02544%2C2408.06327%2C2408.07199%2C2408.11824%2C2408.15978%2C2409.02453%2C2409.04566%2C2409.07429%2C2409.08264%2C2409.09354%2C2409.10741%2C2409.11295%2C2409.13711%2C2409.14337%2C2409.14818%2C2409.15441%2C2409.15637%2C2409.17140%2C2409.20566&max_results=50", "population": "Act2Cap benchmark described in the paper", "qualifier": "exact", "reference_url": "https://arxiv.org/abs/2406.13719", "unit": "video-captioning samples", "value": 4189 } ], "evidence_urls": [ "https://github.com/showlab/GUI-Action-Narrator", "https://export.arxiv.org/api/query?id_list=2406.12814%2C2406.13719%2C2406.14056%2C2406.14250%2C2406.14314%2C2406.18082%2C2406.19263%2C2407.00993%2C2407.01476%2C2407.01489%2C2407.01511%2C2407.01558%2C2407.03037%2C2407.03913%2C2407.04346%2C2407.05291%2C2407.07061%2C2407.08850%2C2407.09018%2C2407.09295%2C2407.10956%2C2407.13032%2C2407.13063%2C2407.15673%2C2407.15711%2C2407.16741%2C2407.17490%2C2407.18901%2C2407.19056%2C2407.20183%2C2408.00203%2C2408.02544%2C2408.06327%2C2408.07199%2C2408.11824%2C2408.15978%2C2409.02453%2C2409.04566%2C2409.07429%2C2409.08264%2C2409.09354%2C2409.10741%2C2409.11295%2C2409.13711%2C2409.14337%2C2409.14818%2C2409.15441%2C2409.15637%2C2409.17140%2C2409.20566&max_results=50" ], "formats": [], "modalities": [ "GUI video", "action captions" ], "notes": "A captioning sample is not necessarily a unique video or complete task trajectory. Package layout and split sizes were not established by the inspected sources.", "splits": [], "supervision": [ "GUI action captioning" ] }, "licenses": { "code": null, "data": null, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:40:52Z", "role": "primary", "sha256": "379aae1a8890a0c3d3b5999589b8338338cf1ea63883c2b77df678fd3bb367a2", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "details.dataset_profile" ], "url": "https://github.com/showlab/GUI-Action-Narrator" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:32Z", "role": "primary", "sha256": "b9a83994d8ac36ccdb606a5219511f8bb35ad3948ade4f9f3e28d386221aedfb", "supports": [ "details.dataset_profile" ], "url": "https://export.arxiv.org/api/query?id_list=2406.12814%2C2406.13719%2C2406.14056%2C2406.14250%2C2406.14314%2C2406.18082%2C2406.19263%2C2407.00993%2C2407.01476%2C2407.01489%2C2407.01511%2C2407.01558%2C2407.03037%2C2407.03913%2C2407.04346%2C2407.05291%2C2407.07061%2C2407.08850%2C2407.09018%2C2407.09295%2C2407.10956%2C2407.13032%2C2407.13063%2C2407.15673%2C2407.15711%2C2407.16741%2C2407.17490%2C2407.18901%2C2407.19056%2C2407.20183%2C2408.00203%2C2408.02544%2C2408.06327%2C2408.07199%2C2408.11824%2C2408.15978%2C2409.02453%2C2409.04566%2C2409.07429%2C2409.08264%2C2409.09354%2C2409.10741%2C2409.11295%2C2409.13711%2C2409.14337%2C2409.14818%2C2409.15441%2C2409.15637%2C2409.17140%2C2409.20566&max_results=50" } ] }, { "id": "url:66096ad4057a3d3726f5", "name": "GUI-Actor data", "url": "https://huggingface.co/datasets/cckevinn/GUI-Actor-Data", "environments": [ "unspecified" ], "profile": { "counts": [], "evidence_urls": [ "https://huggingface.co/datasets/cckevinn/GUI-Actor-Data/raw/main/README.md", "https://huggingface.co/api/datasets/cckevinn/GUI-Actor-Data", "https://raw.githubusercontent.com/microsoft/GUI-Actor/HEAD/data/data_config.yaml" ], "formats": [ "JSON annotations", "ZIP image packages", "multipart image archives" ], "modalities": [ "GUI screenshots", "bounding boxes", "grounding annotations" ], "notes": "Public Hub revision 5a0b35fb includes six bbox JSON files and associated image archives. The training configuration names six input paths with sampling_strategy=all; those input paths are not six disjoint datasets or a verified example count. The card’s source-list wording and mismatched hyperlinks remain unresolved, so its approximately 1M screenshots/10M elements headline is not adopted as a release inventory. No data license is established by the card, and the model repository license is not transferred to these data.", "splits": [ "training" ], "supervision": [ "GUI grounding with bounding-box supervision" ] }, "licenses": { "code": null, "data": null, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T02:42:32Z", "role": "primary", "sha256": "e42bbcf8d466c977f9b2150feb73d8cbda2ff907c279630ad4730a8b1f5d665c", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "details", "details.dataset_profile" ], "url": "https://huggingface.co/datasets/cckevinn/GUI-Actor-Data/raw/main/README.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T02:42:32Z", "role": "primary", "sha256": "d6271cff879b1a2a70490cf3dd95765bef44ecfca531d8ef3545f101673b4423", "supports": [ "identity", "release_status", "details", "licenses.data", "details.dataset_profile" ], "url": "https://huggingface.co/api/datasets/cckevinn/GUI-Actor-Data" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T14:21:12Z", "role": "primary", "sha256": "3521c849b29d7fc88430a8e73a8b2aeb2e613d7fa16ca054dd5bf4ec011b36ca", "supports": [ "details.dataset_profile" ], "url": "https://raw.githubusercontent.com/microsoft/GUI-Actor/HEAD/data/data_config.yaml" } ] }, { "id": "url:d0300db5ba754b1a64fa", "name": "GUI-CIDER causal knowledge data", "url": "https://huggingface.co/datasets/wuuuuuz/GUI-CIDER", "environments": [ "android" ], "profile": { "counts": [], "evidence_urls": [ "https://raw.githubusercontent.com/Wuzheng02/GUI-CIDER/HEAD/README.md", "https://raw.githubusercontent.com/Wuzheng02/GUI-CIDER/HEAD/data/dataset.md", "https://huggingface.co/api/datasets/wuuuuuz/GUI-CIDER" ], "formats": [ "JSONL" ], "modalities": [ "text" ], "notes": "Purpose is established by the official project, not by API tags. No sample records were downloaded; count and data-license fields remain unknown.", "splits": [], "supervision": [ "synthesized static planning knowledge", "synthesized dynamic causal knowledge" ] }, "licenses": { "code": null, "data": null, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:18:20Z", "role": "primary", "sha256": "9a46741bbde1373ed4b87887cdadde98e05ea8795d34efe39fc25d69b4d50213", "supports": [ "name", "kind", "summary", "topics", "scope", "notes", "relations", "details.dataset_profile" ], "url": "https://raw.githubusercontent.com/Wuzheng02/GUI-CIDER/HEAD/README.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:23:07Z", "role": "primary", "sha256": "aec6da0e872092d737953f8b4db227867024da10e127cd32d15d05ff95552d45", "supports": [ "identity", "release_status", "details.hub_id", "details.gated", "details.release_revision" ], "url": "https://huggingface.co/api/datasets/wuuuuuz/GUI-CIDER" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:24:47Z", "role": "primary", "sha256": "bffca456e649a08239f6a1a3be10a7d7c21bcb427e783ba2c304e4b8410d385a", "supports": [ "environments", "details.dataset_profile" ], "url": "https://raw.githubusercontent.com/Wuzheng02/GUI-CIDER/HEAD/data/dataset.md" } ] }, { "id": "url:8c9aaafb918aaf8b4e92", "name": "GUI-Net-1M", "url": "https://huggingface.co/datasets/Bofeee5675/GUI-Net-1M", "environments": [ "unspecified" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://raw.githubusercontent.com/TongUI-agent/TongUI-agent/HEAD/docs/train.md", "population": "TongUI-collected GUI-Net-1M data, excluding added external mixtures", "qualifier": "approximately", "unit": "training trajectories", "value": 1000000 } ], "evidence_urls": [ "https://huggingface.co/datasets/Bofeee5675/GUI-Net-1M/raw/main/README.md", "https://raw.githubusercontent.com/TongUI-agent/TongUI-agent/HEAD/docs/train.md" ], "formats": [ "JSON annotations", "multipart image archives" ], "modalities": [ "text", "screenshots" ], "notes": "The source reports an approximate trajectory total; it does not establish per-platform counts or a complete test-split inventory.", "splits": [ "training collection" ], "supervision": [ "GUI trajectory supervision from multimodal tutorials" ] }, "licenses": { "code": null, "data": { "basis": "Publisher declaration for this dataset packaging; original web/tutorial materials retain applicable rights.", "declared": "apache-2.0", "retrieved_at": "2026-10-17T12:32:07Z", "url": "https://huggingface.co/datasets/Bofeee5675/GUI-Net-1M/raw/main/README.md" }, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:36:55Z", "role": "primary", "sha256": "b51acb70c95d079ccbe1de0a685ad7c8a4b3b5bed11e6162e6f7c2f60d78805e", "supports": [ "summary", "details.dataset_profile" ], "url": "https://raw.githubusercontent.com/TongUI-agent/TongUI-agent/HEAD/docs/train.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:32:07Z", "role": "primary", "sha256": "c2df5c3a6dd576ae53f0dc0f72ecab07d93ed034b04336abd2072a6f0d812c64", "supports": [ "licenses.data", "details.dataset_profile.formats", "notes" ], "url": "https://huggingface.co/datasets/Bofeee5675/GUI-Net-1M/raw/main/README.md" } ] }, { "id": "github:opengvlab/gui-odyssey", "name": "GUI-Odyssey", "url": "https://github.com/OpenGVLab/GUI-Odyssey", "environments": [ "android" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/hflqf88888/GUIOdyssey/raw/main/README.md", "population": "recommended hflqf88888/GUIOdyssey release", "qualifier": "exact", "unit": "episodes", "value": 8334 } ], "evidence_urls": [ "https://raw.githubusercontent.com/OpenGVLab/GUI-Odyssey/HEAD/README.md", "https://huggingface.co/datasets/hflqf88888/GUIOdyssey/raw/main/README.md", "https://raw.githubusercontent.com/OpenGVLab/GUI-Odyssey/HEAD/introduction.md" ], "formats": [ "JSON annotations", "PNG screenshots" ], "modalities": [ "screenshots", "instructions", "actions", "bounding boxes", "step context" ], "notes": "The repository gives conflicting episode totals (8,334 and 8,834). This profile uses 8,334 from the specifically recommended current dataset card. No independent archive recount was performed. Coordinates are normalized to 0–1000.", "splits": [ "random", "task", "device", "app" ], "supervision": [ "cross-app trajectories", "action grounding" ] }, "licenses": { "code": null, "data": null, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:01Z", "role": "primary", "sha256": "4585b765d7c8b3e9bb6187d36d576edde454d4c0158a6aa8b3fdbedf34c89a15", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "details.dataset_profile" ], "url": "https://raw.githubusercontent.com/OpenGVLab/GUI-Odyssey/HEAD/README.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T11:39:52Z", "role": "primary", "sha256": "fd627ee0a6ee0596e0ee8147996b9a7a3436f754fc95ed63cf5f408d778b2831", "supports": [ "details.dataset_profile" ], "url": "https://huggingface.co/datasets/hflqf88888/GUIOdyssey/raw/main/README.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T11:39:52Z", "role": "primary", "sha256": "78c19ee712487af60df1913f11572958564e59a1a2cc663b1b30d971855d7a28", "supports": [ "details.dataset_profile" ], "url": "https://raw.githubusercontent.com/OpenGVLab/GUI-Odyssey/HEAD/introduction.md" } ] }, { "id": "github:dongping-chen/gui-world", "name": "GUI-World", "url": "https://github.com/Dongping-Chen/GUI-World", "environments": [ "cross-platform" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://raw.githubusercontent.com/Dongping-Chen/GUI-World/master/Readme.md", "population": "dataset taxonomy", "qualifier": "exact", "unit": "GUI scenario categories", "value": 6 }, { "basis": "reported", "evidence_url": "https://raw.githubusercontent.com/Dongping-Chen/GUI-World/master/Readme.md", "population": "dataset taxonomy", "qualifier": "exact", "unit": "question types", "value": 8 } ], "evidence_urls": [ "https://raw.githubusercontent.com/Dongping-Chen/GUI-World/master/Readme.md", "https://huggingface.co/datasets/ONE-Lab/GUI-World/raw/main/README.md", "https://export.arxiv.org/api/query?id_list=2403.03186%2C2403.03788%2C2403.07718%2C2403.10170%2C2403.11905%2C2403.16971%2C2403.17918%2C2403.20271%2C2404.01549%2C2404.01744%2C2404.02475%2C2404.03648%2C2404.05427%2C2404.05719%2C2404.05955%2C2404.06474%2C2404.07972%2C2404.08755%2C2404.08860%2C2404.08948%2C2404.09992%2C2404.10887%2C2404.11459%2C2404.16006%2C2404.16048%2C2404.16054%2C2404.16660%2C2404.18074%2C2404.19296%2C2405.00516%2C2405.11120%2C2405.12842%2C2405.14573%2C2405.14751%2C2405.15793%2C2405.16247%2C2405.20309%2C2406.01014%2C2406.01623%2C2406.03679%2C2406.06947%2C2406.07822%2C2406.08184%2C2406.08340%2C2406.08451%2C2406.10227%2C2406.10819%2C2406.11317%2C2406.11896%2C2406.12373&max_results=50" ], "formats": [], "modalities": [ "videos", "frame images", "text" ], "notes": "Taxonomy counts describe coverage, not the number of videos or questions. Cases include Android, iOS, desktop software, websites, multi-application use, and XR. Keyframe-selection settings affect evaluation; exact sample inventories are not reported here.", "splits": [ "train", "test" ], "supervision": [ "GUI video question answering", "temporal interface understanding" ] }, "licenses": { "code": null, "data": null, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T02:03:23Z", "role": "primary", "sha256": "905bf69ce80c866377841474cefe08f85ec4ef552cdd9ffeb2fb1531e07370b6", "supports": [ "details.dataset_profile" ], "url": "https://raw.githubusercontent.com/Dongping-Chen/GUI-World/master/Readme.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T02:06:30Z", "role": "primary", "sha256": "d2dd5886bce90f6eaee880719c79a6ede6ec0eaa08da32d7610bde656b8dc9ed", "supports": [ "details.dataset_profile" ], "url": "https://huggingface.co/datasets/ONE-Lab/GUI-World/raw/main/README.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:31:28Z", "role": "primary", "sha256": "be244bfae7f89ef9449b69d85aac44295eb7b5f7e5e1bbedd76df312696676a7", "supports": [ "details.dataset_profile" ], "url": "https://export.arxiv.org/api/query?id_list=2403.03186%2C2403.03788%2C2403.07718%2C2403.10170%2C2403.11905%2C2403.16971%2C2403.17918%2C2403.20271%2C2404.01549%2C2404.01744%2C2404.02475%2C2404.03648%2C2404.05427%2C2404.05719%2C2404.05955%2C2404.06474%2C2404.07972%2C2404.08755%2C2404.08860%2C2404.08948%2C2404.09992%2C2404.10887%2C2404.11459%2C2404.16006%2C2404.16048%2C2404.16054%2C2404.16660%2C2404.18074%2C2404.19296%2C2405.00516%2C2405.11120%2C2405.12842%2C2405.14573%2C2405.14751%2C2405.15793%2C2405.16247%2C2405.20309%2C2406.01014%2C2406.01623%2C2406.03679%2C2406.06947%2C2406.07822%2C2406.08184%2C2406.08340%2C2406.08451%2C2406.10227%2C2406.10819%2C2406.11317%2C2406.11896%2C2406.12373&max_results=50" } ] }, { "id": "url:6cd150ec23361b4d2e84", "name": "GUIAct", "url": "https://huggingface.co/datasets/yiye2023/GUIAct", "environments": [ "web", "android" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://raw.githubusercontent.com/yiye3/GUICourse/HEAD/README.md", "population": "single-step portion", "qualifier": "approximately", "unit": "action instructions", "value": 67000 }, { "basis": "reported", "evidence_url": "https://raw.githubusercontent.com/yiye3/GUICourse/HEAD/README.md", "population": "multi-step portion", "qualifier": "approximately", "unit": "action instructions", "value": 15000 } ], "evidence_urls": [ "https://raw.githubusercontent.com/yiye3/GUICourse/HEAD/README.md" ], "formats": [ "JSON", "Parquet" ], "modalities": [ "screenshots", "instructions", "actions" ], "notes": "Quantities are rounded publisher descriptions, not downloaded sample counts. Data-license declarations conflict across first-party sources; no permissive license is inferred.", "splits": [ "train", "test" ], "supervision": [ "single-step actions", "multi-step navigation" ] }, "licenses": { "code": null, "data": null, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:01Z", "role": "primary", "sha256": "0968273442bfb9a6478fe78f8b9a6247a3bb8e6d028880939b432fd009961e98", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "details", "licenses.data" ], "url": "https://raw.githubusercontent.com/yiye3/GUICourse/HEAD/README.md" } ] }, { "id": "url:edf38d43800be8c955ae", "name": "GUIChat", "url": "https://huggingface.co/datasets/yiye2023/GUIChat", "environments": [ "unspecified" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://raw.githubusercontent.com/yiye3/GUICourse/HEAD/README.md", "population": "single-turn portion", "qualifier": "approximately", "unit": "QA pairs", "value": 44000 }, { "basis": "reported", "evidence_url": "https://raw.githubusercontent.com/yiye3/GUICourse/HEAD/README.md", "population": "multi-turn portion", "qualifier": "approximately", "unit": "dialogues", "value": 6000 } ], "evidence_urls": [ "https://raw.githubusercontent.com/yiye3/GUICourse/HEAD/README.md" ], "formats": [ "JSON", "Parquet" ], "modalities": [ "screenshots", "text", "bounding boxes" ], "notes": "Quantities are rounded publisher descriptions, not downloaded sample counts. Data-license declarations conflict across first-party sources; no permissive license is inferred.", "splits": [], "supervision": [ "single-turn question answering", "multi-turn dialogue" ] }, "licenses": { "code": null, "data": null, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:01Z", "role": "primary", "sha256": "0968273442bfb9a6478fe78f8b9a6247a3bb8e6d028880939b432fd009961e98", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "details", "licenses.data" ], "url": "https://raw.githubusercontent.com/yiye3/GUICourse/HEAD/README.md" } ] }, { "id": "url:0af07e00658a430cee6a", "name": "GUIEnv-local", "url": "https://huggingface.co/datasets/yiye2023/GUIEnv", "environments": [ "web" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://raw.githubusercontent.com/yiye3/GUICourse/HEAD/README.md", "population": "GUIEnv-local SFT data", "qualifier": "approximately", "unit": "region-text QA pairs", "value": 700000 } ], "evidence_urls": [ "https://raw.githubusercontent.com/yiye3/GUICourse/HEAD/README.md" ], "formats": [ "JSON", "Parquet" ], "modalities": [ "screenshots", "text", "bounding boxes" ], "notes": "Quantities are rounded publisher descriptions, not downloaded sample counts. Data-license declarations conflict across first-party sources; no permissive license is inferred.", "splits": [ "train", "test" ], "supervision": [ "OCR", "region-text grounding" ] }, "licenses": { "code": null, "data": null, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:01Z", "role": "primary", "sha256": "0968273442bfb9a6478fe78f8b9a6247a3bb8e6d028880939b432fd009961e98", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "details", "licenses.data" ], "url": "https://raw.githubusercontent.com/yiye3/GUICourse/HEAD/README.md" } ] }, { "id": "url:422010da7a5c845a18f6", "name": "GUIMid training data", "url": "https://huggingface.co/datasets/hkust-nlp/GUIMid", "environments": [ "web", "android" ], "profile": { "counts": [], "evidence_urls": [ "https://huggingface.co/datasets/hkust-nlp/GUIMid/raw/main/README.md", "https://raw.githubusercontent.com/hkust-nlp/GUIMid/HEAD/README.md" ], "formats": [ "JSON", "tar.gz image archives" ], "modalities": [ "text", "images" ], "notes": "Do not treat Hub size bands or the inconsistent introductory task count as a sample total. Some constituent-domain image packages remain forthcoming.", "splits": [ "train configurations for named mid-training domains" ], "supervision": [ "mid-training instruction supervision", "GUI post-training trajectories" ] }, "licenses": { "code": null, "data": { "basis": "Publisher dataset-card declaration for the released packaging; original source datasets retain their own terms.", "declared": "mit", "retrieved_at": "2026-10-17T11:23:07Z", "url": "https://huggingface.co/datasets/hkust-nlp/GUIMid/raw/main/README.md" }, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:23:07Z", "role": "primary", "sha256": "1cdf702c819ecf370f4191c6c71fae7b579cfbaf766908b42156964a69eddacc", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "notes", "relations", "details.dataset_profile", "licenses.data" ], "url": "https://huggingface.co/datasets/hkust-nlp/GUIMid/raw/main/README.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T11:18:19Z", "role": "primary", "sha256": "d9f63a03088c37f7145725c7a182100d1593fceadd26a9bf817d434ca8d6297e", "supports": [ "notes", "relations" ], "url": "https://raw.githubusercontent.com/hkust-nlp/GUIMid/HEAD/README.md" } ] }, { "id": "url:511903ebfac45e6751b2", "name": "GUIOdyssey — current data release", "url": "https://huggingface.co/datasets/hflqf88888/GUIOdyssey", "environments": [ "android" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/hflqf88888/GUIOdyssey/raw/main/README.md", "population": "recommended hflqf88888/GUIOdyssey release", "qualifier": "exact", "unit": "episodes", "value": 8334 } ], "evidence_urls": [ "https://raw.githubusercontent.com/OpenGVLab/GUI-Odyssey/HEAD/README.md", "https://huggingface.co/datasets/hflqf88888/GUIOdyssey/raw/main/README.md", "https://raw.githubusercontent.com/OpenGVLab/GUI-Odyssey/HEAD/introduction.md" ], "formats": [ "JSON annotations", "PNG screenshots" ], "modalities": [ "screenshots", "instructions", "actions", "bounding boxes", "step context" ], "notes": "The repository gives conflicting episode totals (8,334 and 8,834). This profile uses 8,334 from the specifically recommended current dataset card. No independent archive recount was performed. Coordinates are normalized to 0–1000.", "splits": [ "random", "task", "device", "app" ], "supervision": [ "cross-app trajectories", "action grounding" ] }, "licenses": { "code": null, "data": { "basis": "publisher model/dataset card metadata; third-party assets retain their own terms", "declared": "cc-by-4.0", "retrieved_at": "2026-10-16T11:39:52Z", "url": "https://huggingface.co/datasets/hflqf88888/GUIOdyssey/raw/main/README.md" }, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T11:39:52Z", "role": "primary", "sha256": "fd627ee0a6ee0596e0ee8147996b9a7a3436f754fc95ed63cf5f408d778b2831", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "details" ], "url": "https://huggingface.co/datasets/hflqf88888/GUIOdyssey/raw/main/README.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:01Z", "role": "primary", "sha256": "4585b765d7c8b3e9bb6187d36d576edde454d4c0158a6aa8b3fdbedf34c89a15", "supports": [ "details.dataset_profile" ], "url": "https://raw.githubusercontent.com/OpenGVLab/GUI-Odyssey/HEAD/README.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T11:39:52Z", "role": "primary", "sha256": "78c19ee712487af60df1913f11572958564e59a1a2cc663b1b30d971855d7a28", "supports": [ "details.dataset_profile" ], "url": "https://raw.githubusercontent.com/OpenGVLab/GUI-Odyssey/HEAD/introduction.md" }, { "method": "huggingface_card", "retrieved_at": "2026-10-16T11:39:52Z", "role": "primary", "sha256": "fd627ee0a6ee0596e0ee8147996b9a7a3436f754fc95ed63cf5f408d778b2831", "supports": [ "licenses.data" ], "url": "https://huggingface.co/datasets/hflqf88888/GUIOdyssey/raw/main/README.md" } ] }, { "id": "url:e062cf1445eaee0f3ade", "name": "Jedi", "url": "https://huggingface.co/datasets/xlangai/Jedi", "environments": [ "desktop" ], "profile": { "counts": [], "evidence_urls": [ "https://huggingface.co/datasets/xlangai/Jedi/raw/main/README.md" ], "formats": [], "modalities": [ "images", "text", "coordinates" ], "notes": "Coordinates were resized for a specified Qwen2.5-VL image processor and must remain aligned with image resizing. AGUVIS++ material requires images from upstream AGUVIS and OS-Atlas releases; this repository is not a self-contained copy of every referenced image collection.", "splits": [], "supervision": [ "icon grounding", "component grounding", "layout grounding", "refusal" ] }, "licenses": { "code": null, "data": { "basis": "publisher model/dataset card", "declared": "apache-2.0", "retrieved_at": "2026-10-16T09:33:18Z", "url": "https://huggingface.co/datasets/xlangai/Jedi" }, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T02:02:38Z", "role": "primary", "sha256": "1d4d15c0cd27837602d55f0fda1ed91d9e8a98b33b3e3c4ba64decae42399558", "supports": [ "details.dataset_profile" ], "url": "https://huggingface.co/datasets/xlangai/Jedi/raw/main/README.md" } ] }, { "id": "url:b80bfa0a4939a493a11f", "name": "Mobile3M", "url": "https://huggingface.co/datasets/xwk123/Mobile3M", "environments": [ "android" ], "profile": { "counts": [], "evidence_urls": [ "https://huggingface.co/datasets/xwk123/Mobile3M/raw/3df26694ff9186604eb44a8e633894d3ece67ed9/README.md", "https://huggingface.co/api/datasets/xwk123/Mobile3M", "https://raw.githubusercontent.com/XiaoMi/mobilevlm/HEAD/README.md" ], "formats": [ "7z app-graph archives", "multipart 7z files" ], "modalities": [], "notes": "Official README calls this a partial training release and says app data will be uploaded gradually. Its training-JSON and test-data links point to separate Hub repositories; those artifacts are not counted as files or splits of xwk123/Mobile3M. Public revision 3df26694 lists app-graph archives; their names do not establish a three-million-example downloadable inventory. Precise inner record/modalities schema is not inspected. The card YAML says Apache-2.0 while its prose and official README assign CC-BY-NC-SA-4.0 to data and Apache to code; the existing data-license value remains unknown with the conflict documented.", "splits": [ "partial training release" ], "supervision": [ "mobile UI pretraining for MobileVLM" ] }, "licenses": { "code": null, "data": null, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:38:26Z", "role": "primary", "sha256": "356a8dca28fa3dc46bc05b13eaf04a3db273e63c06be4fd15d0e87e0343c0824", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "licenses.data", "details.dataset_profile" ], "url": "https://huggingface.co/api/datasets/xwk123/Mobile3M" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T14:10:01Z", "role": "primary", "sha256": "8a097dbc7384d3743f262dc0164c176ed577bf720cbbc92ff8b3cd820d1aed4f", "supports": [ "details.dataset_profile", "relations" ], "url": "https://huggingface.co/datasets/xwk123/Mobile3M/raw/3df26694ff9186604eb44a8e633894d3ece67ed9/README.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T14:22:04Z", "role": "primary", "sha256": "e8a92a783b6b65cacedf105e5ede583668f8774f2a81a2005dc6897da6fa88ef", "supports": [ "details.dataset_profile" ], "url": "https://raw.githubusercontent.com/XiaoMi/mobilevlm/HEAD/README.md" }, { "method": "huggingface_api", "retrieved_at": "2026-10-16T06:38:26Z", "role": "primary", "sha256": "356a8dca28fa3dc46bc05b13eaf04a3db273e63c06be4fd15d0e87e0343c0824", "supports": [ "details", "licenses.data" ], "url": "https://huggingface.co/api/datasets/xwk123/Mobile3M" } ] }, { "id": "url:cc4aa8caeee0cff58e73", "name": "MobileViews", "url": "https://huggingface.co/datasets/mllmTeam/MobileViews", "environments": [ "android" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/mllmTeam/MobileViews/raw/c734715eb90a8f3ac0c80973f93ee63950e5a8c8/README.md", "population": "publisher-reported MobileViews-600K first release", "qualifier": "more-than", "unit": "screenshot–view-hierarchy pairs", "value": 600000 }, { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/mllmTeam/MobileViews/raw/c734715eb90a8f3ac0c80973f93ee63950e5a8c8/README.md", "population": "publisher-reported MobileViews-600K first release", "qualifier": "more-than", "unit": "Android apps", "value": 20000 } ], "evidence_urls": [ "https://huggingface.co/datasets/mllmTeam/MobileViews/raw/c734715eb90a8f3ac0c80973f93ee63950e5a8c8/README.md", "https://huggingface.co/api/datasets/mllmTeam/MobileViews" ], "formats": [ "JPEG", "JSON", "XML", "Parquet", "CSV", "ZIP packages", "HTML/JavaScript trace visualization" ], "modalities": [ "screenshots", "view hierarchies", "action traces", "app metadata" ], "notes": "Counts describe the card’s first-release claim, not an independently counted archive inventory. The card distinguishes globally image-hash-deduplicated screenshot/VH pairs from the November 2024 complete-app traces; trace state counts must not be added as new unique screens. JPEG/JSON and Parquet are alternative representations. Listed filename ranges are examples, not a complete count proof. No train/validation/test split is documented. Hub revision c734715e is ungated; MIT is its data declaration, without resolving third-party app content rights.", "splits": [], "supervision": [ "paired screenshot/view-hierarchy structure", "recorded app states, actions and transitions" ] }, "licenses": { "code": null, "data": { "basis": "publisher model/dataset card", "declared": "mit", "retrieved_at": "2026-10-16T06:38:26Z", "url": "https://huggingface.co/datasets/mllmTeam/MobileViews" }, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:38:26Z", "role": "primary", "sha256": "d36d62283deecd3c5ccf1ac1af49aa7ba779a1d69cdcaea39a1bed37ff5d66b9", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "details.dataset_profile" ], "url": "https://huggingface.co/api/datasets/mllmTeam/MobileViews" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T14:10:01Z", "role": "primary", "sha256": "94a4f04e180dbd597c271b0d7470c907e6526b95a6420f01b3183feb1ee24d6e", "supports": [ "details.dataset_profile" ], "url": "https://huggingface.co/datasets/mllmTeam/MobileViews/raw/c734715eb90a8f3ac0c80973f93ee63950e5a8c8/README.md" }, { "method": "huggingface_api", "retrieved_at": "2026-10-16T06:38:26Z", "role": "primary", "sha256": "d36d62283deecd3c5ccf1ac1af49aa7ba779a1d69cdcaea39a1bed37ff5d66b9", "supports": [ "details", "licenses.data" ], "url": "https://huggingface.co/api/datasets/mllmTeam/MobileViews" } ] }, { "id": "url:570654ff67ecefa2b955", "name": "MONDAY annotations", "url": "https://huggingface.co/datasets/runamu/MONDAY", "environments": [ "android", "ios" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/runamu/MONDAY/raw/main/README.md", "population": "train split", "qualifier": "exact", "unit": "video annotation records", "value": 19725 }, { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/runamu/MONDAY/raw/main/README.md", "population": "validation split", "qualifier": "exact", "unit": "video annotation records", "value": 495 }, { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/runamu/MONDAY/raw/main/README.md", "population": "test split", "qualifier": "exact", "unit": "video annotation records", "value": 100 }, { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/runamu/MONDAY/raw/main/README.md", "population": "test_unseen_os split", "qualifier": "exact", "unit": "video annotation records", "value": 50 }, { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/runamu/MONDAY/raw/main/README.md", "population": "publisher overview of MONDAY", "qualifier": "approximately", "unit": "detected scenes", "value": 333000 }, { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/runamu/MONDAY/raw/main/README.md", "population": "publisher overview of MONDAY", "qualifier": "approximately", "unit": "identified actions", "value": 313000 } ], "evidence_urls": [ "https://huggingface.co/datasets/runamu/MONDAY/raw/main/README.md", "https://raw.githubusercontent.com/runamu/monday/HEAD/README.md" ], "formats": [ "Parquet" ], "modalities": [ "text", "timestamps", "bounding boxes", "action labels" ], "notes": "Split counts are video-annotation rows; scene and action totals are rounded publisher reports and are not added to row counts. Source videos/images are not included in the Hub files.", "splits": [ "train", "validation", "test", "test_unseen_os" ], "supervision": [ "video-derived scene and action annotations" ] }, "licenses": { "code": null, "data": null, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:32:07Z", "role": "primary", "sha256": "62a346fd0d328deb5b56a652c8581850b0c8120f5c77e53b33f24b9baf937adb", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "notes", "relations", "details.dataset_profile", "licenses.data" ], "url": "https://huggingface.co/datasets/runamu/MONDAY/raw/main/README.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:30:53Z", "role": "primary", "sha256": "cb3d2329571a80b6edeab98c04f8b63c7f4e976929788d6a8283238b0b7fdadc", "supports": [ "notes", "details.dataset_profile", "licenses.data" ], "url": "https://raw.githubusercontent.com/runamu/monday/HEAD/README.md" } ] }, { "id": "github:aburns4/motif", "name": "MoTIF", "url": "https://github.com/aburns4/MoTIF", "environments": [ "android" ], "profile": { "counts": [], "evidence_urls": [ "https://raw.githubusercontent.com/aburns4/MoTIF/HEAD/README.md" ], "formats": [ "JSON metadata", "screen images" ], "modalities": [ "screenshots", "view hierarchies", "language", "interaction sequences", "feasibility labels" ], "notes": "The raw collection mixes action, language, exploration, and unusable/other traces. These groups have different annotation coverage; not every raw trace is a valid task demonstration.", "splits": [], "supervision": [ "interaction trajectories", "task feasibility" ] }, "licenses": { "code": null, "data": null, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:01Z", "role": "primary", "sha256": "4b2f5a23dc28e96b671272380b953e7fabaf34f4b1e83f3513643846718e3389", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "details.dataset_profile" ], "url": "https://raw.githubusercontent.com/aburns4/MoTIF/HEAD/README.md" } ] }, { "id": "url:bdfb50330deb97893ce4", "name": "MT-Mind2Web", "url": "https://huggingface.co/datasets/magicgh/MT-Mind2Web", "environments": [ "web" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/magicgh/MT-Mind2Web/raw/main/README.md", "population": "train", "qualifier": "exact", "unit": "conversations", "value": 600 }, { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/magicgh/MT-Mind2Web/raw/main/README.md", "population": "test-task", "qualifier": "exact", "unit": "conversations", "value": 34 }, { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/magicgh/MT-Mind2Web/raw/main/README.md", "population": "test-website", "qualifier": "exact", "unit": "conversations", "value": 42 }, { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/magicgh/MT-Mind2Web/raw/main/README.md", "population": "test-subdomain", "qualifier": "exact", "unit": "conversations", "value": 44 }, { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/magicgh/MT-Mind2Web/raw/main/README.md", "population": "train", "qualifier": "exact", "unit": "dialogue turns", "value": 2896 }, { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/magicgh/MT-Mind2Web/raw/main/README.md", "population": "test-task", "qualifier": "exact", "unit": "dialogue turns", "value": 191 }, { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/magicgh/MT-Mind2Web/raw/main/README.md", "population": "test-website", "qualifier": "exact", "unit": "dialogue turns", "value": 218 }, { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/magicgh/MT-Mind2Web/raw/main/README.md", "population": "test-subdomain", "qualifier": "exact", "unit": "dialogue turns", "value": 216 } ], "evidence_urls": [ "https://huggingface.co/datasets/magicgh/MT-Mind2Web/raw/main/README.md" ], "formats": [ "JSON", "auxiliary PKL" ], "modalities": [ "dialogue text", "HTML", "element candidates", "actions" ], "notes": "Conversation, dialogue-turn and action-step units differ. The released file manifest is inspected; underlying examples were not downloaded.", "splits": [ "train", "test_task", "test_website", "test_subdomain" ], "supervision": [ "multi-turn web instruction following", "element/action prediction" ] }, "licenses": { "code": null, "data": { "basis": "Publisher dataset-card declaration for the multi-turn annotation release.", "declared": "cc-by-4.0", "retrieved_at": "2026-10-17T12:34:10Z", "url": "https://huggingface.co/datasets/magicgh/MT-Mind2Web/raw/main/README.md" }, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:34:10Z", "role": "primary", "sha256": "8685e0a26a06b3339b5c078632a7b0ade1ead40e6b586ef1ff3676414699a4bc", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "notes", "details.dataset_profile", "licenses.data" ], "url": "https://huggingface.co/datasets/magicgh/MT-Mind2Web/raw/main/README.md" } ] }, { "id": "github:neulab/multiui", "name": "MultiUI", "url": "https://github.com/neulab/multiui", "environments": [ "web" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://raw.githubusercontent.com/neulab/multiui/HEAD/README.md", "population": "reported MultiUI training collection", "qualifier": "approximately", "unit": "samples", "value": 7300000 } ], "evidence_urls": [ "https://raw.githubusercontent.com/neulab/multiui/HEAD/README.md" ], "formats": [], "modalities": [ "webpage UI content", "text", "accessibility-derived structure" ], "notes": "The README provides a rounded sample count. It does not establish a unique-screenshot inventory or a normalized split breakdown. Synthetic examples and publicly sourced web content have provenance and quality limits; data terms must be checked separately from repository code.", "splits": [ "training collection" ], "supervision": [ "UI understanding", "text-rich visual tasks" ] }, "licenses": { "code": null, "data": null, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:01Z", "role": "primary", "sha256": "fe0c03fe73529a29788d559103c4aed48dca6ed9ba3bfd5f151f902fa8858b38", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "details" ], "url": "https://raw.githubusercontent.com/neulab/multiui/HEAD/README.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:01Z", "role": "primary", "sha256": "fe0c03fe73529a29788d559103c4aed48dca6ed9ba3bfd5f151f902fa8858b38", "supports": [ "details.dataset_profile" ], "url": "https://raw.githubusercontent.com/neulab/multiui/HEAD/README.md" } ] }, { "id": "url:546e6c95825d1318c98d", "name": "OpenMobile-Data-v2", "url": "https://huggingface.co/datasets/OpenMobile-2/OpenMobile-Data-v2", "environments": [ "android", "web" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/OpenMobile-2/OpenMobile-Data-v2/raw/main/README.md", "population": "SFT collection", "qualifier": "exact", "unit": "trajectories", "value": 11643 }, { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/OpenMobile-2/OpenMobile-Data-v2/raw/main/README.md", "population": "SFT collection", "qualifier": "exact", "unit": "decision steps", "value": 118582 }, { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/OpenMobile-2/OpenMobile-Data-v2/raw/main/README.md", "population": "RL collection", "qualifier": "exact", "unit": "executable tasks", "value": 2475 } ], "evidence_urls": [ "https://huggingface.co/datasets/OpenMobile-2/OpenMobile-Data-v2/raw/main/README.md" ], "formats": [ "JSON", "JSONL", "PNG" ], "modalities": [ "screenshots", "text", "tool calls" ], "notes": "These are publisher-reported totals at three distinct grains, not values to sum. Earlier screenshots may be collapsed; each SFT example keeps at most three images. The card and repository disagree on the singular/plural RL filename, so consumers should inspect the actual file manifest.", "splits": [ "sft/train", "rl/train" ], "supervision": [ "next-action supervision", "verifiable task outcomes" ] }, "licenses": { "code": null, "data": null, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T01:48:51Z", "role": "primary", "sha256": "abacf9a10759a9e7a8eeec5a266c96ed83742bd9296a19be95d09c9717e18b7c", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "details" ], "url": "https://huggingface.co/datasets/OpenMobile-2/OpenMobile-Data-v2/raw/main/README.md" } ] }, { "id": "url:0fdeb1cf5f49f84820e6", "name": "OS-Atlas Data", "url": "https://huggingface.co/datasets/OS-Copilot/OS-Atlas-data", "environments": [ "cross-platform" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/OS-Copilot/OS-Atlas-data/raw/main/README.md", "population": "SeeClick-derived web subset", "qualifier": "more-than", "unit": "screenshots", "value": 270000 }, { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/OS-Copilot/OS-Atlas-data/raw/main/README.md", "population": "SeeClick-derived web subset", "qualifier": "more-than", "unit": "UI elements", "value": 3000000 }, { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/OS-Copilot/OS-Atlas-data/raw/main/README.md", "population": "FineWeb-derived subset", "qualifier": "at-least", "unit": "images", "value": 1600000 } ], "evidence_urls": [ "https://huggingface.co/datasets/OS-Copilot/OS-Atlas-data/raw/main/README.md" ], "formats": [ "JSON annotations", "image archives" ], "modalities": [ "screenshots", "referring expressions", "bounding boxes" ], "notes": "These are subset-specific counts, not a total for the full OS-Atlas release. Raw boxes use 0–1 coordinates; the documented training wrapper scales them to 0–1000.", "splits": [], "supervision": [ "element grounding" ] }, "licenses": { "code": null, "data": { "basis": "publisher model/dataset card", "declared": "apache-2.0", "retrieved_at": "2026-10-16T06:38:26Z", "url": "https://huggingface.co/datasets/OS-Copilot/OS-Atlas-data" }, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T11:40:46Z", "role": "primary", "sha256": "19f28b4bc0798e28180b968010c0f7c8dfed2dbfb24b122b958476b871d2e4fd", "supports": [ "details.dataset_profile" ], "url": "https://huggingface.co/datasets/OS-Copilot/OS-Atlas-data/raw/main/README.md" } ] }, { "id": "github:os-copilot/os-genesis", "name": "OS-Genesis", "url": "https://github.com/OS-Copilot/OS-Genesis", "environments": [ "cross-platform" ], "profile": { "counts": [], "evidence_urls": [ "https://raw.githubusercontent.com/OS-Copilot/OS-Genesis/HEAD/README.md", "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=800&max_results=100&sortBy=submittedDate&sortOrder=descending" ], "formats": [ "JSONL trajectories", "JSON transition triples" ], "modalities": [ "screenshots", "text", "actions" ], "notes": "The repository links distinct AndroidControl-oriented, AndroidWorld-oriented, and web training files plus raw pre-state/action/post-state triples. These are training artifacts, not a documented train/test split, and related representations are not disjoint corpus totals. No numerical inventory is asserted from release names or linked archives.", "splits": [], "supervision": [ "reverse task synthesis", "GUI action trajectories" ] }, "licenses": { "code": null, "data": null, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:01Z", "role": "primary", "sha256": "430e495ab250395d666854bd18b0fc29b819cd784cd7730215ef65e461834d0d", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "details" ], "url": "https://raw.githubusercontent.com/OS-Copilot/OS-Genesis/HEAD/README.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:01Z", "role": "primary", "sha256": "430e495ab250395d666854bd18b0fc29b819cd784cd7730215ef65e461834d0d", "supports": [ "details.dataset_profile" ], "url": "https://raw.githubusercontent.com/OS-Copilot/OS-Genesis/HEAD/README.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:58Z", "role": "primary", "sha256": "c87e97eb397da04806d53145cf9c13be739fc657bb54dca9318c8c4ed2a36249", "supports": [ "details.dataset_profile" ], "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=800&max_results=100&sortBy=submittedDate&sortOrder=descending" } ] }, { "id": "url:d3ec5122a2b52fd5ae4b", "name": "OS-Genesis mobile training data", "url": "https://huggingface.co/datasets/OS-Copilot/OS-Genesis-mobile-data", "environments": [ "android" ], "profile": { "counts": [], "evidence_urls": [ "https://huggingface.co/datasets/OS-Copilot/OS-Genesis-mobile-data/raw/main/README.md", "https://huggingface.co/api/datasets/OS-Copilot/OS-Genesis-mobile-data", "https://raw.githubusercontent.com/OS-Copilot/OS-Genesis/HEAD/README.md" ], "formats": [ "JSONL", "ZIP" ], "modalities": [ "screenshots", "text", "actions" ], "notes": "AC and AW refer to distinct target training sets; no sample count is inferred from the two JSONL files or ZIP packaging.", "splits": [ "AndroidControl training", "AndroidWorld training" ], "supervision": [ "mobile action trajectories" ] }, "licenses": { "code": null, "data": { "basis": "publisher model/dataset card metadata; third-party assets retain their own terms", "declared": "mit", "retrieved_at": "2026-10-17T04:01:34Z", "url": "https://huggingface.co/datasets/OS-Copilot/OS-Genesis-mobile-data/raw/main/README.md" }, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:01:34Z", "role": "primary", "sha256": "de9de63e21e60e882277a6268e8153abb6c14aaf3e9a7f83e7f98ac14bf37170", "supports": [ "name", "kind", "relations", "licenses.data" ], "url": "https://huggingface.co/datasets/OS-Copilot/OS-Genesis-mobile-data/raw/main/README.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:01:33Z", "role": "primary", "sha256": "6a5e0c2baecc2dc8bf4466903798f5ecda07cdac917042bbd4cfbe54d895c11e", "supports": [ "identity", "release_status", "details", "licenses.data" ], "url": "https://huggingface.co/api/datasets/OS-Copilot/OS-Genesis-mobile-data" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:01Z", "role": "primary", "sha256": "430e495ab250395d666854bd18b0fc29b819cd784cd7730215ef65e461834d0d", "supports": [ "summary", "environments", "topics", "scope" ], "url": "https://raw.githubusercontent.com/OS-Copilot/OS-Genesis/HEAD/README.md" }, { "method": "huggingface_card", "retrieved_at": "2026-10-17T04:01:34Z", "role": "primary", "sha256": "de9de63e21e60e882277a6268e8153abb6c14aaf3e9a7f83e7f98ac14bf37170", "supports": [ "licenses.data" ], "url": "https://huggingface.co/datasets/OS-Copilot/OS-Genesis-mobile-data/raw/main/README.md" } ] }, { "id": "url:14449fe321e0a1ca34ea", "name": "PC-Agent-E training data", "url": "https://huggingface.co/datasets/henryhe0123/PC-Agent-E", "environments": [ "desktop", "windows", "linux" ], "profile": { "counts": [], "evidence_urls": [ "https://raw.githubusercontent.com/GAIR-NLP/PC-Agent-E/HEAD/README.md", "https://huggingface.co/api/datasets/henryhe0123/PC-Agent-E" ], "formats": [ "ZIP package" ], "modalities": [ "GUI screenshots", "action trajectories", "generated reasoning" ], "notes": "Public manifest exposes data.zip; the internal file schema and number of examples remain unverified. Supervision describes the publisher’s refinement/thought-completion/trajectory-boost pipeline, not an independently sampled data-quality audit.", "splits": [ "training" ], "supervision": [ "human demonstration refinement", "generated action reasoning", "trajectory augmentation" ] }, "licenses": { "code": null, "data": { "basis": "Publisher dataset-card declaration for this release; it does not establish rights to all upstream screenshots, applications or source content.", "declared": "MIT", "retrieved_at": "2026-10-18T04:35:17Z", "url": "https://huggingface.co/datasets/henryhe0123/PC-Agent-E/raw/4f64c7b055154bed9ffea677aa86aeb51a01cb73/README.md" }, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:27:13Z", "role": "primary", "sha256": "3ffb8c843c6acb8c2d5bbba11ba49d6b36cd566553a89974b6252a2bfd289d5d", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "notes", "relations", "details.dataset_profile" ], "url": "https://raw.githubusercontent.com/GAIR-NLP/PC-Agent-E/HEAD/README.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:33:21Z", "role": "primary", "sha256": "66f70ee2704cdf2e8847cfe04be05d9e14b3a3c1bee953e744f8209d6c9c2b85", "supports": [ "identity", "release_status", "details.hub_id", "details.hub_revision", "details.gated", "details.disabled", "details.download_url", "details.dataset_profile" ], "url": "https://huggingface.co/api/datasets/henryhe0123/PC-Agent-E" } ] }, { "id": "url:ba6453cfdae0eb049ced", "name": "Plan-and-Act training data", "url": "https://huggingface.co/datasets/xTRam1/plan-and-act-data", "environments": [ "web" ], "profile": { "counts": [], "evidence_urls": [ "https://huggingface.co/datasets/xTRam1/plan-and-act-data/raw/main/README.md", "https://huggingface.co/api/datasets/xTRam1/plan-and-act-data" ], "formats": [ "JSON", "JSONL" ], "modalities": [ "text", "plans", "actions" ], "notes": "The release contains planner and actor files for two web environments. No sample count is inferred from the package-file manifest. Card loading examples have repository/path inconsistencies.", "splits": [ "train (QwQ-32B files)", "validation (QwQ-32B files)" ], "supervision": [ "high-level plans", "action execution" ] }, "licenses": { "code": null, "data": { "basis": "publisher model/dataset card metadata; third-party assets retain their own terms", "declared": "mit", "retrieved_at": "2026-10-17T02:02:29Z", "url": "https://huggingface.co/datasets/xTRam1/plan-and-act-data/raw/main/README.md" }, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T02:02:29Z", "role": "primary", "sha256": "2ec8f4a03b8331bdd2ba8d6f6800d6dea9d955cfd9e7c1d2168ecb64deb25448", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "details" ], "url": "https://huggingface.co/datasets/xTRam1/plan-and-act-data/raw/main/README.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T02:02:28Z", "role": "primary", "sha256": "a98f98b7d4ceb81b00f217983ff271257f2f1e7d2c1a09836b872b2350d79ae9", "supports": [ "identity", "release_status", "details", "licenses.data" ], "url": "https://huggingface.co/api/datasets/xTRam1/plan-and-act-data" }, { "method": "huggingface_card", "retrieved_at": "2026-10-17T02:02:29Z", "role": "primary", "sha256": "2ec8f4a03b8331bdd2ba8d6f6800d6dea9d955cfd9e7c1d2168ecb64deb25448", "supports": [ "licenses.data" ], "url": "https://huggingface.co/datasets/xTRam1/plan-and-act-data/raw/main/README.md" } ] }, { "id": "url:0b134b082a7bd507fc6a", "name": "Rico", "url": "https://www.interactionmining.org/archive/rico", "environments": [ "android" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://www.interactionmining.org/archive/rico", "population": "original Rico downloads described on the project page", "qualifier": "more-than", "unit": "unique UI screens", "value": 66000 }, { "basis": "reported", "evidence_url": "https://www.interactionmining.org/archive/rico", "population": "original Rico collection described on the project page", "qualifier": "more-than", "unit": "Android apps", "value": 9300 }, { "basis": "reported", "evidence_url": "https://www.interactionmining.org/archive/rico", "population": "crowd-worker collection before automated exploration", "qualifier": "exact", "unit": "human interaction traces", "value": 10811 } ], "evidence_urls": [ "https://www.interactionmining.org/archive/rico", "https://danafergan.com/publications/deka2017rico.pdf" ], "formats": [ "PNG", "JSON", "CSV", "NumPy NPY", "GIF" ], "modalities": [ "screenshots", "Android view hierarchies", "gesture traces", "transition animations", "app/UI metadata" ], "notes": "Project-page scope: screenshots paired with augmented view hierarchies, gesture coordinates, layout vectors and metadata. These observations are not action/task totals. The later semantic-annotation download is a related augmentation of screens, not an additional disjoint corpus. The retained original paper reports more than 72k screens from more than 9.7k apps while this project page says more than 66k screens and more than 9.3k apps; the difference is unresolved. Profile counts follow the project page and do not merge these populations. No train/validation/test partition or data license is established here; archives were not downloaded.", "splits": [], "supervision": [ "UI structure and element properties", "recorded human interactions", "learned UI layout embeddings" ] }, "licenses": { "code": null, "data": null, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:38:29Z", "role": "primary", "sha256": "daa370b9aae5bce9f5171ea81fa4574c6155e04177af1db138529efd76377f89", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "details", "notes", "details.dataset_profile" ], "url": "https://www.interactionmining.org/archive/rico" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T10:01:32Z", "role": "primary", "sha256": "a1ec58c526b152c052c5c72f9a62725f1026b5f0e4f45c8fe85fce284295da84", "supports": [ "notes", "details.dataset_profile" ], "url": "https://danafergan.com/publications/deka2017rico.pdf" } ] }, { "id": "github:alibabaresearch/rots", "name": "RoTS", "url": "https://github.com/AlibabaResearch/RoTS", "environments": [ "cross-platform" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://raw.githubusercontent.com/AlibabaResearch/RoTS/HEAD/README.md", "population": "paper-described synthesis output; not a released file inventory", "qualifier": "approximately", "unit": "training samples", "value": 800000 } ], "evidence_urls": [ "https://raw.githubusercontent.com/AlibabaResearch/RoTS/HEAD/README.md" ], "formats": [], "modalities": [ "GUI interaction trajectories" ], "notes": "The inspected README marks the dataset and collection pipelines as in preparation. This profile records an announced research asset, not a verified downloadable corpus; file formats, splits, and release-specific data terms remain unknown.", "splits": [], "supervision": [ "recovery trajectory synthesis" ] }, "licenses": { "code": null, "data": null, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:02Z", "role": "primary", "sha256": "bf5c1469d33ced951ff0a5de017494b65f654023ceee8e7fbfd8b60afb082244", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "details" ], "url": "https://raw.githubusercontent.com/AlibabaResearch/RoTS/HEAD/README.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:02Z", "role": "primary", "sha256": "bf5c1469d33ced951ff0a5de017494b65f654023ceee8e7fbfd8b60afb082244", "supports": [ "details.dataset_profile" ], "url": "https://raw.githubusercontent.com/AlibabaResearch/RoTS/HEAD/README.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:02Z", "role": "primary", "sha256": "bf5c1469d33ced951ff0a5de017494b65f654023ceee8e7fbfd8b60afb082244", "supports": [ "summary", "notes", "details.availability" ], "url": "https://raw.githubusercontent.com/AlibabaResearch/RoTS/HEAD/README.md" } ] }, { "id": "url:631e74223e198ef40202", "name": "ScaleCUA Data", "url": "https://huggingface.co/datasets/OpenGVLab/ScaleCUA-Data", "environments": [ "cross-platform" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/OpenGVLab/ScaleCUA-Data/raw/main/README.md", "population": "Linux, macOS, Windows, Android, iOS, and Web", "qualifier": "exact", "unit": "platform categories", "value": 6 } ], "evidence_urls": [ "https://huggingface.co/datasets/OpenGVLab/ScaleCUA-Data/raw/main/README.md" ], "formats": [ "JSONL annotations", "JSON manifest", "split image archives" ], "modalities": [ "screenshots", "text", "actions" ], "notes": "The six categories include Web, so they are not six operating systems. Grounding and trajectory annotations follow different collection processes. No sample total or train/test division is inferred from archive-part counts or Hub size tags.", "splits": [], "supervision": [ "GUI grounding", "GUI action trajectories" ] }, "licenses": { "code": null, "data": null, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T02:02:37Z", "role": "primary", "sha256": "8c545d66cc7199a9258bd91ed48930691d0d99555bc30ee457fae9bf656fd18d", "supports": [ "details.dataset_profile", "relations" ], "url": "https://huggingface.co/datasets/OpenGVLab/ScaleCUA-Data/raw/main/README.md" } ] }, { "id": "url:4784f63cd7117f64a2a3", "name": "ScienceBoard evaluation trajectories", "url": "https://huggingface.co/datasets/OS-Copilot/ScienceBoard-Traj", "environments": [ "desktop", "linux" ], "profile": { "counts": [], "evidence_urls": [ "https://huggingface.co/api/datasets/OS-Copilot/ScienceBoard-Traj", "https://raw.githubusercontent.com/OS-Copilot/ScienceBoard/HEAD/README.md" ], "formats": [ "ZIP" ], "modalities": [ "screenshots", "accessibility trees", "text" ], "notes": "Observation modes follow publisher archive labels rather than inspected record schemas. No count or training-use permission is inferred.", "splits": [], "supervision": [ "evaluation rollout logs" ] }, "licenses": { "code": null, "data": null, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:07:19Z", "role": "primary", "sha256": "0a97233bd9132fdddc6ddb26fd3cf9f2af06ae086429f367a61cfab0c16c4f44", "supports": [ "name", "kind", "identity", "release_status", "details" ], "url": "https://huggingface.co/api/datasets/OS-Copilot/ScienceBoard-Traj" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:35:58Z", "role": "primary", "sha256": "4c3fe93aa740dbf4a279a246ddd836f2590a2a36f39b820abe166e38cb484577", "supports": [ "summary", "environments", "relations", "topics", "scope" ], "url": "https://raw.githubusercontent.com/OS-Copilot/ScienceBoard/HEAD/README.md" }, { "method": "huggingface_api", "retrieved_at": "2026-10-17T04:07:19Z", "role": "primary", "sha256": "0a97233bd9132fdddc6ddb26fd3cf9f2af06ae086429f367a61cfab0c16c4f44", "supports": [ "details", "licenses.data" ], "url": "https://huggingface.co/api/datasets/OS-Copilot/ScienceBoard-Traj" } ] }, { "id": "github:google-research-datasets/screen2words", "name": "Screen2Words", "url": "https://github.com/google-research-datasets/screen2words", "environments": [ "android" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://raw.githubusercontent.com/google-research-datasets/screen2words/HEAD/README.md", "population": "screen2words release", "qualifier": "exact", "unit": "summaries", "value": 112085 }, { "basis": "reported", "evidence_url": "https://raw.githubusercontent.com/google-research-datasets/screen2words/HEAD/README.md", "population": "RICO screens referenced by screen2words", "qualifier": "exact", "unit": "screens", "value": 22417 } ], "evidence_urls": [ "https://raw.githubusercontent.com/google-research-datasets/screen2words/HEAD/README.md" ], "formats": [ "CSV" ], "modalities": [ "text summaries", "RICO screen references" ], "notes": "Multiple summaries describe one screen. The repository provides annotations and split files; use the referenced RICO assets for screenshots.", "splits": [ "train", "dev", "test" ], "supervision": [ "screen summarization" ] }, "licenses": { "code": null, "data": null, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:01Z", "role": "primary", "sha256": "8be66dc5a3907e0e84993a66679416d928ed1a32aae70db8bb0e0f771c7a8715", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "details.sample_count", "details.sample_unit", "details.screen_count", "details.modalities", "details.dataset_profile" ], "url": "https://raw.githubusercontent.com/google-research-datasets/screen2words/HEAD/README.md" } ] }, { "id": "url:fe43af1801032be708cc", "name": "ScreenDrag", "url": "https://huggingface.co/datasets/h-siyuan/ScreenDrag", "environments": [ "desktop" ], "profile": { "counts": [], "evidence_urls": [ "https://huggingface.co/datasets/h-siyuan/ScreenDrag/raw/main/README.md" ], "formats": [ "Parquet", "episode files" ], "modalities": [ "screen images", "instructions", "previous state", "continuous actions" ], "notes": "Raw and Parquet folders are alternative views of the same data. Each sample describes a dragging task over multiple timesteps; action vectors encode button state and coordinates.", "splits": [ "train", "test" ], "supervision": [ "continuous GUI dragging" ] }, "licenses": { "code": null, "data": null, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T11:12:56Z", "role": "primary", "sha256": "39c7c028f7ef5ca5c75f79b59a107c7e25444776095a2a08bb7535c4f523f7fa", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "details.modalities", "details.download_url", "details.dataset_profile" ], "url": "https://huggingface.co/datasets/h-siyuan/ScreenDrag/raw/main/README.md" } ] }, { "id": "github:google-research-datasets/screen_qa", "name": "ScreenQA", "url": "https://github.com/google-research-datasets/screen_qa", "environments": [ "android" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://raw.githubusercontent.com/google-research-datasets/screen_qa/HEAD/README.md", "population": "original ScreenQA train split", "qualifier": "exact", "unit": "question-answer pairs", "value": 68951 }, { "basis": "reported", "evidence_url": "https://raw.githubusercontent.com/google-research-datasets/screen_qa/HEAD/README.md", "population": "original ScreenQA validation split", "qualifier": "exact", "unit": "question-answer pairs", "value": 8614 }, { "basis": "reported", "evidence_url": "https://raw.githubusercontent.com/google-research-datasets/screen_qa/HEAD/README.md", "population": "original ScreenQA test split", "qualifier": "exact", "unit": "question-answer pairs", "value": 8419 } ], "evidence_urls": [ "https://raw.githubusercontent.com/google-research-datasets/screen_qa/HEAD/README.md" ], "formats": [ "JSON" ], "modalities": [ "questions", "answers", "screen references", "bounding boxes" ], "notes": "All questions for a given screenshot share one split. ScreenQA Short reuses the same questions/screens; ComplexQA is a separate extension. Do not add these variants as independent original examples.", "splits": [ "train", "validation", "test" ], "supervision": [ "screen question answering", "answer grounding" ] }, "licenses": { "code": null, "data": null, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:01Z", "role": "primary", "sha256": "7d1bfe7d6eddd5d3fc4c33d4814de3cabf7a6b6fd3d3f85ba4c2b33036bf8867", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "details.dataset_profile" ], "url": "https://raw.githubusercontent.com/google-research-datasets/screen_qa/HEAD/README.md" } ] }, { "id": "url:56bda04bd8d3a438deb3", "name": "ScreenRef", "url": "https://huggingface.co/datasets/PrentisAI/ScreenRef", "environments": [ "desktop", "web", "android", "linux" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/PrentisAI/ScreenRef-Annotations/raw/main/README.md", "population": "ScreenRef image inventory", "qualifier": "exact", "unit": "distinct screenshots", "value": 585981 }, { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/PrentisAI/ScreenRef-Annotations/raw/main/README.md", "population": "full recipe", "qualifier": "exact", "unit": "annotation rows", "value": 633369 }, { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/PrentisAI/ScreenRef-Annotations/raw/main/README.md", "population": "refusal subset of full recipe", "qualifier": "exact", "unit": "annotation rows", "value": 22475 } ], "evidence_urls": [ "https://huggingface.co/datasets/PrentisAI/ScreenRef-Annotations/raw/main/README.md" ], "formats": [ "Parquet" ], "modalities": [ "screenshots", "text", "coordinates" ], "notes": "The publisher reports these inventories in the companion annotation card. The refusal subset is included in the full recipe. Screenshot access is gated; no image download or independent corpus recount was performed.", "splits": [ "train" ], "supervision": [ "instruction-to-click grounding", "bounding boxes", "absent-target abstention" ] }, "licenses": { "code": null, "data": { "basis": "publisher model/dataset card", "declared": "other", "retrieved_at": "2026-10-17T01:48:51Z", "url": "https://huggingface.co/datasets/PrentisAI/ScreenRef" }, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T01:48:10Z", "role": "primary", "sha256": "96a87222645c3f823e6f67e50708792e2917ddeb8eea5aacdf2de8c5bbff165f", "supports": [ "summary", "environments", "topics", "scope", "notes", "relations", "details.dataset_profile" ], "url": "https://huggingface.co/datasets/PrentisAI/ScreenRef-Annotations/raw/main/README.md" } ] }, { "id": "url:c1db2ba79e6d6a3db2b9", "name": "ScreenRef Annotations", "url": "https://huggingface.co/datasets/PrentisAI/ScreenRef-Annotations", "environments": [ "desktop", "web", "android", "linux" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/PrentisAI/ScreenRef-Annotations/raw/main/README.md", "population": "full recipe", "qualifier": "exact", "unit": "annotation rows", "value": 633369 }, { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/PrentisAI/ScreenRef-Annotations/raw/main/README.md", "population": "point recipe", "qualifier": "exact", "unit": "annotation rows", "value": 610894 } ], "evidence_urls": [ "https://huggingface.co/datasets/PrentisAI/ScreenRef-Annotations/raw/main/README.md" ], "formats": [ "JSONL", "JSON task recipes", "TSV manifests" ], "modalities": [ "text", "coordinates", "image references" ], "notes": "The recipes reuse source images and are not additive datasets. This download contains no screenshots. Counts are publisher-reported; rows named for trajectories are independent decision examples, not full trajectories.", "splits": [ "full/train", "point/train" ], "supervision": [ "instruction-to-click grounding", "bounding boxes", "absent-target abstention" ] }, "licenses": { "code": null, "data": { "basis": "publisher model/dataset card metadata; third-party assets retain their own terms", "declared": "other", "retrieved_at": "2026-10-17T01:48:10Z", "url": "https://huggingface.co/datasets/PrentisAI/ScreenRef-Annotations/raw/main/README.md" }, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T01:48:10Z", "role": "primary", "sha256": "96a87222645c3f823e6f67e50708792e2917ddeb8eea5aacdf2de8c5bbff165f", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "details" ], "url": "https://huggingface.co/datasets/PrentisAI/ScreenRef-Annotations/raw/main/README.md" }, { "method": "huggingface_card", "retrieved_at": "2026-10-17T01:48:10Z", "role": "primary", "sha256": "96a87222645c3f823e6f67e50708792e2917ddeb8eea5aacdf2de8c5bbff165f", "supports": [ "licenses.data" ], "url": "https://huggingface.co/datasets/PrentisAI/ScreenRef-Annotations/raw/main/README.md" } ] }, { "id": "url:c79e152e6f7af1a9efed", "name": "ScreenSpot-Pro data", "url": "https://huggingface.co/datasets/likaixin/ScreenSpot-Pro", "environments": [ "desktop", "windows", "macos", "linux" ], "profile": { "counts": [ { "basis": "computed", "evidence_url": "https://huggingface.co/datasets/likaixin/ScreenSpot-Pro/raw/main/README.md", "population": "sum of icon/text counts in the published card table", "qualifier": "exact", "unit": "target annotations", "value": 1581 } ], "evidence_urls": [ "https://huggingface.co/datasets/likaixin/ScreenSpot-Pro/raw/main/README.md", "https://raw.githubusercontent.com/likaixin2000/ScreenSpot-Pro-GUI-Grounding/HEAD/eval_screenspot_pro.py" ], "formats": [ "JSON annotations", "screen images" ], "modalities": [ "high-resolution screenshots", "instructions", "bounding boxes" ], "notes": "Counts describe target annotations, not unique screenshots or expanded language/style variants. The evaluation code can reuse a target across configurations.", "splits": [], "supervision": [ "GUI grounding" ] }, "licenses": { "code": null, "data": { "basis": "publisher model/dataset card metadata; third-party assets retain their own terms", "declared": "mit", "retrieved_at": "2026-10-16T11:35:55Z", "url": "https://huggingface.co/datasets/likaixin/ScreenSpot-Pro/raw/main/README.md" }, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T11:35:55Z", "role": "primary", "sha256": "76ae2231564fe84af029f8625c02d9cd7fb6cf85c5f8af1b2a2593e2107719d9", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "details" ], "url": "https://huggingface.co/datasets/likaixin/ScreenSpot-Pro/raw/main/README.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T11:38:05Z", "role": "primary", "sha256": "a77c859775b33591b5619e8520c94702a53a1f9a29ada93e66744dbe23afe9dc", "supports": [ "details.dataset_profile" ], "url": "https://raw.githubusercontent.com/likaixin2000/ScreenSpot-Pro-GUI-Grounding/HEAD/eval_screenspot_pro.py" }, { "method": "huggingface_card", "retrieved_at": "2026-10-16T11:35:55Z", "role": "primary", "sha256": "76ae2231564fe84af029f8625c02d9cd7fb6cf85c5f8af1b2a2593e2107719d9", "supports": [ "licenses.data" ], "url": "https://huggingface.co/datasets/likaixin/ScreenSpot-Pro/raw/main/README.md" } ] }, { "id": "url:f976dec3d1c5e0bedbd7", "name": "ShowUI Desktop", "url": "https://huggingface.co/datasets/showlab/ShowUI-desktop-8K", "environments": [ "desktop" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/showlab/ShowUI-desktop-8K/raw/main/README.md", "population": "train split declared in the dataset card", "qualifier": "exact", "unit": "examples", "value": 7496 } ], "evidence_urls": [ "https://huggingface.co/datasets/showlab/ShowUI-desktop-8K/raw/main/README.md" ], "formats": [ "Hub table with an image column" ], "modalities": [ "screenshots", "text", "bounding boxes", "points" ], "notes": "The 8K release name is not an exact record count; the card declares 7,496 examples. Images and original annotations come from OmniAct and are augmented with generated descriptions. Examples are not asserted to be unique screenshots.", "splits": [ "train" ], "supervision": [ "instruction-to-element grounding" ] }, "licenses": { "code": null, "data": null, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T02:02:38Z", "role": "primary", "sha256": "577a78efa03cde05141c23033222014094681cb5d04786dbb4a698df8543b3df", "supports": [ "details.dataset_profile", "relations" ], "url": "https://huggingface.co/datasets/showlab/ShowUI-desktop-8K/raw/main/README.md" } ] }, { "id": "url:8933977bb0a57940ed23", "name": "ShowUI-web", "url": "https://huggingface.co/datasets/showlab/ShowUI-web", "environments": [ "web" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/showlab/ShowUI-web/raw/main/README.md", "population": "train split", "qualifier": "exact", "unit": "rows", "value": 21988 } ], "evidence_urls": [ "https://huggingface.co/datasets/showlab/ShowUI-web/raw/main/README.md" ], "formats": [ "Parquet", "JSON", "TAR.GZ" ], "modalities": [ "screenshots", "text", "bounding boxes", "points" ], "notes": "Row count is the card dataset_info value; one row may contain multiple instructions. The card summarizes screenshots as approximately 22K. No data license is declared.", "splits": [ "train" ], "supervision": [ "element grounding" ] }, "licenses": { "code": null, "data": null, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T02:42:32Z", "role": "primary", "sha256": "08586aa1ded1f1a1f984fb55697fdb1007d86c7fdf4988a2dc1fcf3fdfd49a47", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "details" ], "url": "https://huggingface.co/datasets/showlab/ShowUI-web/raw/main/README.md" } ] }, { "id": "url:3dab53c6c38c9e7217ea", "name": "ShowUI-π training data", "url": "https://huggingface.co/datasets/showlab/ShowUI-pi-data", "environments": [ "desktop" ], "profile": { "counts": [], "evidence_urls": [ "https://huggingface.co/datasets/showlab/ShowUI-pi-data/raw/main/README.md" ], "formats": [ "Parquet", "LeRobot metadata" ], "modalities": [ "screenshots", "instructions", "actions" ], "notes": "No sample or episode count is inferred from the size tag or package manifest. Main-branch files were inspected; the card’s v3.0 usage example was not executed.", "splits": [], "supervision": [ "drag trajectories", "click episodes" ] }, "licenses": { "code": null, "data": null, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:01:33Z", "role": "primary", "sha256": "0e3a2a923865ae24d0de590143e9e32564b0e20db059579582d6181cdcf75bf1", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "details" ], "url": "https://huggingface.co/datasets/showlab/ShowUI-pi-data/raw/main/README.md" } ] }, { "id": "url:c4898ad1bfc049926a63", "name": "UGround V1 Data", "url": "https://huggingface.co/datasets/osunlp/UGround-V1-Data", "environments": [ "cross-platform" ], "profile": { "counts": [], "evidence_urls": [ "https://huggingface.co/api/datasets/osunlp/UGround-V1-Data", "https://raw.githubusercontent.com/OSU-NLP-Group/UGround/HEAD/README.md" ], "formats": [ "Parquet shards" ], "modalities": [ "GUI screenshots", "natural-language grounding descriptions" ], "notes": "Public API revision 33325877 lists Parquet assets but gated=auto; the pinned raw card returned HTTP 401 and no access was requested. Official README identifies this as V1 training data; the API excerpt also announces a Web-Hybrid bounding-box variant with coordinates normalized to [0,999]. That does not establish every shard schema or a release-wide point/bbox count. No train/test partition, example total, or unrestricted downloadability is claimed. Preserve the recorded CC-BY-NC-SA-4.0 data declaration separately from model/code terms.", "splits": [], "supervision": [ "GUI visual-grounding training for the UGround-V1 family" ] }, "licenses": { "code": null, "data": { "basis": "publisher model/dataset card", "declared": "cc-by-nc-sa-4.0", "retrieved_at": "2026-10-16T06:38:26Z", "url": "https://huggingface.co/datasets/osunlp/UGround-V1-Data" }, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:38:26Z", "role": "primary", "sha256": "0342862bd7857dd21e389ee5d351375dfea722cad4725c8e33271efc93e009f6", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "details.dataset_profile" ], "url": "https://huggingface.co/api/datasets/osunlp/UGround-V1-Data" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T06:36:00Z", "role": "primary", "sha256": "72ca3f23114c3a08fefb724573acf10c9f0a1b3d4a50d811c98356264ecf6ffc", "supports": [ "details.dataset_profile", "relations" ], "url": "https://raw.githubusercontent.com/OSU-NLP-Group/UGround/HEAD/README.md" }, { "method": "huggingface_api", "retrieved_at": "2026-10-16T06:38:26Z", "role": "primary", "sha256": "0342862bd7857dd21e389ee5d351375dfea722cad4725c8e33271efc93e009f6", "supports": [ "details", "licenses.data" ], "url": "https://huggingface.co/api/datasets/osunlp/UGround-V1-Data" } ] }, { "id": "url:84e5aeeffaf561baa966", "name": "UI-Genie reward data", "url": "https://huggingface.co/datasets/HanXiao1999/UI-Genie-RM-517k", "environments": [ "android" ], "profile": { "counts": [], "evidence_urls": [ "https://huggingface.co/datasets/HanXiao1999/UI-Genie-RM-517k/raw/main/README.md", "https://raw.githubusercontent.com/Euphoria16/UI-Genie/HEAD/README.md" ], "formats": [ "JSONL" ], "modalities": [ "text" ], "notes": "The public manifest contains reward_data.jsonl but no separately packaged image archive. The card declares MIT. The 517k identifier is not converted into a verified sample count, and complete image packaging is not inferred from the JSONL filename.", "splits": [], "supervision": [ "trajectory rewards" ] }, "licenses": { "code": null, "data": { "basis": "publisher model/dataset card metadata; third-party assets retain their own terms", "declared": "mit", "retrieved_at": "2026-10-17T04:01:34Z", "url": "https://huggingface.co/datasets/HanXiao1999/UI-Genie-RM-517k/raw/main/README.md" }, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:01:34Z", "role": "primary", "sha256": "dddb70b2b6986525f3980cbe50c3241d17f840a81fda9715b01ac3b25dd35d63", "supports": [ "name", "kind", "relations", "licenses.data" ], "url": "https://huggingface.co/datasets/HanXiao1999/UI-Genie-RM-517k/raw/main/README.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T03:59:54Z", "role": "primary", "sha256": "e08569bd9d8a6ff44537d4fe69243ddfeb8a41ae5c9f87ef84af50a67c64c726", "supports": [ "summary", "environments", "topics", "scope" ], "url": "https://raw.githubusercontent.com/Euphoria16/UI-Genie/HEAD/README.md" }, { "method": "huggingface_card", "retrieved_at": "2026-10-17T04:01:34Z", "role": "primary", "sha256": "dddb70b2b6986525f3980cbe50c3241d17f840a81fda9715b01ac3b25dd35d63", "supports": [ "licenses.data" ], "url": "https://huggingface.co/datasets/HanXiao1999/UI-Genie-RM-517k/raw/main/README.md" } ] }, { "id": "url:2e1927450da2183a5abe", "name": "UI-Genie trajectory data", "url": "https://huggingface.co/datasets/HanXiao1999/UI-Genie-Agent-16k", "environments": [ "android" ], "profile": { "counts": [], "evidence_urls": [ "https://huggingface.co/datasets/HanXiao1999/UI-Genie-Agent-16k/raw/main/README.md", "https://raw.githubusercontent.com/Euphoria16/UI-Genie/HEAD/README.md" ], "formats": [ "JSONL", "PNG" ], "modalities": [ "screenshots", "text", "actions" ], "notes": "Public JSONL annotations and screenshots are present. MIT is declared in the dataset card. The release name, model-card links and annotation filename use different size labels; this review does not infer a reliable trajectory count from them.", "splits": [], "supervision": [ "GUI action trajectories" ] }, "licenses": { "code": null, "data": { "basis": "publisher model/dataset card metadata; third-party assets retain their own terms", "declared": "mit", "retrieved_at": "2026-10-17T04:01:34Z", "url": "https://huggingface.co/datasets/HanXiao1999/UI-Genie-Agent-16k/raw/main/README.md" }, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:01:34Z", "role": "primary", "sha256": "a748fc7dbb53d5d751c5ee109e437c377e214b1d837762f8d09995349d86cec9", "supports": [ "name", "kind", "relations", "licenses.data" ], "url": "https://huggingface.co/datasets/HanXiao1999/UI-Genie-Agent-16k/raw/main/README.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T03:59:54Z", "role": "primary", "sha256": "e08569bd9d8a6ff44537d4fe69243ddfeb8a41ae5c9f87ef84af50a67c64c726", "supports": [ "summary", "environments", "topics", "scope" ], "url": "https://raw.githubusercontent.com/Euphoria16/UI-Genie/HEAD/README.md" }, { "method": "huggingface_card", "retrieved_at": "2026-10-17T04:01:34Z", "role": "primary", "sha256": "a748fc7dbb53d5d751c5ee109e437c377e214b1d837762f8d09995349d86cec9", "supports": [ "licenses.data" ], "url": "https://huggingface.co/datasets/HanXiao1999/UI-Genie-Agent-16k/raw/main/README.md" } ] }, { "id": "url:16184830c0f4bdb146fa", "name": "UI-S1 released training examples", "url": "https://huggingface.co/datasets/mPLUG/UI_S1_dataset", "environments": [ "android" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://raw.githubusercontent.com/X-PLUG/MobileAgent/HEAD/UI-S1/README.md", "population": "public example subset", "qualifier": "exact", "unit": "training examples", "value": 1000 } ], "evidence_urls": [ "https://huggingface.co/datasets/mPLUG/UI_S1_dataset/raw/main/README.md", "https://raw.githubusercontent.com/X-PLUG/MobileAgent/HEAD/UI-S1/README.md" ], "formats": [ "JSONL", "Parquet" ], "modalities": [ "images", "text", "actions" ], "notes": "The count is explicitly reported by the publisher, not inferred from the filename. Full training data remains outside this release.", "splits": [ "training example subset" ], "supervision": [ "GUI actions" ] }, "licenses": { "code": null, "data": { "basis": "publisher model/dataset card metadata; third-party assets retain their own terms", "declared": "apache-2.0", "retrieved_at": "2026-10-17T04:07:19Z", "url": "https://huggingface.co/datasets/mPLUG/UI_S1_dataset/raw/main/README.md" }, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:07:19Z", "role": "primary", "sha256": "d826463e2aa159f083dc74869bfabb8abb5b8ea4f2cdf4aeb7676172b18aaaa5", "supports": [ "name", "kind", "relations", "licenses.data" ], "url": "https://huggingface.co/datasets/mPLUG/UI_S1_dataset/raw/main/README.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:06:57Z", "role": "primary", "sha256": "f668c890a5a87953a243715d0d47367c23f0c99b524d80f48bbdde8163f3e942", "supports": [ "summary", "environments", "details.dataset_profile", "topics", "scope" ], "url": "https://raw.githubusercontent.com/X-PLUG/MobileAgent/HEAD/UI-S1/README.md" }, { "method": "huggingface_card", "retrieved_at": "2026-10-17T04:07:19Z", "role": "primary", "sha256": "d826463e2aa159f083dc74869bfabb8abb5b8ea4f2cdf4aeb7676172b18aaaa5", "supports": [ "licenses.data" ], "url": "https://huggingface.co/datasets/mPLUG/UI_S1_dataset/raw/main/README.md" } ] }, { "id": "url:2c2004baae4669f8169a", "name": "UI-Vision", "url": "https://huggingface.co/datasets/ServiceNow/ui-vision", "environments": [ "desktop" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/ServiceNow/ui-vision/raw/main/README.md", "population": "paper-described benchmark coverage", "qualifier": "exact", "unit": "software applications", "value": 83 } ], "evidence_urls": [ "https://huggingface.co/datasets/ServiceNow/ui-vision/raw/main/README.md" ], "formats": [ "JSON annotations", "image files" ], "modalities": [ "screenshots", "bounding boxes", "UI labels", "action annotations" ], "notes": "This is an offline evaluation dataset. Application coverage is not a sample count. The inspected file-layout documentation describes grounding annotations and images; it does not establish a common split or complete action-trajectory inventory.", "splits": [], "supervision": [ "element grounding", "layout grounding", "action prediction" ] }, "licenses": { "code": null, "data": { "basis": "publisher model/dataset card", "declared": "mit", "retrieved_at": "2026-10-16T06:38:26Z", "url": "https://huggingface.co/datasets/ServiceNow/ui-vision" }, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T02:02:37Z", "role": "primary", "sha256": "295cf7f7500a18cea5c80eab1cdf4d7264f2f0e959b75efc5ba59083d93c9097", "supports": [ "details.dataset_profile" ], "url": "https://huggingface.co/datasets/ServiceNow/ui-vision/raw/main/README.md" } ] }, { "id": "github:google-research-datasets/uibert", "name": "UIBert AppSim and RefExp annotations", "url": "https://github.com/google-research-datasets/uibert", "environments": [ "android" ], "profile": { "counts": [], "evidence_urls": [ "https://raw.githubusercontent.com/google-research-datasets/uibert/HEAD/README.md" ], "formats": [ "TFRecord" ], "modalities": [ "text", "bounding boxes", "UI hierarchy metadata", "Rico image identifiers" ], "notes": "Original UI images are retrieved separately by Rico IDs. No release-specific sample count is established.", "splits": [ "AppSim train/dev/test", "RefExp train/dev/test" ], "supervision": [ "similar UI element retrieval", "referring-expression component retrieval" ] }, "licenses": { "code": null, "data": { "basis": "The README explicitly says the datasets are licensed under CC BY 4.0; original Rico materials keep their source terms.", "declared": "CC-BY-4.0", "retrieved_at": "2026-10-17T12:30:54Z", "url": "https://raw.githubusercontent.com/google-research-datasets/uibert/HEAD/README.md" }, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T12:30:54Z", "role": "primary", "sha256": "45d1ca0f5c727cf58b2671dc5579f0628f4d78e07b977a5d8b018295c6fe1f58", "supports": [ "name", "kind", "summary", "topics", "scope", "notes", "relations", "details.dataset_profile", "licenses.data" ], "url": "https://raw.githubusercontent.com/google-research-datasets/uibert/HEAD/README.md" } ] }, { "id": "github:google-research-datasets/uicrit", "name": "UICrit", "url": "https://github.com/google-research-datasets/uicrit", "environments": [ "unspecified" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://raw.githubusercontent.com/google-research-datasets/uicrit/HEAD/README.md", "population": "current three-annotator release", "qualifier": "exact", "unit": "mobile UI screens", "value": 1000 }, { "basis": "reported", "evidence_url": "https://raw.githubusercontent.com/google-research-datasets/uicrit/HEAD/README.md", "population": "current three-annotator release", "qualifier": "exact", "unit": "design critiques", "value": 11344 } ], "evidence_urls": [ "https://raw.githubusercontent.com/google-research-datasets/uicrit/HEAD/README.md" ], "formats": [ "CSV" ], "modalities": [ "text", "bounding boxes", "quality ratings" ], "notes": "Publisher-reported current release, separate from the smaller original-paper population. Screenshot pixels are obtained through referenced RICO IDs.", "splits": [], "supervision": [ "design critique", "region localization", "quality rating" ] }, "licenses": { "code": null, "data": null, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T02:02:45Z", "role": "primary", "sha256": "345ff7003120f146016741099dd57b9b1a9ffc54ce1fc90f4d16d61e31d379e6", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "details" ], "url": "https://raw.githubusercontent.com/google-research-datasets/uicrit/HEAD/README.md" } ] }, { "id": "url:2b5dead3172c0b70da7e", "name": "VideoCAD data", "url": "https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/WX8PCK", "environments": [ "web" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://dataverse.harvard.edu/api/datasets/:persistentId/?persistentId=doi:10.7910/DVN/WX8PCK", "population": "VideoCAD published collection", "qualifier": "more-than", "unit": "video recordings", "value": 41000 } ], "evidence_urls": [ "https://dataverse.harvard.edu/api/datasets/:persistentId/?persistentId=doi:10.7910/DVN/WX8PCK", "https://raw.githubusercontent.com/ghadinehme/VideoCAD/2d69eeaf0ac44210c76dcab2d08b4d4610be236c/README.md" ], "formats": [ "ZIP", "MP4", "JSON", "PNG" ], "modalities": [ "video", "UI action logs", "target CAD images" ], "notes": "The reported video total is distinct from the Dataverse package-file count. The exact-version paper identifies the recorded interface as browser-based Onshape; operating-system compatibility is not established.", "splits": [], "supervision": [ "timestamped UI actions", "target model images" ] }, "licenses": { "code": null, "data": { "basis": "publisher Dataverse dataset-version license metadata; original declaration and URI retained in details.dataverse.license", "declared": "CC0 1.0", "retrieved_at": "2026-10-17T02:03:20Z", "url": "https://dataverse.harvard.edu/api/datasets/:persistentId/?persistentId=doi:10.7910/DVN/WX8PCK" }, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T02:03:20Z", "role": "primary", "sha256": "f67df0a4422a0484aaa2f93cd185b7000070d2a88d919d9ef995587f5e724007", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "details" ], "url": "https://dataverse.harvard.edu/api/datasets/:persistentId/?persistentId=doi:10.7910/DVN/WX8PCK" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-18T12:02:53.536297+00:00", "role": "primary", "sha256": "cbb08803922b4b7736979ca0a5fe552b111fcd428fa9317401bc090b14bb4e54", "supports": [ "summary", "relations", "details.dataset_profile" ], "url": "https://raw.githubusercontent.com/ghadinehme/VideoCAD/2d69eeaf0ac44210c76dcab2d08b4d4610be236c/README.md" }, { "method": "dataverse_api", "retrieved_at": "2026-10-17T02:03:20Z", "role": "primary", "sha256": "f67df0a4422a0484aaa2f93cd185b7000070d2a88d919d9ef995587f5e724007", "supports": [ "details.dataverse", "licenses.data" ], "url": "https://dataverse.harvard.edu/api/datasets/:persistentId/?persistentId=doi:10.7910/DVN/WX8PCK" } ] }, { "id": "url:0dbb55f127da04d95222", "name": "Wave UI", "url": "https://huggingface.co/datasets/agentsea/wave-ui", "environments": [ "unspecified" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/agentsea/wave-ui/raw/main/README.md", "population": "train split", "qualifier": "exact", "unit": "rows", "value": 63530 }, { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/agentsea/wave-ui/raw/main/README.md", "population": "validation split", "qualifier": "exact", "unit": "rows", "value": 7944 }, { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/agentsea/wave-ui/raw/main/README.md", "population": "test split", "qualifier": "exact", "unit": "rows", "value": 7938 } ], "evidence_urls": [ "https://huggingface.co/datasets/agentsea/wave-ui/raw/main/README.md", "https://huggingface.co/datasets/agentsea/wave-ui/raw/main/LICENSE.md" ], "formats": [ "Parquet" ], "modalities": [ "images", "text", "bounding boxes", "OCR metadata" ], "notes": "Card-reported row counts are not unique-screen counts. The source field is important for the per-image license terms; the compilation does not relicense original images.", "splits": [ "train", "validation", "test" ], "supervision": [ "instruction-to-target boxes" ] }, "licenses": { "code": null, "data": { "basis": "Publisher compilation license; individual images keep their source-dataset terms and receive no additional rights from this compilation.", "declared": "Wave UI Dataset License; per-image source terms retained", "retrieved_at": "2026-10-17T04:06:57Z", "url": "https://huggingface.co/datasets/agentsea/wave-ui/raw/main/LICENSE.md" }, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:01:33Z", "role": "primary", "sha256": "27ec13aa77dc55113e4d1a19c2269070e2d69d2fe8df8e2313721a1e3fc66bd9", "supports": [ "details" ], "url": "https://huggingface.co/datasets/agentsea/wave-ui/raw/main/README.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:06:57Z", "role": "primary", "sha256": "63c6b3ce6a3d9c21a505865ceed698df2894bcb292590c59686e9477df867942", "supports": [ "licenses.data" ], "url": "https://huggingface.co/datasets/agentsea/wave-ui/raw/main/LICENSE.md" } ] }, { "id": "url:e126bbd9729ebdaf05ab", "name": "WebEvolver SFT data", "url": "https://huggingface.co/datasets/CognitiveKernel/WebEvolver", "environments": [ "web" ], "profile": { "counts": [], "evidence_urls": [ "https://huggingface.co/datasets/CognitiveKernel/WebEvolver/raw/13f4f45b359e138a45b1c89bd4e913298c586ca9/README.md", "https://huggingface.co/api/datasets/CognitiveKernel/WebEvolver" ], "formats": [ "JSONL" ], "modalities": [], "notes": "Two purpose-specific files are released: webevolver_policy_sft.jsonl and webevolver_world_model_sft.jsonl. They are not assumed disjoint train/test splits, and no modality or example count is inferred from filenames alone.", "splits": [], "supervision": [ "agent-policy supervised fine-tuning", "web-world-model supervised fine-tuning" ] }, "licenses": { "code": null, "data": { "basis": "Publisher dataset-card declaration for this release; it does not establish rights to all upstream screenshots, applications or source content.", "declared": "MIT", "retrieved_at": "2026-10-18T04:35:17Z", "url": "https://huggingface.co/datasets/CognitiveKernel/WebEvolver/raw/13f4f45b359e138a45b1c89bd4e913298c586ca9/README.md" }, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:35:17Z", "role": "primary", "sha256": "36ccdce12c1b1512ad4b21326c5d0c0379c73e85f0b8150779d43240b54686de", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "notes", "relations", "licenses.data", "details.dataset_profile" ], "url": "https://huggingface.co/datasets/CognitiveKernel/WebEvolver/raw/13f4f45b359e138a45b1c89bd4e913298c586ca9/README.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:33:29Z", "role": "primary", "sha256": "cbef3f8037405d311ed9fe8aa620ec3734f91c77ca8f4209fbe98167fb33bee8", "supports": [ "identity", "release_status", "details.hub_id", "details.hub_revision", "details.gated", "details.disabled", "details.download_url", "details.dataset_profile" ], "url": "https://huggingface.co/api/datasets/CognitiveKernel/WebEvolver" } ] }, { "id": "url:fcc98b149272bbf31b05", "name": "WebPRM checklist-generation data", "url": "https://huggingface.co/datasets/LangAGI-Lab/WebPRMCollection_checklist_generation", "environments": [ "web" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/LangAGI-Lab/WebPRMCollection_checklist_generation/raw/main/README.md", "population": "Hub split named test", "qualifier": "exact", "unit": "rows", "value": 3630 } ], "evidence_urls": [ "https://huggingface.co/datasets/LangAGI-Lab/WebPRMCollection_checklist_generation/raw/main/README.md", "https://huggingface.co/api/collections/LangAGI-Lab/web-shepherd-advancing-prms-for-reinforcing-web-agents-682b4f4ad607fc27c4dc49e8" ], "formats": [ "Parquet" ], "modalities": [ "screenshots", "text", "action history" ], "notes": "This is the checklist-generation release rather than the separate preference-pair collection. No unique-task count or data permission is inferred.", "splits": [ "test" ], "supervision": [ "checklist generation", "subgoal analysis" ] }, "licenses": { "code": null, "data": null, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T04:01:33Z", "role": "primary", "sha256": "3693cb307065a6ced63a4789a7f592b5eba0ad6a5ffe1a3caf0649decd5cb6e8", "supports": [ "details" ], "url": "https://huggingface.co/datasets/LangAGI-Lab/WebPRMCollection_checklist_generation/raw/main/README.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T02:45:05Z", "role": "primary", "sha256": "647d9e7bdad5fe2c03a8cfcd34d93f3b2bf7c1553b517a4a843bc0113fa47456", "supports": [ "identity", "summary" ], "url": "https://huggingface.co/api/collections/LangAGI-Lab/web-shepherd-advancing-prms-for-reinforcing-web-agents-682b4f4ad607fc27c4dc49e8" } ] }, { "id": "url:8dfc84eb4016204fe70a", "name": "WebPRM Collection preference data", "url": "https://huggingface.co/datasets/LangAGI-Lab/WebPRMCollection_preference_pair", "environments": [ "web" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/LangAGI-Lab/WebPRMCollection_preference_pair/raw/main/README.md", "population": "Hub split named test", "qualifier": "exact", "unit": "rows", "value": 9460 } ], "evidence_urls": [ "https://huggingface.co/datasets/LangAGI-Lab/WebPRMCollection_preference_pair/raw/main/README.md", "https://raw.githubusercontent.com/kyle8581/Web-Shepherd/HEAD/README.md" ], "formats": [ "Parquet" ], "modalities": [ "screenshots", "text", "action history" ], "notes": "Preserves the publisher’s split label despite the collection’s training purpose. Rows are not individual preference pairs because rejected is a list. Data license is unknown.", "splits": [ "test" ], "supervision": [ "preferred and rejected continuations", "task checklists" ] }, "licenses": { "code": null, "data": null, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T02:44:50Z", "role": "primary", "sha256": "9c091c5fc625ce53f53f8262f5cee8d08194e4fd1b8eeed543ff1c3723c823fd", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "details" ], "url": "https://huggingface.co/datasets/LangAGI-Lab/WebPRMCollection_preference_pair/raw/main/README.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T02:44:04Z", "role": "primary", "sha256": "07431058d8b9a71b80e75b7a74a40a8346c1503eec240628459cc4d4e2f0802f", "supports": [ "summary", "environments" ], "url": "https://raw.githubusercontent.com/kyle8581/Web-Shepherd/HEAD/README.md" } ] }, { "id": "url:e0ba328ae1a643b0a5aa", "name": "WebSRC v1.0", "url": "https://huggingface.co/datasets/X-LANCE/WebSRC_v1.0", "environments": [ "web" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/X-LANCE/WebSRC_v1.0/raw/7aa0bc6efc7ef43f68c192e2091108541acbaf1a/README.md", "population": "WebSRC v1.0 train", "qualifier": "exact", "unit": "question–answer examples", "value": 307315 }, { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/X-LANCE/WebSRC_v1.0/raw/7aa0bc6efc7ef43f68c192e2091108541acbaf1a/README.md", "population": "WebSRC v1.0 train", "qualifier": "exact", "unit": "web pages", "value": 4549 }, { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/X-LANCE/WebSRC_v1.0/raw/7aa0bc6efc7ef43f68c192e2091108541acbaf1a/README.md", "population": "WebSRC v1.0 dev", "qualifier": "exact", "unit": "question–answer examples", "value": 52826 }, { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/X-LANCE/WebSRC_v1.0/raw/7aa0bc6efc7ef43f68c192e2091108541acbaf1a/README.md", "population": "WebSRC v1.0 dev", "qualifier": "exact", "unit": "web pages", "value": 913 }, { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/X-LANCE/WebSRC_v1.0/raw/7aa0bc6efc7ef43f68c192e2091108541acbaf1a/README.md", "population": "WebSRC v1.0 test", "qualifier": "exact", "unit": "question–answer examples", "value": 40357 }, { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/X-LANCE/WebSRC_v1.0/raw/7aa0bc6efc7ef43f68c192e2091108541acbaf1a/README.md", "population": "WebSRC v1.0 test", "qualifier": "exact", "unit": "web pages", "value": 985 } ], "evidence_urls": [ "https://huggingface.co/datasets/X-LANCE/WebSRC_v1.0/raw/7aa0bc6efc7ef43f68c192e2091108541acbaf1a/README.md", "https://huggingface.co/api/datasets/X-LANCE/WebSRC_v1.0", "https://x-lance.github.io/WebSRC/" ], "formats": [ "CSV", "HTML", "JSON", "ZIP packages" ], "modalities": [ "questions and answers", "HTML", "screenshots", "layout metadata" ], "notes": "Each dataset.csv row is a QA example; web pages and QA examples are different units. Use the v1.0 split table rather than merging the older project headline into it. The card retains email-evaluation instructions, while the manifest now includes test answers; no submission was made. Payload archives were not downloaded.", "splits": [ "train", "dev", "test" ], "supervision": [ "extractive or yes/no answers", "answer DOM-element references" ] }, "licenses": { "code": null, "data": { "basis": "Publisher dataset-card declaration for this release; it does not establish rights to all upstream screenshots, applications or source content.", "declared": "CC-BY-4.0", "retrieved_at": "2026-10-18T04:35:16Z", "url": "https://huggingface.co/datasets/X-LANCE/WebSRC_v1.0/raw/7aa0bc6efc7ef43f68c192e2091108541acbaf1a/README.md" }, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:35:16Z", "role": "primary", "sha256": "061e5bcaa49e819f0133afb912ad5ce20a8c2b6c28ca60319a4635d6ce835ddb", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "notes", "relations", "licenses.data", "details.dataset_profile" ], "url": "https://huggingface.co/datasets/X-LANCE/WebSRC_v1.0/raw/7aa0bc6efc7ef43f68c192e2091108541acbaf1a/README.md" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-18T04:33:29Z", "role": "primary", "sha256": "a7976dd931c3fcf11de2456614f95eb071978599bd70fb89c0ea009d31da4300", "supports": [ "identity", "release_status", "details.hub_id", "details.hub_revision", "details.gated", "details.disabled", "details.download_url", "details.dataset_profile" ], "url": "https://huggingface.co/api/datasets/X-LANCE/WebSRC_v1.0" }, { "method": "editorial_primary_review", "retrieved_at": "2026-10-17T15:37:04Z", "role": "primary", "sha256": "3c2c601d8b4ad2f379cac9b97a2cbb901883d9bc6c1a682359f9b4135e6dd4bc", "supports": [ "notes", "details.dataset_profile" ], "url": "https://x-lance.github.io/WebSRC/" } ] }, { "id": "url:243ab00712ba19cc2089", "name": "WorkDemo-350", "url": "https://huggingface.co/datasets/yuqi777/WorkDemo-350", "environments": [ "desktop" ], "profile": { "counts": [ { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/yuqi777/WorkDemo-350/raw/main/README.md", "population": "packaged tasks/videos", "qualifier": "exact", "unit": "demonstrations", "value": 350 }, { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/yuqi777/WorkDemo-350/raw/main/README.md", "population": "final packaged images", "qualifier": "exact", "unit": "evidence images", "value": 8388 }, { "basis": "reported", "evidence_url": "https://huggingface.co/datasets/yuqi777/WorkDemo-350/raw/main/README.md", "population": "packaged action traces", "qualifier": "exact", "unit": "action records", "value": 11951 } ], "evidence_urls": [ "https://huggingface.co/datasets/yuqi777/WorkDemo-350/raw/main/README.md" ], "formats": [ "MP4", "PNG", "JSON", "JSONL", "commented key logs" ], "modalities": [ "screen video", "screenshots", "input events", "task text" ], "notes": "The OSWorld subset was selected post hoc using model outcomes; no train/test split is supplied. Coordinate calibration, task success, and complete anonymization are not established by package-format checks.", "splits": [], "supervision": [ "human workflow demonstrations", "skill induction" ] }, "licenses": { "code": null, "data": { "basis": "publisher model/dataset card metadata; third-party assets retain their own terms", "declared": "cc-by-4.0", "retrieved_at": "2026-10-16T10:47:49Z", "url": "https://huggingface.co/datasets/yuqi777/WorkDemo-350/raw/main/README.md" }, "document": null, "weights": null }, "evidence": [ { "method": "editorial_primary_review", "retrieved_at": "2026-10-16T10:47:49Z", "role": "primary", "sha256": "ae14cfe91c8c9a79edf1f306273a2ee9d1790b1dc5be0cd2d89e93df09db42f0", "supports": [ "name", "kind", "summary", "environments", "topics", "scope", "relations", "details.sample_count", "details.sample_unit", "details.modalities", "details.download_url", "details.dataset_profile" ], "url": "https://huggingface.co/datasets/yuqi777/WorkDemo-350/raw/main/README.md" }, { "method": "huggingface_card", "retrieved_at": "2026-10-16T10:47:49Z", "role": "primary", "sha256": "ae14cfe91c8c9a79edf1f306273a2ee9d1790b1dc5be0cd2d89e93df09db42f0", "supports": [ "licenses.data" ], "url": "https://huggingface.co/datasets/yuqi777/WorkDemo-350/raw/main/README.md" } ] } ] }