B-MoCA
Mobile control benchmark with varied interface configurations.
AI-assisted editorial review against a primary source. This is a catalog annotation, not an independent reproduction or endorsement.
What is this resource?
- Resource type
- Benchmarks
- Environment
- android
- Topics
- evaluation, robustness
- Record publication date
- Not recorded
- Evidence retrieved
- 2026-10-16T06:35:58Z
- Resource ID
- github:jylee425/b-moca
What licenses are recorded?
Code, training data, weights, and documents can have different terms. A blank declaration means unknown, not unrestricted use.
- Code
- Apache-2.0 (repository LICENSE header; not a weights/data license)
- Data
- Not recorded
- Document
- Not recorded
- Weights
- Not recorded
Evaluation protocol
- Focus
- Android control across visual/device variation, generalization across environment snapshots
- Setting
- interactive
- Observations
- screenshot pixels, XML view hierarchy, goal instruction
- Actions / outputs
- normalized touch/lift coordinate pairs for tap or swipe
- Evaluation
- Task success is detected using Appium; positive task reward terminates the episode. Environment variants change device/locale/wallpaper/DPI/dark mode and are loaded as snapshots. The numeric action interface is (touch_y, touch_x, lift_y, lift_x); wrapper/tanh transformations must be kept with the evaluated agent.
Scale and counting units
- 131 task-definition files — asset/tasks/**/*.textproto in retained release/ver.3 tree; not a paper test-task total (computed) source
- 35 environment configuration rows — environments_train.csv, retained release/ver.3 snapshot (computed) source
- 10 environment configuration rows — environments_test.csv, retained release/ver.3 snapshot (computed) source
Current source inventory differs in grain from published experiment subsets: do not multiply 131 definitions by 35/10 configuration rows or label the product as evaluated tasks. Setup requires Android API 29, Appium, external app versions and generated AVD snapshots. No apps/snapshots were downloaded or run. Code Apache-2.0 does not establish data or app rights.
Compare source-reviewed profiles
Explore related topics
Primary evidence and verification
Source retrieval is separate from experiment reproduction. Use the original publication or publisher page when citing claims about the resource.
- editorial primary review
Retrieved 2026-10-16T06:35:58Z. Supports: name, kind, summary, environments, topics, scope, relations, details.benchmark_protocol.
Content fingerprint
bd1354c8008d7d79d4883c0c037b7918392f86fab61391b39b52e507b04672ce - editorial primary review
Retrieved 2026-10-17T14:14:05Z. Supports: details.benchmark_protocol.
Content fingerprint
06ba40a5e0d5fb52e7bf5e5df636cb8e8bbbc56a8308dc6d528012489f7650ee - editorial primary review
Retrieved 2026-10-17T14:24:53Z. Supports: details.benchmark_protocol.
Content fingerprint
34bc0c23949732e0a8091e334d59d2d41cae49a82cde850247aa0e6d739d2464 - editorial primary review
Retrieved 2026-10-17T14:21:10Z. Supports: details.benchmark_protocol.
Content fingerprint
d866af344c0cff5255b813576f2e9e9c5c2964e6809058b39e2b5180af71d946 - editorial primary review
Retrieved 2026-10-17T14:23:14Z. Supports: details.benchmark_protocol.
Content fingerprint
c278cc28f8a0667b7fdc6ba638704cfbe43783cd496181231c45c865087543f3 - editorial primary review
Retrieved 2026-10-17T14:23:15Z. Supports: details.benchmark_protocol.
Content fingerprint
4b92933fe4f4f66e71a694b579940db11bedd5ea8f153752a44e633825b06fa3 - license header
Retrieved 2026-10-16T06:41:58Z. Supports: licenses.code.
Content fingerprint
cfc7749b96f63bd31c3c42b5c471bf756814053e847c10f3eb003417bc523d30 - github repository identity
Retrieved 2026-10-17T14:14:03Z. Supports: aliases.
Content fingerprint
9d4706306b04960f0eb4298887496961efdee6b7d41445e82abcac489d63779f - github repository identity
Retrieved 2026-10-17T14:14:04Z. Supports: aliases.
Content fingerprint
9d4706306b04960f0eb4298887496961efdee6b7d41445e82abcac489d63779f
Suggest a correction
Open a source-backed correction. Include this record ID and the original source. Read our editorial policy and coverage boundaries.