{ "schema_version": 1, "experiment": "7-12", "status": "complete", "generated_at_utc": "2026-08-04T09:35:34.274750+00:00", "run_dir": "chapter7/android-world/validation", "git_commit": "0d0df3e758872c7e73a998e57d2e529b16ece095", "command": "Five isolated Pixel 6/API-33 trial shards used run_controlled_experiment.py with local-vLLM credentials supplied only by environment-variable name; merge_candidate_shards.py strictly merged trials 1-5.", "provider_receipt_count": 0, "status_reasons": [ "580/580 direct episodes completed across 116 tasks x five trials with zero runtime errors; evaluator failures are retained.", "Every shard completed official Pixel 6/API-33 setup and recorded the same 24/24 required package versions.", "The result is negative: 26/580 strict successes and deployment is not approved.", "The candidate used local Qwen2.5-7B while the paired H5C source used Doubao, so no same-model uplift or noninferiority is claimed.", "All disclosed evaluator, emulator-race, context-limit, resume, and exact-parameter retry compatibility treatments remain in retained evidence." ], "inputs": [ { "path": "chapter7/android-world/experiment_core.py", "bytes": 24201, "sha256": "752c1f181f0bef3cb0726fcc35eddc8c715624c4804c39b9a2d371518f4b3ac6" }, { "path": "chapter7/android-world/run_controlled_experiment.py", "bytes": 76108, "sha256": "ebc5417066fadbcd3de15d878d8b95a6ab9bff7f1b8e9eec392d148dbc59817e" }, { "path": "chapter7/android-world/merge_candidate_shards.py", "bytes": 11368, "sha256": "c7b0519c2246e88750f91859603fd34fea72a67f04c1e8eacb8fc5d2d63cd0f1" }, { "path": "chapter7/android-world/t3a_summary.md", "bytes": 28800, "sha256": "e5616507e2b0658b64dc5d0e2c08e6207eba12da8345a31d1cb85bf68957f002" }, { "path": "chapter7/android-world/t3a_failed_analysis.md", "bytes": 14448, "sha256": "7486112a3bf0791a17ca72b81b3745dcd92936416b5c3da937618c8d7a6eb00d" } ], "artifacts": [ { "path": "chapter7/android-world/validation/candidate_h5c_api33_local_qwen_20260804/evidence.json", "bytes": 3932422, "sha256": "526e73e061bbafa3802484934dd29512a3b94a6a066d0efa10fc44c3f8138083" }, { "path": "chapter7/android-world/validation/candidate_h5c_api33_local_qwen_20260804/report.md", "bytes": 70854, "sha256": "4b4222ba4597eb57f35f40a30de180284d00a8fa66824e5492c75c4c8ce8b96a" }, { "path": "chapter7/android-world/validation/candidate_h5c_api33_local_shard1/evidence.json", "bytes": 833946, "sha256": "8c9bad94ee2141c4de2e666e291f41e1f7d7cf7c53a8ad77a73ab17341bb68a3" }, { "path": "chapter7/android-world/validation/candidate_h5c_api33_local_shard1/report.md", "bytes": 23232, "sha256": "6113f7d935c4c1f085a53a4a2f0be5e9d8053e47c5aa4434d56a6a5d7c56e6a4" }, { "path": "chapter7/android-world/validation/candidate_h5c_api33_local_shard2/evidence.json", "bytes": 805331, "sha256": "2cf319e6eb7f99758c7dd093a46d445afa29ff35a919afc5f08f01c0a2085f44" }, { "path": "chapter7/android-world/validation/candidate_h5c_api33_local_shard2/report.md", "bytes": 22455, "sha256": "573f6fa57a846d6b231db2702069afff277434f39518deec8b64bdc0720eac92" }, { "path": "chapter7/android-world/validation/candidate_h5c_api33_local_shard3/evidence.json", "bytes": 815150, "sha256": "9b4bfed4165696044768c9e05fa00d696469ea99a06e9d3f694ea817a1041911" }, { "path": "chapter7/android-world/validation/candidate_h5c_api33_local_shard3/report.md", "bytes": 22157, "sha256": "8e37b4fdaf97eaa0bc14a6a161bcf14914ae6512782a94b5901c7bbfc361806a" }, { "path": "chapter7/android-world/validation/candidate_h5c_api33_local_shard4/evidence.json", "bytes": 820872, "sha256": "4da385617b9b2f7a3d684884fd79184970e23d862583ab6b622b48f975e15696" }, { "path": "chapter7/android-world/validation/candidate_h5c_api33_local_shard4/report.md", "bytes": 21949, "sha256": "509a9224d6ce823c6d9ccff15a962fafdc0ed0b9724c053c2d83754517764f02" }, { "path": "chapter7/android-world/validation/candidate_h5c_api33_local_shard5/evidence.json", "bytes": 808670, "sha256": "245f99f7a8924d1b8340e510a6b12f345ac35ea779099605755d15d180109ce3" }, { "path": "chapter7/android-world/validation/candidate_h5c_api33_local_shard5/report.md", "bytes": 21696, "sha256": "4d22f0cdeb7b5f82560241b2f91169b94629c1f9cca2f320de4f54f5f1b99479" }, { "path": "chapter7/android-world/validation/paired_h5_a11y_api35_20260729/evidence.json", "bytes": 47072, "sha256": "b2276e35e1f58d32775ea70ac04142a7d3075c074b9f31d40b153e1be10f93da" }, { "path": "chapter7/android-world/validation/paired_h5_a11y_api35_20260729/report.md", "bytes": 8239, "sha256": "5d5b0db9580020c286096ca53617cbd2d0f7fb811e48c4cf51688212ef638272" }, { "path": "chapter7/android-world/validation/paired_h5c_compact_api35_20260729/evidence.json", "bytes": 39643, "sha256": "a60204b6c0ac187b0ae9a68182b5ada302420fc31b2fc22c308e10eb1242e390" }, { "path": "chapter7/android-world/validation/paired_h5c_compact_api35_20260729/report.md", "bytes": 8930, "sha256": "55abde0ef9a6d5ed090f26bc99e424346c42a5e98036a278bd50edcf4bf48f2e" }, { "path": "chapter7/android-world/validation/paired_wifi_api35_20260729/evidence.json", "bytes": 45941, "sha256": "a1665bffafed7b8935db03dc4369435015f784d6f6465fe09c7da86fc0504635" }, { "path": "chapter7/android-world/validation/paired_wifi_api35_20260729/report.md", "bytes": 4096, "sha256": "067f176e4722082afd45bedbd79a392b26d677d54013a8b14a81cea1fbd70d57" } ] }