The run completed all 100 requested steps and saved checkpoints every 10 steps, but no actor optimization update was applied. All 100 update attempts were skipped because every training batch was marked score_only. A subsequent bitwise audit compared all 750 tensors (8,767,123,696 elements) and confirmed that this step-100 export is exactly equal to the pinned Model E base checkpoint. The held-out validation success rate was also unchanged at every evaluation: 11/193 (5.6995%).

This repository preserves the requested completed-run artifact and its full provenance. It should not be interpreted as an improved GRPO model.

Artifact identity

Run: uedgpo_q3_model_e_awlegacy_random_dense_v38_b200x4_s100_20260728
Step: 100
Base model: namhokaist/appgen-qwen3-vl-8b-sft-ngc-amex-avariant-E-ngc-lr2p5e7-1ep
Base revision: 6cdf0aa413850771f9a6f4c4da38f53d9d060f1c
Training code: grpo_ued_train at 750fce45b6dfb8550c352be950582a1bbccd654d
W&B run: https://wandb.ai/namhokoh-korea-advanced-institute-of-science-and-technology/ued-train-grpo/runs/q3e-awlegacy-v38-b200x4-randdense-s100-20260728

Random-GRPO contract

Reward shaping: potential-based dense reward, delta emission
Actor learning rate: 2e-7
Group size: 8; train rows: 8; PPO minibatch: 64
Maximum environment steps: 25
Replay probability: 0.0; adaptive replay disabled
UCB: disabled
Category sampling: target prior, hierarchical scope
Total steps: 100; checkpoint/evaluation interval: 10
Prompt profile: AndroidWorld legacy, text-first, 10-turn history
Coordinate space: normalized with denominator 999

Prompt and data provenance

System prompt: appgen_system_prompt.txt
Prompt bytes: 4,041
Prompt SHA-256: 8795391af87a58a1670a33ae3f3e568e2af46899bc9b93fdc795c5f1fbbedfaf
Environment data: luca0621/appgen-training-data@e96ee5f9f53b394a23ca1ce1912cb9ad40720842
Requested random pool: 331 environments; 327 passed runtime validation
Goal-text data: luca0621/appgen-sft-data@c195ae15abd3d6aaa07f971b8d732e7a28fa8dbf
Goal-text artifact: sft_qwen3_UNIFIED.json, 2,768 rows
Goal-text SHA-256: 0f6817d5c522d629437389aeec02d4d4f1fa88e7b10dd9770ad9d9569557f8bf

Final held-out validation

Category	Success / tasks	Rate
communication	0 / 28	0.00%
finance	1 / 13	7.69%
food and drink	1 / 17	5.88%
health and fitness	0 / 18	0.00%
maps and navigation	2 / 21	9.52%
productivity	1 / 22	4.55%
shopping	1 / 11	9.09%
social	1 / 15	6.67%
tools	3 / 20	15.00%
travel and local	1 / 28	3.57%
pooled	11 / 193	5.70%

The final mean partial-credit test score was 0.3516881456426913.

Verification files

appgen_grpo_manifest.json: exact run, prompt, base-model, and training contract
grpo_publication_identity.json: identity of this GRPO publication
step100_vs_base_weight_audit.json: zero-update and exact-weight-equality audit
run_manifest.json: inherited Model E SFT provenance
publication_identity.json and training_verification.json: inherited Model E publication records

Limitations

This artifact did not change the base model weights, so it should not be used to claim a Random-GRPO improvement. It is retained for reproducibility and diagnosis of the score-only training path. This model is for GUI-agent research and is not intended for safety-critical autonomous deployment.

namhokaist/appgen-qwen3-model-e-uedgrpo-awlegacy-randdense-v38-b200x4-s100-20260728-step100

AppGen Qwen3-VL Model E — Random-GRPO dense v38, step 100

Important training outcome