{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/get-unfinished","entry":"get_unfinished","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":5,"n_papers_ran":5,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":4,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":6,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":2,"unverified":1},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2606.31270","paper":"/paper/arxiv-2606-31270","title":"Learning from Failure: Inference-Time Self-Improvement for Computer-Use Agents","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"snow10072740/Learning_from_Failure","path":"run_autoglm.py","file_url":"https://github.com/snow10072740/Learning_from_Failure/blob/HEAD/run_autoglm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f3d6789ba3daef88","mcp_get_code":{"code_sha256":"f3d6789ba3daef88"}},{"arxiv_id":"2505.13934","paper":"/paper/rlvr-world-training-world-models-with","title":"RLVR-World: Training World Models with Reinforcement Learning","date":"2025-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thuml/RLVR-World","path":"lang_wm/webagent/run_for_trajectory.py","file_url":"https://github.com/thuml/RLVR-World/blob/HEAD/lang_wm/webagent/run_for_trajectory.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c4557f6bed96e135","mcp_get_code":{"code_sha256":"c4557f6bed96e135"}},{"arxiv_id":"2505.13934","paper":"/paper/rlvr-world-training-world-models-with","title":"RLVR-World: Training World Models with Reinforcement Learning","date":"2025-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thuml/RLVR-World","path":"lang_wm/webagent/run_w_world_model.py","file_url":"https://github.com/thuml/RLVR-World/blob/HEAD/lang_wm/webagent/run_w_world_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"93f43874ebbe522a","mcp_get_code":{"code_sha256":"93f43874ebbe522a"}},{"arxiv_id":"2503.09780","paper":"/paper/agentdam-privacy-leakage-evaluation-for","title":"AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents","date":"2025-03-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"c4557f6bed96e135","mcp_get_code":{"code_sha256":"c4557f6bed96e135"}},{"arxiv_id":"2410.13232","paper":"/paper/web-agents-with-world-models-learning-and","title":"Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation","date":"2024-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kyle8581/wma-agents","path":"run_for_trajectory.py","file_url":"https://github.com/kyle8581/wma-agents/blob/HEAD/run_for_trajectory.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c4557f6bed96e135","mcp_get_code":{"code_sha256":"c4557f6bed96e135"}},{"arxiv_id":"2404.07972","paper":"/paper/osworld-benchmarking-multimodal-agents-for","title":"OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments","date":"2024-04-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xlang-ai/OSWorld","path":"mm_agents/maestro/osworld_run_maestro.py","file_url":"https://github.com/xlang-ai/OSWorld/blob/HEAD/mm_agents/maestro/osworld_run_maestro.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"66d512885244b2c1","mcp_get_code":{"code_sha256":"66d512885244b2c1"}}]}