{"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/experience","entry":"Experience","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":3,"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":5,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":3,"unverified":2},"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":"2606.24428","paper":"/paper/arxiv-2606-24428","title":"Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"shidingz/EDV","path":"src/edv/pipeline.py","file_url":"https://github.com/shidingz/EDV/blob/HEAD/src/edv/pipeline.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"655a360541b6efd9","mcp_get_code":{"code_sha256":"655a360541b6efd9"}},{"arxiv_id":"2602.06025","paper":"/paper/arxiv-2602-06025","title":"Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"ViktorAxelsen/BudgetMem","path":"src/trainer/ppo_trainer.py","file_url":"https://github.com/ViktorAxelsen/BudgetMem/blob/HEAD/src/trainer/ppo_trainer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"22603ec8294c0b15","mcp_get_code":{"code_sha256":"22603ec8294c0b15"}},{"arxiv_id":"2306.00398","paper":"/paper/preference-grounded-token-level-guidance-for-1","title":"Preference-grounded Token-level Guidance for Language Model Fine-tuning","date":"2023-06-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yinyueqin/denserewardrlhf-ppo","path":"denserlhf/trainer/ppo_utils/experience_maker.py","file_url":"https://github.com/yinyueqin/denserewardrlhf-ppo/blob/HEAD/denserlhf/trainer/ppo_utils/experience_maker.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":"5017ac033cf345d5","mcp_get_code":{"code_sha256":"5017ac033cf345d5"}},{"arxiv_id":"2008.06043","paper":"/paper/offline-meta-reinforcement-learning-with","title":"Offline Meta-Reinforcement Learning with Advantage Weighting","date":"2020-08-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eric-mitchell/macaw-min","path":"impl.py","file_url":"https://github.com/eric-mitchell/macaw-min/blob/HEAD/impl.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b843875d4ee6d657","mcp_get_code":{"code_sha256":"b843875d4ee6d657"}},{"arxiv_id":"1511.05952","paper":"/paper/prioritized-experience-replay","title":"Prioritized Experience Replay","date":"2015-11-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Damcy/prioritized-experience-replay","path":"rank_based.py","file_url":"https://github.com/Damcy/prioritized-experience-replay/blob/HEAD/rank_based.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"02ee81b07942c502","mcp_get_code":{"code_sha256":"02ee81b07942c502"}}]}