{"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/weightedl2","entry":"WeightedL2","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":8,"n_papers_ran":8,"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":8,"n_samples_ran":8,"n_samples_fingerprinted":6,"n_places":8,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":8,"unverified":0},"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":"2603.17685","paper":"/paper/arxiv-2603-17685","title":"Flow Matching Policy Optimization with Mirror Descent and Entropy Constraints","date":"2026-03-18","month_inferred_from_arxiv_id":null,"title_source":"syntology","repo":"wadx2019/qvpo","path":"agent/qvpo.py","file_url":"https://github.com/wadx2019/qvpo/blob/HEAD/agent/qvpo.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3b2b8b659d67b0af","mcp_get_code":{"code_sha256":"3b2b8b659d67b0af"}},{"arxiv_id":"2510.11499","paper":"/paper/arxiv-2510-11499","title":"Offline Reinforcement Learning with Generative Trajectory Policies","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"wmd3i/gtp","path":"agents/diffusion.py","file_url":"https://github.com/wmd3i/gtp/blob/HEAD/agents/diffusion.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"56917a389275eaae","mcp_get_code":{"code_sha256":"56917a389275eaae"}},{"arxiv_id":"2402.07226","paper":"/paper/stitching-sub-trajectories-with-conditional","title":"Stitching Sub-Trajectories with Conditional Diffusion Model for Goal-Conditioned Offline RL","date":"2024-02-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rlatjddbs/SSD","path":"dc/dc.py","file_url":"https://github.com/rlatjddbs/SSD/blob/HEAD/dc/dc.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"264959cf75b98c11","mcp_get_code":{"code_sha256":"264959cf75b98c11"}},{"arxiv_id":"2310.05333","paper":"/paper/diffcps-diffusion-model-based-constrained","title":"DiffCPS: Diffusion Model based Constrained Policy Search for Offline Reinforcement Learning","date":"2023-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"felix-thu/DiffCPS","path":"agents/diffcps.py","file_url":"https://github.com/felix-thu/DiffCPS/blob/HEAD/agents/diffcps.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1b472abd57f98492","mcp_get_code":{"code_sha256":"1b472abd57f98492"}},{"arxiv_id":"2309.16984","paper":"/paper/consistency-models-as-a-rich-and-efficient","title":"Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learning","date":"2023-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"quantumiracle/consistency_model_for_reinforcement_learning","path":"agents/consistency.py","file_url":"https://github.com/quantumiracle/consistency_model_for_reinforcement_learning/blob/HEAD/agents/consistency.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"04bd445ebe6af984","mcp_get_code":{"code_sha256":"04bd445ebe6af984"}},{"arxiv_id":"2305.18459","paper":"/paper/diffusion-model-is-an-effective-planner-and-1","title":"Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning","date":"2023-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jannerm/diffuser","path":"diffuser/models/diffusion.py","file_url":"https://github.com/jannerm/diffuser/blob/HEAD/diffuser/models/diffusion.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"63bb8b129db38dfb","mcp_get_code":{"code_sha256":"63bb8b129db38dfb"}},{"arxiv_id":"2210.15629","paper":"/paper/lad-language-augmented-diffusion-for","title":"Language Control Diffusion: Efficiently Scaling through Space, Time, and Tasks","date":"2022-10-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ezhang7423/language-control-diffusion","path":"src/lcd/models/diffusion.py","file_url":"https://github.com/ezhang7423/language-control-diffusion/blob/HEAD/src/lcd/models/diffusion.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"33d5229f504bb6ae","mcp_get_code":{"code_sha256":"33d5229f504bb6ae"}},{"arxiv_id":"2208.06193","paper":"/paper/diffusion-policies-as-an-expressive-policy","title":"Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning","date":"2022-08-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zzmtsvv/rl_task","path":"diffusion_ql/dql.py","file_url":"https://github.com/zzmtsvv/rl_task/blob/HEAD/diffusion_ql/dql.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"480e0c2c2219727e","mcp_get_code":{"code_sha256":"480e0c2c2219727e"}}]}