{"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/vp-beta-schedule","entry":"vp_beta_schedule","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":10,"n_papers_ran":10,"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":5,"n_samples_fingerprinted":2,"n_places":10,"n_places_pointer_only":5,"by_status":{"ran_honours":3,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":2,"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":"2605.21282","paper":"/paper/arxiv-2605-21282","title":"Stochastic MeanFlow Policies: One-Step Generative Control with Entropic Mirror Descent","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"diffusionyes/MaxEntDP","path":"jaxrl5/networks/diffusion.py","file_url":"https://github.com/diffusionyes/MaxEntDP/blob/HEAD/jaxrl5/networks/diffusion.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"539aaf559a17a19a","mcp_get_code":{"code_sha256":"539aaf559a17a19a"}},{"arxiv_id":"2502.05932","paper":"/paper/skill-expansion-and-composition-in-parameter","title":"Skill Expansion and Composition in Parameter Space","date":"2025-02-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ltlhuuu/PSEC","path":"jaxrl5/networks/diffusion.py","file_url":"https://github.com/ltlhuuu/PSEC/blob/HEAD/jaxrl5/networks/diffusion.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"539aaf559a17a19a","mcp_get_code":{"code_sha256":"539aaf559a17a19a"}},{"arxiv_id":"2502.05450","paper":"/paper/conrft-a-reinforced-fine-tuning-method-for","title":"ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy","date":"2025-02-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cccedric/conrft","path":"serl_launcher/serl_launcher/networks/diffusion_nets.py","file_url":"https://github.com/cccedric/conrft/blob/HEAD/serl_launcher/serl_launcher/networks/diffusion_nets.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"539aaf559a17a19a","mcp_get_code":{"code_sha256":"539aaf559a17a19a"}},{"arxiv_id":"2402.06559","paper":"/paper/diffusion-es-gradient-free-planning-with","title":"Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous Driving and Zero-Shot Instruction Following","date":"2024-02-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bhyang/diffusion-es","path":"nuplan-devkit/nuplan/planning/training/modeling/models/diffusion_utils.py","file_url":"https://github.com/bhyang/diffusion-es/blob/HEAD/nuplan-devkit/nuplan/planning/training/modeling/models/diffusion_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"76f83814a33af5eb","mcp_get_code":{"code_sha256":"76f83814a33af5eb"}},{"arxiv_id":"2401.10700","paper":"/paper/safe-offline-reinforcement-learning-with","title":"Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model","date":"2024-01-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhengyinan-air/fisor","path":"jaxrl5/networks/diffusion.py","file_url":"https://github.com/zhengyinan-air/fisor/blob/HEAD/jaxrl5/networks/diffusion.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4567300f0e6b808c","mcp_get_code":{"code_sha256":"4567300f0e6b808c"}},{"arxiv_id":"2312.11752","paper":"/paper/learning-a-diffusion-model-policy-from","title":"Learning a Diffusion Model Policy from Rewards via Q-Score Matching","date":"2023-12-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Alescontrela/score_matching_rl","path":"jaxrl5/agents/score_matching/score_matching_learner.py","file_url":"https://github.com/Alescontrela/score_matching_rl/blob/HEAD/jaxrl5/agents/score_matching/score_matching_learner.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"539aaf559a17a19a","mcp_get_code":{"code_sha256":"539aaf559a17a19a"}},{"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_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"47c7ce0ace6e7c47","mcp_get_code":{"code_sha256":"47c7ce0ace6e7c47"}},{"arxiv_id":"2308.12952","paper":"/paper/bridgedata-v2-a-dataset-for-robot-learning-at","title":"BridgeData V2: A Dataset for Robot Learning at Scale","date":"2023-08-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rail-berkeley/BridgeData-V2","path":"jaxrl_m/networks/diffusion_nets.py","file_url":"https://github.com/rail-berkeley/BridgeData-V2/blob/HEAD/jaxrl_m/networks/diffusion_nets.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"539aaf559a17a19a","mcp_get_code":{"code_sha256":"539aaf559a17a19a"}},{"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":"tinnerhrhe/MTDiff","path":"diffuser/models/helpers.py","file_url":"https://github.com/tinnerhrhe/MTDiff/blob/HEAD/diffuser/models/helpers.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"47c7ce0ace6e7c47","mcp_get_code":{"code_sha256":"47c7ce0ace6e7c47"}},{"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_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"25a711883c5a59fe","mcp_get_code":{"code_sha256":"25a711883c5a59fe"}}]}