{"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/ensemblize","entry":"ensemblize","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":12,"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":2,"n_samples_fingerprinted":0,"n_places":12,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":0,"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":"2609.15883","paper":"/paper/arxiv-2609-15883","title":"Learning Multimodal One-step Flow Policy via Value-weighted Optimal Transport","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"Yonsei-DILLab/OptiFlow","path":"optiflow/networks.py","file_url":"https://github.com/Yonsei-DILLab/OptiFlow/blob/HEAD/optiflow/networks.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":"f157becc6d5dd71b","mcp_get_code":{"code_sha256":"f157becc6d5dd71b"}},{"arxiv_id":"2608.01205","paper":"/paper/arxiv-2608-01205","title":"ReBRAC-v2: The Return of the King","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"JongseongChae/FAC","path":"agents/rebrac.py","file_url":"https://github.com/JongseongChae/FAC/blob/HEAD/agents/rebrac.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":"f157becc6d5dd71b","mcp_get_code":{"code_sha256":"f157becc6d5dd71b"}},{"arxiv_id":"2606.11087","paper":"/paper/arxiv-2606-11087","title":"Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"zhouzypaul/qgf","path":"utils/networks.py","file_url":"https://github.com/zhouzypaul/qgf/blob/HEAD/utils/networks.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":"f157becc6d5dd71b","mcp_get_code":{"code_sha256":"f157becc6d5dd71b"}},{"arxiv_id":"2510.15382","paper":"/paper/arxiv-2510-15382","title":"Towards Robust Zero-Shot Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"seohongpark/HILP","path":"hilp_gcrl/jaxrl_m/networks.py","file_url":"https://github.com/seohongpark/HILP/blob/HEAD/hilp_gcrl/jaxrl_m/networks.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7f174e0d2fe49c08","mcp_get_code":{"code_sha256":"7f174e0d2fe49c08"}},{"arxiv_id":"2506.08902","paper":"/paper/intention-conditioned-flow-occupancy-models","title":"Intention-Conditioned Flow Occupancy Models","date":"2025-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chongyi-zheng/infom","path":"agents/infom.py","file_url":"https://github.com/chongyi-zheng/infom/blob/HEAD/agents/infom.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e2b6e84f73d1d030","mcp_get_code":{"code_sha256":"e2b6e84f73d1d030"}},{"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/actor_critic_nets.py","file_url":"https://github.com/cccedric/conrft/blob/HEAD/serl_launcher/serl_launcher/networks/actor_critic_nets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4e9a6a46c6aeee0b","mcp_get_code":{"code_sha256":"4e9a6a46c6aeee0b"}},{"arxiv_id":"2412.07762","paper":"/paper/efficient-online-reinforcement-learning-fine","title":"Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data","date":"2024-12-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhouzypaul/wsrl","path":"wsrl/networks/actor_critic_nets.py","file_url":"https://github.com/zhouzypaul/wsrl/blob/HEAD/wsrl/networks/actor_critic_nets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4e9a6a46c6aeee0b","mcp_get_code":{"code_sha256":"4e9a6a46c6aeee0b"}},{"arxiv_id":"2402.17135","paper":"/paper/unsupervised-zero-shot-reinforcement-learning","title":"Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings","date":"2024-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kvfrans/fre","path":"common/networks/basic.py","file_url":"https://github.com/kvfrans/fre/blob/HEAD/common/networks/basic.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7f174e0d2fe49c08","mcp_get_code":{"code_sha256":"7f174e0d2fe49c08"}},{"arxiv_id":"2402.15567","paper":"/paper/foundation-policies-with-hilbert","title":"Foundation Policies with Hilbert Representations","date":"2024-02-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"seohongpark/hilp","path":"hilp_gcrl/jaxrl_m/networks.py","file_url":"https://github.com/seohongpark/hilp/blob/HEAD/hilp_gcrl/jaxrl_m/networks.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7f174e0d2fe49c08","mcp_get_code":{"code_sha256":"7f174e0d2fe49c08"}},{"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/actor_critic_nets.py","file_url":"https://github.com/rail-berkeley/BridgeData-V2/blob/HEAD/jaxrl_m/networks/actor_critic_nets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4e9a6a46c6aeee0b","mcp_get_code":{"code_sha256":"4e9a6a46c6aeee0b"}},{"arxiv_id":"2307.11949","paper":"/paper/hiql-offline-goal-conditioned-rl-with-latent-1","title":"HIQL: Offline Goal-Conditioned RL with Latent States as Actions","date":"2023-07-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"seohongpark/hiql","path":"jaxrl_m/networks.py","file_url":"https://github.com/seohongpark/hiql/blob/HEAD/jaxrl_m/networks.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7f174e0d2fe49c08","mcp_get_code":{"code_sha256":"7f174e0d2fe49c08"}},{"arxiv_id":"openreview_RdkOaK4q6p","paper":null,"title":"arXiv:openreview_RdkOaK4q6p","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"2012060/DFQL","path":"utils/networks.py","file_url":"https://github.com/2012060/DFQL/blob/HEAD/utils/networks.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":"f157becc6d5dd71b","mcp_get_code":{"code_sha256":"f157becc6d5dd71b"}}]}