{"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/gen-net","entry":"gen_net","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":7,"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":8,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":1,"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":"2607.13172","paper":"/paper/arxiv-2607-13172","title":"Learning Safe Agent Behaviour from Human Preferences and Justifications via World Models","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"ilkaza/DROPJ","path":"reward_model_pref.py","file_url":"https://github.com/ilkaza/DROPJ/blob/HEAD/reward_model_pref.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8dfae1ca61764388","mcp_get_code":{"code_sha256":"8dfae1ca61764388"}},{"arxiv_id":"2506.12822","paper":"/paper/enhancing-rating-based-reinforcement-learning","title":"Enhancing Rating-Based Reinforcement Learning to Effectively Leverage Feedback from Large Vision-Language Models","date":"2025-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tunglm2203/erlvlm","path":"reward_model_vlm_rating.py","file_url":"https://github.com/tunglm2203/erlvlm/blob/HEAD/reward_model_vlm_rating.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":"a17d99b8eda680ff","mcp_get_code":{"code_sha256":"a17d99b8eda680ff"}},{"arxiv_id":"2506.00388","paper":"/paper/clarify-contrastive-preference-reinforcement","title":"CLARIFY: Contrastive Preference Reinforcement Learning for Untangling Ambiguous Queries","date":"2025-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"moonoutcloudback/clarify_pbrl","path":"reward_model.py","file_url":"https://github.com/moonoutcloudback/clarify_pbrl/blob/HEAD/reward_model.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":"a17d99b8eda680ff","mcp_get_code":{"code_sha256":"a17d99b8eda680ff"}},{"arxiv_id":"2310.15709","paper":"/paper/causal-representation-learning-made","title":"Causal Representation Learning Made Identifiable by Grouping of Observational Variables","date":"2023-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hmorioka/gcarl","path":"subfunc/generate_dataset.py","file_url":"https://github.com/hmorioka/gcarl/blob/HEAD/subfunc/generate_dataset.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":"aadafdde9f61d6f7","mcp_get_code":{"code_sha256":"aadafdde9f61d6f7"}},{"arxiv_id":"2305.17400","paper":"/paper/query-policy-misalignment-in-preference-based","title":"Query-Policy Misalignment in Preference-Based Reinforcement Learning","date":"2023-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"huxiao09/QPA","path":"reward_model.py","file_url":"https://github.com/huxiao09/QPA/blob/HEAD/reward_model.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":"a17d99b8eda680ff","mcp_get_code":{"code_sha256":"a17d99b8eda680ff"}},{"arxiv_id":"2205.03990","paper":"/paper/predicting-parametric-spatiotemporal-dynamics","title":"Multi-resolution partial differential equations preserved learning framework for spatiotemporal dynamics","date":"2022-05-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jianxun-wang/ppnn","path":"src/models.py","file_url":"https://github.com/jianxun-wang/ppnn/blob/HEAD/src/models.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1a1ef27bd5a830bc","mcp_get_code":{"code_sha256":"1a1ef27bd5a830bc"}},{"arxiv_id":"2111.03026","paper":"/paper/b-pref-benchmarking-preference-based","title":"B-Pref: Benchmarking Preference-Based Reinforcement Learning","date":"2021-11-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rll-research/B-Pref","path":"reward_model.py","file_url":"https://github.com/rll-research/B-Pref/blob/HEAD/reward_model.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":"a17d99b8eda680ff","mcp_get_code":{"code_sha256":"a17d99b8eda680ff"}},{"arxiv_id":"2106.05091","paper":"/paper/pebble-feedback-efficient-interactive","title":"PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training","date":"2021-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rll-research/bpref","path":"reward_model.py","file_url":"https://github.com/rll-research/bpref/blob/HEAD/reward_model.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":"a17d99b8eda680ff","mcp_get_code":{"code_sha256":"a17d99b8eda680ff"}}]}