{"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/get-feedback","entry":"get_feedback","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":4,"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":4,"n_samples_fingerprinted":2,"n_places":10,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":3,"unverified":4},"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":"2601.10712","paper":"/paper/arxiv-2601-10712","title":"MatchTIR: Fine-Grained Supervision for Tool-Integrated Reasoning via Bipartite Matching","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"quchangle1/MatchTIR","path":"Code/verl/utils/reward_score/tool.py","file_url":"https://github.com/quchangle1/MatchTIR/blob/HEAD/Code/verl/utils/reward_score/tool.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":"3673b46bdbf2a6ac","mcp_get_code":{"code_sha256":"3673b46bdbf2a6ac"}},{"arxiv_id":"2501.11858","paper":"/paper/embodiedeval-evaluate-multimodal-llms-as","title":"EmbodiedEval: Evaluate Multimodal LLMs as Embodied Agents","date":"2025-01-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thunlp/embodiedeval","path":"predicate.py","file_url":"https://github.com/thunlp/embodiedeval/blob/HEAD/predicate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"eb552bd8bc6c7308","mcp_get_code":{"code_sha256":"eb552bd8bc6c7308"}},{"arxiv_id":"2404.00530","paper":"/paper/comparing-bad-apples-to-good-oranges-aligning","title":"Comparing Bad Apples to Good Oranges: Aligning Large Language Models via Joint Preference Optimization","date":"2024-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hritikbansal/dove","path":"jpo/ai_feedback.py","file_url":"https://github.com/hritikbansal/dove/blob/HEAD/jpo/ai_feedback.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"841ccc2439e64906","mcp_get_code":{"code_sha256":"841ccc2439e64906"}},{"arxiv_id":"2404.00530","paper":"/paper/comparing-bad-apples-to-good-oranges-aligning","title":"Comparing Bad Apples to Good Oranges: Aligning Large Language Models via Joint Preference Optimization","date":"2024-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hritikbansal/dove","path":"jpo/auto_eval.py","file_url":"https://github.com/hritikbansal/dove/blob/HEAD/jpo/auto_eval.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4abdf461254ec7ab","mcp_get_code":{"code_sha256":"4abdf461254ec7ab"}},{"arxiv_id":"2402.01306","paper":"/paper/kto-model-alignment-as-prospect-theoretic","title":"KTO: Model Alignment as Prospect Theoretic Optimization","date":"2024-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"contextualai/halos","path":"train/data.py","file_url":"https://github.com/contextualai/halos/blob/HEAD/train/data.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":"1ed0ab0ac3d9655a","mcp_get_code":{"code_sha256":"1ed0ab0ac3d9655a"}},{"arxiv_id":"2306.07012","paper":"/paper/generating-language-corrections-for-teaching","title":"Generating Language Corrections for Teaching Physical Control Tasks","date":"2023-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Stanford-ILIAD/corgi","path":"interfaces/teaching-interface/generator.py","file_url":"https://github.com/Stanford-ILIAD/corgi/blob/HEAD/interfaces/teaching-interface/generator.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2ab7a6b7bfaa426f","mcp_get_code":{"code_sha256":"2ab7a6b7bfaa426f"}},{"arxiv_id":"1910.04365","paper":"/paper/asking-easy-questions-a-user-friendly","title":"Asking Easy Questions: A User-Friendly Approach to Active Reward Learning","date":"2019-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Stanford-ILIAD/easy-active-learning","path":"simulation_utils.py","file_url":"https://github.com/Stanford-ILIAD/easy-active-learning/blob/HEAD/simulation_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"355e0f4248993f2b","mcp_get_code":{"code_sha256":"355e0f4248993f2b"}},{"arxiv_id":"1810.04303","paper":"/paper/batch-active-preference-based-learning-of","title":"Batch Active Preference-Based Learning of Reward Functions","date":"2018-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Stanford-ILIAD/batch-active-preference-based-learning","path":"simulation_utils.py","file_url":"https://github.com/Stanford-ILIAD/batch-active-preference-based-learning/blob/HEAD/simulation_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2a6e648f2f77d0f5","mcp_get_code":{"code_sha256":"2a6e648f2f77d0f5"}},{"arxiv_id":"2025.findings-acl.39","paper":null,"title":"arXiv:2025.findings-acl.39","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Hritikbansal/jpo","path":"jpo/ai_feedback.py","file_url":"https://github.com/Hritikbansal/jpo/blob/HEAD/jpo/ai_feedback.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"841ccc2439e64906","mcp_get_code":{"code_sha256":"841ccc2439e64906"}},{"arxiv_id":"2025.findings-acl.39","paper":null,"title":"arXiv:2025.findings-acl.39","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Hritikbansal/jpo","path":"jpo/auto_eval.py","file_url":"https://github.com/Hritikbansal/jpo/blob/HEAD/jpo/auto_eval.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4abdf461254ec7ab","mcp_get_code":{"code_sha256":"4abdf461254ec7ab"}}]}