{"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/match-score","entry":"match_score","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":7,"n_papers_ran":6,"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":7,"n_samples_ran":6,"n_samples_fingerprinted":5,"n_places":7,"n_places_pointer_only":4,"by_status":{"ran_honours":2,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":2,"ran":2,"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":"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_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"94757c508755516a","mcp_get_code":{"code_sha256":"94757c508755516a"}},{"arxiv_id":"2504.13958","paper":"/paper/toolrl-reward-is-all-tool-learning-needs","title":"ToolRL: Reward is All Tool Learning Needs","date":"2025-04-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qiancheng0/toolrl","path":"verl/utils/reward_score/rlla.py","file_url":"https://github.com/qiancheng0/toolrl/blob/HEAD/verl/utils/reward_score/rlla.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"6281513745ecdf4e","mcp_get_code":{"code_sha256":"6281513745ecdf4e"}},{"arxiv_id":"2502.08265","paper":"/paper/exploring-the-potential-of-large-language-12","title":"Exploring the Potential of Large Language Models to Simulate Personality","date":"2025-02-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mary-silence/simulating_personality","path":"experiment_functions/questionnaire.py","file_url":"https://github.com/mary-silence/simulating_personality/blob/HEAD/experiment_functions/questionnaire.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"10fc91019ecc483f","mcp_get_code":{"code_sha256":"10fc91019ecc483f"}},{"arxiv_id":"2412.00207","paper":"/paper/can-llm-self-report-evaluating-the-validity","title":"Can LLM \"Self-report\"?: Evaluating the Validity of Self-report Scales in Measuring Personality Design in LLM-based Chatbots","date":null,"month_inferred_from_arxiv_id":"2024-12","title_source":"archive","repo":"isle-dev/self-report","path":"self_report.py","file_url":"https://github.com/isle-dev/self-report/blob/HEAD/self_report.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"328a2e7aef54aed2","mcp_get_code":{"code_sha256":"328a2e7aef54aed2"}},{"arxiv_id":"2402.18025","paper":"/paper/hire-a-linguist-learning-endangered-languages","title":"Hire a Linguist!: Learning Endangered Languages with In-Context Linguistic Descriptions","date":"2024-02-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"llilab/llm4endangeredlang","path":"fst_src/ilg_helpers.py","file_url":"https://github.com/llilab/llm4endangeredlang/blob/HEAD/fst_src/ilg_helpers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fa9257629938eebf","mcp_get_code":{"code_sha256":"fa9257629938eebf"}},{"arxiv_id":"2402.11100","paper":"/paper/when-llms-meet-cunning-questions-a-fallacy","title":"When LLMs Meet Cunning Texts: A Fallacy Understanding Benchmark for Large Language Models","date":"2024-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thukelab/flub","path":"code/analysis.py","file_url":"https://github.com/thukelab/flub/blob/HEAD/code/analysis.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"480af19711021070","mcp_get_code":{"code_sha256":"480af19711021070"}},{"arxiv_id":"2310.13774","paper":"/paper/seq2seq-is-all-you-need-for-coreference","title":"Seq2seq is All You Need for Coreference Resolution","date":"2023-10-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"WenzhengZhang/Seq2seqCoref","path":"alignment.py","file_url":"https://github.com/WenzhengZhang/Seq2seqCoref/blob/HEAD/alignment.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2f6a512c201dda17","mcp_get_code":{"code_sha256":"2f6a512c201dda17"}}]}