{"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/resolve-model-name","entry":"resolve_model_name","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":5,"n_papers_ran":3,"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":6,"n_samples_ran":4,"n_samples_fingerprinted":3,"n_places":6,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":4,"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":"2607.20491","paper":"/paper/arxiv-2607-20491","title":"DFAH-Bench: Benchmarking Observable Agent Instability in Financial Decision-Making *","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"ibm-client-engineering/output-drift-financial-llms","path":"harness/load_models.py","file_url":"https://github.com/ibm-client-engineering/output-drift-financial-llms/blob/HEAD/harness/load_models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f8a9742e520382f7","mcp_get_code":{"code_sha256":"f8a9742e520382f7"}},{"arxiv_id":"2606.13662","paper":"/paper/arxiv-2606-13662","title":"EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"THU-Team-Eureka/EurekAgent","path":"src/pricing.py","file_url":"https://github.com/THU-Team-Eureka/EurekAgent/blob/HEAD/src/pricing.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"AGPL-3.0","inline_ok":false,"code_sha256_prefix":"0cf92ec0f0c10240","mcp_get_code":{"code_sha256":"0cf92ec0f0c10240"}},{"arxiv_id":"2605.28375","paper":"/paper/arxiv-2605-28375","title":"PrionNER: A Named Entity Recognition Dataset for Prion Disease Biomedical Literature","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"daotuanan/PrionNER","path":"code/train_bert_ner.py","file_url":"https://github.com/daotuanan/PrionNER/blob/HEAD/code/train_bert_ner.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"57dfe5261a9134b3","mcp_get_code":{"code_sha256":"57dfe5261a9134b3"}},{"arxiv_id":"2605.28375","paper":"/paper/arxiv-2605-28375","title":"PrionNER: A Named Entity Recognition Dataset for Prion Disease Biomedical Literature","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"daotuanan/PrionNER","path":"code/train_gliner2_ner.py","file_url":"https://github.com/daotuanan/PrionNER/blob/HEAD/code/train_gliner2_ner.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ea7bb9a0ef66200b","mcp_get_code":{"code_sha256":"ea7bb9a0ef66200b"}},{"arxiv_id":"2604.19459","paper":"/paper/arxiv-2604-19459","title":"Do LLMs Game Formalization? Evaluating Faithfulness in Logical Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"koreankiwi99/formalization-gaming","path":"src/utils/api_client.py","file_url":"https://github.com/koreankiwi99/formalization-gaming/blob/HEAD/src/utils/api_client.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a8c0ee30b68f960e","mcp_get_code":{"code_sha256":"a8c0ee30b68f960e"}},{"arxiv_id":"2506.15862","paper":null,"title":"arXiv:2506.15862","date":null,"month_inferred_from_arxiv_id":"2025-06","title_source":null,"repo":"Josh1108/MixtureRetrievers","path":"core/encoders.py","file_url":"https://github.com/Josh1108/MixtureRetrievers/blob/HEAD/core/encoders.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":"6a411cc92d0d5ee3","mcp_get_code":{"code_sha256":"6a411cc92d0d5ee3"}}]}