{"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/macro-f1","entry":"macro_f1","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":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":5,"n_samples_ran":4,"n_samples_fingerprinted":4,"n_places":5,"n_places_pointer_only":1,"by_status":{"ran_honours":2,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":1,"ran":0,"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":"2608.05817","paper":"/paper/arxiv-2608-05817","title":"M 3 R-Bench: A Unified Benchmark for Evidence-Grounded Multimodal Metaphor Understanding","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"hongshi4/M3R-Bench","path":"train/evaluate_sft_outputs.py","file_url":"https://github.com/hongshi4/M3R-Bench/blob/HEAD/train/evaluate_sft_outputs.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bc11bcbfa86ea6fa","mcp_get_code":{"code_sha256":"bc11bcbfa86ea6fa"}},{"arxiv_id":"2606.16535","paper":"/paper/arxiv-2606-16535","title":"Assessing Reliability of Symbol Detection in Concept Bottleneck Models","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"Fuminides/cbm_sanity","path":"src/symbol_sanity/multihead.py","file_url":"https://github.com/Fuminides/cbm_sanity/blob/HEAD/src/symbol_sanity/multihead.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"19b09245ff0215ab","mcp_get_code":{"code_sha256":"19b09245ff0215ab"}},{"arxiv_id":"2604.22937","paper":"/paper/arxiv-2604-22937","title":"AutoPyVerifier: Learning Compact Executable Verifiers for Large Language Model Outputs","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"megagonlabs/AutoPyVerifier","path":"src/autopyverifier/search.py","file_url":"https://github.com/megagonlabs/AutoPyVerifier/blob/HEAD/src/autopyverifier/search.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"d7ee35668f18f66e","mcp_get_code":{"code_sha256":"d7ee35668f18f66e"}},{"arxiv_id":"2102.01335","paper":"/paper/neural-data-augmentation-via-example","title":"Neural Data Augmentation via Example Extrapolation","date":"2021-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google/example_extrapolation","path":"tasks.py","file_url":"https://github.com/google/example_extrapolation/blob/HEAD/tasks.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7e6b1e68cbf8c750","mcp_get_code":{"code_sha256":"7e6b1e68cbf8c750"}},{"arxiv_id":"1806.10701","paper":"/paper/empirical-risk-minimization-and-stochastic","title":"Empirical Risk Minimization and Stochastic Gradient Descent for Relational Data","date":"2018-06-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wooden-spoon/relational-ERM","path":"src/relational_erm/models/metrics.py","file_url":"https://github.com/wooden-spoon/relational-ERM/blob/HEAD/src/relational_erm/models/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"29195ba13112cc60","mcp_get_code":{"code_sha256":"29195ba13112cc60"}}]}