{"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/eval-accuracy","entry":"eval_accuracy","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":1,"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":1,"n_samples_fingerprinted":0,"n_places":8,"n_places_pointer_only":5,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":1,"ran":0,"unverified":5},"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":"2609.02684","paper":"/paper/arxiv-2609-02684","title":"H3DNAS: Hardware-Aware ONNX-Native 3D Point Cloud Model Compression","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"ClarityLab-Org/h3dnas","path":"h3dnas/datapipe/evaluators.py","file_url":"https://github.com/ClarityLab-Org/h3dnas/blob/HEAD/h3dnas/datapipe/evaluators.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":"e8423b7f577e3884","mcp_get_code":{"code_sha256":"e8423b7f577e3884"}},{"arxiv_id":"2602.03486","paper":"/paper/arxiv-2602-03486","title":"DeepDFA: Injecting Temporal Logic in Deep Learning for Sequential Subsymbolic Applications","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"KRLGroup/DeepDFAGrounding","path":"utils.py","file_url":"https://github.com/KRLGroup/DeepDFAGrounding/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"99e1d633cb48cb20","mcp_get_code":{"code_sha256":"99e1d633cb48cb20"}},{"arxiv_id":"2411.02988","paper":"/paper/confidence-calibration-of-classifiers-with","title":"Confidence Calibration of Classifiers with Many Classes","date":"2024-11-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mominabbass/LinC","path":"run_classification.py","file_url":"https://github.com/mominabbass/LinC/blob/HEAD/run_classification.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4db3f48d30d8c5af","mcp_get_code":{"code_sha256":"4db3f48d30d8c5af"}},{"arxiv_id":"2401.12406","paper":"/paper/enhancing-in-context-learning-via-linear","title":"Enhancing In-context Learning via Linear Probe Calibration","date":"2024-01-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mominabbass/linc","path":"run_classification.py","file_url":"https://github.com/mominabbass/linc/blob/HEAD/run_classification.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4db3f48d30d8c5af","mcp_get_code":{"code_sha256":"4db3f48d30d8c5af"}},{"arxiv_id":"2312.04021","paper":"/paper/a-study-on-the-calibration-of-in-context","title":"A Study on the Calibration of In-context Learning","date":"2023-12-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hlzhang109/icl-calibration","path":"run_classification.py","file_url":"https://github.com/hlzhang109/icl-calibration/blob/HEAD/run_classification.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"556aa6b923228885","mcp_get_code":{"code_sha256":"556aa6b923228885"}},{"arxiv_id":"2112.01008","paper":"/paper/editing-a-classifier-by-rewriting-its-1","title":"Editing a classifier by rewriting its prediction rules","date":"2021-12-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"madrylab/editingclassifiers","path":"helpers/classifier_helpers.py","file_url":"https://github.com/madrylab/editingclassifiers/blob/HEAD/helpers/classifier_helpers.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"12410dbd824f0347","mcp_get_code":{"code_sha256":"12410dbd824f0347"}},{"arxiv_id":"2102.09690","paper":"/paper/calibrate-before-use-improving-few-shot","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","date":"2021-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tonyzhaozh/few-shot-learning","path":"run_classification.py","file_url":"https://github.com/tonyzhaozh/few-shot-learning/blob/HEAD/run_classification.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":"7753000f9482cac5","mcp_get_code":{"code_sha256":"7753000f9482cac5"}},{"arxiv_id":"2005.14165","paper":"/paper/language-models-are-few-shot-learners","title":"Language Models are Few-Shot Learners","date":"2020-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"7753000f9482cac5","mcp_get_code":{"code_sha256":"7753000f9482cac5"}}]}