{"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/calculate-confusion-matrix","entry":"calculate_confusion_matrix","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":0,"n_places":5,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":1,"ran":3,"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":"2408.16266","paper":"/paper/improving-diffusion-based-data-augmentation","title":"Inversion Circle Interpolation: Diffusion-based Image Augmentation for Data-scarce Classification","date":"2024-08-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"scuwyh2000/diff-ii","path":"utils.py","file_url":"https://github.com/scuwyh2000/diff-ii/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"334ec5d32fa6d718","mcp_get_code":{"code_sha256":"334ec5d32fa6d718"}},{"arxiv_id":"2404.09556","paper":"/paper/nnu-net-revisited-a-call-for-rigorous","title":"nnU-Net Revisited: A Call for Rigorous Validation in 3D Medical Image Segmentation","date":"2024-04-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DeepMicroscopy/nnUNet","path":"nnunetv2/evaluation.py","file_url":"https://github.com/DeepMicroscopy/nnUNet/blob/HEAD/nnunetv2/evaluation.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":"58d38fedb5114f60","mcp_get_code":{"code_sha256":"58d38fedb5114f60"}},{"arxiv_id":"2403.20078","paper":"/paper/negative-label-guided-ood-detection-with","title":"Negative Label Guided OOD Detection with Pretrained Vision-Language Models","date":"2024-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tmlr-group/NegLabel","path":"mmcls/core/evaluation/eval_metrics.py","file_url":"https://github.com/tmlr-group/NegLabel/blob/HEAD/mmcls/core/evaluation/eval_metrics.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":"7aa2a71e9cdafd0a","mcp_get_code":{"code_sha256":"7aa2a71e9cdafd0a"}},{"arxiv_id":"2403.19600","paper":"/paper/enhance-image-classification-via-inter-class","title":"Enhance Image Classification via Inter-Class Image Mixup with Diffusion Model","date":"2024-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhicaiwww/diff-mix","path":"downstream_tasks/mixup.py","file_url":"https://github.com/zhicaiwww/diff-mix/blob/HEAD/downstream_tasks/mixup.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cd1bc928867e1ef4","mcp_get_code":{"code_sha256":"cd1bc928867e1ef4"}},{"arxiv_id":"2311.05081","paper":"/paper/generalized-test-utilities-for-long-tail","title":"Generalized test utilities for long-tail performance in extreme multi-label classification","date":"2023-11-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mwydmuch/macro-measures-in-xmlc","path":"xcolumns/frank_wolfe.py","file_url":"https://github.com/mwydmuch/macro-measures-in-xmlc/blob/HEAD/xcolumns/frank_wolfe.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f77c581447ce8785","mcp_get_code":{"code_sha256":"f77c581447ce8785"}}]}