{"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/cosine","entry":"cosine","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":20,"n_papers_ran":12,"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":16,"n_samples_ran":7,"n_samples_fingerprinted":6,"n_places":22,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":2,"ran_draft_wrong":0,"ran_fixture":0,"ran":5,"unverified":9},"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":"2607.29441","paper":"/paper/arxiv-2607-29441","title":"End-to-End Fairness Optimization with Fair Decision-Focused Learning","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"DennisWang2488/fair-dfl","path":"fair_dfl_moo/src/fair_dfl/metrics.py","file_url":"https://github.com/DennisWang2488/fair-dfl/blob/HEAD/fair_dfl_moo/src/fair_dfl/metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3cd6b9b5e395742f","mcp_get_code":{"code_sha256":"3cd6b9b5e395742f"}},{"arxiv_id":"2607.26339","paper":"/paper/arxiv-2607-26339","title":"RAGuard: A Layered Defense Framework for Retrieval-Augmented Generation Systems Against Data Poisoning","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"RAGuard-AI/RAGuard","path":"zkip.py","file_url":"https://github.com/RAGuard-AI/RAGuard/blob/HEAD/zkip.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cf8c7150e4ab53bb","mcp_get_code":{"code_sha256":"cf8c7150e4ab53bb"}},{"arxiv_id":"2607.10617","paper":"/paper/arxiv-2607-10617","title":"modelDNA: Calibrated Lineage Verification and Merge Decomposition from Sampled Weight Fingerprints","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"AwaisAdilKhokhar/modelDNA","path":"src/modeldna/compare.py","file_url":"https://github.com/AwaisAdilKhokhar/modelDNA/blob/HEAD/src/modeldna/compare.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f174ba05861dd3e2","mcp_get_code":{"code_sha256":"f174ba05861dd3e2"}},{"arxiv_id":"2607.09691","paper":"/paper/arxiv-2607-09691","title":"What Context Does a Coding Agent Actually Need to Act?","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"integrallis/act-context","path":"src/dhcm_ng/embed.py","file_url":"https://github.com/integrallis/act-context/blob/HEAD/src/dhcm_ng/embed.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ae2a1aba1e25a436","mcp_get_code":{"code_sha256":"ae2a1aba1e25a436"}},{"arxiv_id":"2602.22182","paper":"/paper/arxiv-2602-22182","title":"LiCQA : A Lightweight Complex Question Answering System","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"souravsaha/licqa","path":"code/sentence_embedding_ranking.py","file_url":"https://github.com/souravsaha/licqa/blob/HEAD/code/sentence_embedding_ranking.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a2a8999f1b9ffa71","mcp_get_code":{"code_sha256":"a2a8999f1b9ffa71"}},{"arxiv_id":"2402.18458","paper":"/paper/meta-task-prompting-elicits-embedding-from","title":"Meta-Task Prompting Elicits Embeddings from Large Language Models","date":"2024-02-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yibin-lei/metaeol","path":"SentEval/senteval/utils.py","file_url":"https://github.com/yibin-lei/metaeol/blob/HEAD/SentEval/senteval/utils.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a2a8999f1b9ffa71","mcp_get_code":{"code_sha256":"a2a8999f1b9ffa71"}},{"arxiv_id":"2310.02012","paper":"/paper/towards-training-without-depth-limits-batch","title":"Towards Training Without Depth Limits: Batch Normalization Without Gradient Explosion","date":"2023-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alexandrumeterez/bngrad","path":"src/modules/utils.py","file_url":"https://github.com/alexandrumeterez/bngrad/blob/HEAD/src/modules/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"58d2ba2db914e81d","mcp_get_code":{"code_sha256":"58d2ba2db914e81d"}},{"arxiv_id":"2309.05098","paper":"/paper/3d-implicit-transporter-for-temporally","title":"3D Implicit Transporter for Temporally Consistent Keypoint Discovery","date":"2023-09-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhongcl-thu/3D-Implicit-Transporter","path":"core/losses/pose_loss.py","file_url":"https://github.com/zhongcl-thu/3D-Implicit-Transporter/blob/HEAD/core/losses/pose_loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"63dac5bcaa4953a7","mcp_get_code":{"code_sha256":"63dac5bcaa4953a7"}},{"arxiv_id":"2211.06127","paper":"/paper/english-contrastive-learning-can-learn","title":"English Contrastive Learning Can Learn Universal Cross-lingual Sentence Embeddings","date":"2022-11-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yaushian/msimcse","path":"eval/evaluation_xsts.py","file_url":"https://github.com/yaushian/msimcse/blob/HEAD/eval/evaluation_xsts.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a2a8999f1b9ffa71","mcp_get_code":{"code_sha256":"a2a8999f1b9ffa71"}},{"arxiv_id":"2207.12201","paper":"/paper/calibrated-one-class-classification-for","title":"Calibrated One-class Classification for Unsupervised Time Series Anomaly Detection","date":"2022-07-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xuhongzuo/couta","path":"src/experiments/data_generator_collective_case.py","file_url":"https://github.com/xuhongzuo/couta/blob/HEAD/src/experiments/data_generator_collective_case.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":"1be0714f24c5f3db","mcp_get_code":{"code_sha256":"1be0714f24c5f3db"}},{"arxiv_id":"2204.11660","paper":"/paper/a-survey-on-word-meta-embedding-learning","title":"A Survey on Word Meta-Embedding Learning","date":"2022-04-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Bollegala/Meta-Embedding-Framework","path":"wordreps.py","file_url":"https://github.com/Bollegala/Meta-Embedding-Framework/blob/HEAD/wordreps.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bf95ee6195f77f93","mcp_get_code":{"code_sha256":"bf95ee6195f77f93"}},{"arxiv_id":"2109.07437","paper":"/paper/should-we-be-pre-training-an-argument-for-end","title":"Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative","date":"2021-09-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ldery/tartan","path":"simple_vision_tartan/tartan_utils.py","file_url":"https://github.com/ldery/tartan/blob/HEAD/simple_vision_tartan/tartan_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c54b69f5721172e3","mcp_get_code":{"code_sha256":"c54b69f5721172e3"}},{"arxiv_id":"2104.15114","paper":"/paper/paraphrastic-representations-at-scale","title":"Paraphrastic Representations at Scale","date":"2021-04-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"a2a8999f1b9ffa71","mcp_get_code":{"code_sha256":"a2a8999f1b9ffa71"}},{"arxiv_id":"2008.01998","paper":"/paper/optimal-variance-control-of-the-score","title":"Optimal Variance Control of the Score Function Gradient Estimator for Importance Weighted Bounds","date":"2020-08-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vlievin/ovis","path":"ovis/analysis/utils.py","file_url":"https://github.com/vlievin/ovis/blob/HEAD/ovis/analysis/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ab7404dcc5622e61","mcp_get_code":{"code_sha256":"ab7404dcc5622e61"}},{"arxiv_id":"2003.08561","paper":"/paper/xtarnet-learning-to-extract-task-adaptive","title":"XtarNet: Learning to Extract Task-Adaptive Representation for Incremental Few-Shot Learning","date":"2020-03-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"EdwinKim3069/XtarNet","path":"run_proto_exp.py","file_url":"https://github.com/EdwinKim3069/XtarNet/blob/HEAD/run_proto_exp.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4dedc68d854ae87b","mcp_get_code":{"code_sha256":"4dedc68d854ae87b"}},{"arxiv_id":"1909.13872","paper":"/paper/simple-and-effective-paraphrastic-similarity-1","title":"Simple and Effective Paraphrastic Similarity from Parallel Translations","date":"2019-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jwieting/paraphrastic-representations-at-scale","path":"score_sentence_pairs.py","file_url":"https://github.com/jwieting/paraphrastic-representations-at-scale/blob/HEAD/score_sentence_pairs.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"a2a8999f1b9ffa71","mcp_get_code":{"code_sha256":"a2a8999f1b9ffa71"}},{"arxiv_id":"1905.07790","paper":"/paper/correlation-coefficients-and-semantic-textual","title":"Correlation Coefficients and Semantic Textual Similarity","date":"2019-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Babylonpartners/corrsim","path":"senteval/utils.py","file_url":"https://github.com/Babylonpartners/corrsim/blob/HEAD/senteval/utils.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a2a8999f1b9ffa71","mcp_get_code":{"code_sha256":"a2a8999f1b9ffa71"}},{"arxiv_id":"1905.07790","paper":"/paper/correlation-coefficients-and-semantic-textual","title":"Correlation Coefficients and Semantic Textual Similarity","date":"2019-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Babylonpartners/corrsim","path":"evaluation/wordsim_eval.py","file_url":"https://github.com/Babylonpartners/corrsim/blob/HEAD/evaluation/wordsim_eval.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":"f2117d4a4682efc4","mcp_get_code":{"code_sha256":"f2117d4a4682efc4"}},{"arxiv_id":"1905.07790","paper":"/paper/correlation-coefficients-and-semantic-textual","title":"Correlation Coefficients and Semantic Textual Similarity","date":"2019-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Babylonpartners/corrsim","path":"similarity/baseline.py","file_url":"https://github.com/Babylonpartners/corrsim/blob/HEAD/similarity/baseline.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":"aac4af37868d65c4","mcp_get_code":{"code_sha256":"aac4af37868d65c4"}},{"arxiv_id":"1810.07218","paper":"/paper/incremental-few-shot-learning-with-attention","title":"Incremental Few-Shot Learning with Attention Attractor Networks","date":"2018-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"renmengye/inc-few-shot-attractor-public","path":"run_proto_exp.py","file_url":"https://github.com/renmengye/inc-few-shot-attractor-public/blob/HEAD/run_proto_exp.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4dedc68d854ae87b","mcp_get_code":{"code_sha256":"4dedc68d854ae87b"}},{"arxiv_id":"1412.6623","paper":"/paper/word-representations-via-gaussian-embedding","title":"Word Representations via Gaussian Embedding","date":"2014-12-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"seomoz/word2gauss","path":"word2gauss/utils.py","file_url":"https://github.com/seomoz/word2gauss/blob/HEAD/word2gauss/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9bcaf4440155a17a","mcp_get_code":{"code_sha256":"9bcaf4440155a17a"}},{"arxiv_id":"aaai_33848","paper":null,"title":"arXiv:aaai_33848","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"grodino/QuRD","path":"qurd/fingerprint/distance.py","file_url":"https://github.com/grodino/QuRD/blob/HEAD/qurd/fingerprint/distance.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8c07999ef25c0edd","mcp_get_code":{"code_sha256":"8c07999ef25c0edd"}}]}