{"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/sinkhorn","entry":"sinkhorn","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":47,"n_papers_ran":35,"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":47,"n_samples_ran":34,"n_samples_fingerprinted":20,"n_places":51,"n_places_pointer_only":23,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":14,"ran_fixture":11,"ran":9,"unverified":13},"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":"2607.09126","paper":"/paper/arxiv-2607-09126","title":"VTaMo: Video-Text Alignment Model for Sign Language Translation","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"junyi2005/vtamo","path":"vtamo/ot_sinkhorn.py","file_url":"https://github.com/junyi2005/vtamo/blob/HEAD/vtamo/ot_sinkhorn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"4b98eb7a7db4a79f","mcp_get_code":{"code_sha256":"4b98eb7a7db4a79f"}},{"arxiv_id":"2604.05060","paper":"/paper/arxiv-2604-05060","title":"R3PM-Net: Real-time, Robust, Real-world Point Matching Network","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"YasiiKB/R3PM-Net","path":"r3pm_net/model.py","file_url":"https://github.com/YasiiKB/R3PM-Net/blob/HEAD/r3pm_net/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6de325d6b2842746","mcp_get_code":{"code_sha256":"6de325d6b2842746"}},{"arxiv_id":"2603.14392","paper":"/paper/arxiv-2603-14392","title":"WestWorld: A Knowledge-Encoded Scalable Trajectory World Model for Diverse Robotic Systems","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"511205787/WestWorld","path":"models/WestWorld/mamba_moe.py","file_url":"https://github.com/511205787/WestWorld/blob/HEAD/models/WestWorld/mamba_moe.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"771c65667dd313cc","mcp_get_code":{"code_sha256":"771c65667dd313cc"}},{"arxiv_id":"2602.23353","paper":"/paper/arxiv-2602-23353","title":"SOTAlign: Semi-Supervised Alignment of Unimodal Vision and Language Models via Optimal Transport","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"ExplainableML/SOTAlign","path":"src/optimal_transport/klot.py","file_url":"https://github.com/ExplainableML/SOTAlign/blob/HEAD/src/optimal_transport/klot.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e923560e828c8607","mcp_get_code":{"code_sha256":"e923560e828c8607"}},{"arxiv_id":"2601.01653","paper":"/paper/arxiv-2601-01653","title":"Learning Resilient Elections with Adversarial GNNs","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"MarkHaoxiang/geometric-governance","path":"src/geometric_governance/model/sinkhorn.py","file_url":"https://github.com/MarkHaoxiang/geometric-governance/blob/HEAD/src/geometric_governance/model/sinkhorn.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6a6e9165af567cd8","mcp_get_code":{"code_sha256":"6a6e9165af567cd8"}},{"arxiv_id":"2510.10136","paper":"/paper/arxiv-2510-10136","title":"PermLLM: Learnable Channel Permutation for N:M Sparse Large Language Models","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"lanchengzou/PermLLM","path":"lib/learnable_sparsity.py","file_url":"https://github.com/lanchengzou/PermLLM/blob/HEAD/lib/learnable_sparsity.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7819985853d82f66","mcp_get_code":{"code_sha256":"7819985853d82f66"}},{"arxiv_id":"2506.08694","paper":"/paper/mosic-optimal-transport-motion-trajectory-for","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","date":"2025-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SMSD75/MoSiC","path":"experiments/exp_mosic.py","file_url":"https://github.com/SMSD75/MoSiC/blob/HEAD/experiments/exp_mosic.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"432bf71f80b71af8","mcp_get_code":{"code_sha256":"432bf71f80b71af8"}},{"arxiv_id":"2412.08139","paper":"/paper/wasserstein-distance-rivals-kullback-leibler","title":"Wasserstein Distance Rivals Kullback-Leibler Divergence for Knowledge Distillation","date":"2024-12-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JiamingLv/WKD","path":"mdistiller/distillers/WKD.py","file_url":"https://github.com/JiamingLv/WKD/blob/HEAD/mdistiller/distillers/WKD.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e6f1ae7024ada5d7","mcp_get_code":{"code_sha256":"e6f1ae7024ada5d7"}},{"arxiv_id":"2411.01833","paper":"/paper/owmatch-conditional-self-labeling-with","title":"OwMatch: Conditional Self-Labeling with Consistency for Open-World Semi-Supervised Learning","date":"2024-11-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"niusj03/OwMatch","path":"utils.py","file_url":"https://github.com/niusj03/OwMatch/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f781192145291ab9","mcp_get_code":{"code_sha256":"f781192145291ab9"}},{"arxiv_id":"2410.04383","paper":"/paper/braincodec-neural-fmri-codec-for-the-decoding","title":"BrainCodec: Neural fMRI codec for the decoding of cognitive brain states","date":"2024-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amano-k-lab/BrainCodec","path":"braincodec/F2_sinkhorn_algorithm/compare_two_encodec.py","file_url":"https://github.com/amano-k-lab/BrainCodec/blob/HEAD/braincodec/F2_sinkhorn_algorithm/compare_two_encodec.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8fbfa70ae7d40c40","mcp_get_code":{"code_sha256":"8fbfa70ae7d40c40"}},{"arxiv_id":"2410.03052","paper":"/paper/learning-structured-representations-by","title":"Learning Structured Representations by Embedding Class Hierarchy with Fast Optimal Transport","date":"2024-10-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uiuctml/OTCPCC","path":"loss.py","file_url":"https://github.com/uiuctml/OTCPCC/blob/HEAD/loss.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8cf6df4a3ab3e2a1","mcp_get_code":{"code_sha256":"8cf6df4a3ab3e2a1"}},{"arxiv_id":"2404.01340","paper":"/paper/from-similarity-to-superiority-channel","title":"From Similarity to Superiority: Channel Clustering for Time Series Forecasting","date":"2024-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"graph-and-geometric-learning/timeseriesccm","path":"models/layers.py","file_url":"https://github.com/graph-and-geometric-learning/timeseriesccm/blob/HEAD/models/layers.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3e002910aaac8995","mcp_get_code":{"code_sha256":"3e002910aaac8995"}},{"arxiv_id":"2402.03094","paper":"/paper/cross-domain-few-shot-object-detection-via","title":"Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector","date":"2024-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lovelyqian/CDFSOD-benchmark","path":"lib/prototype_learner.py","file_url":"https://github.com/lovelyqian/CDFSOD-benchmark/blob/HEAD/lib/prototype_learner.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":"f8c7f9605872c11b","mcp_get_code":{"code_sha256":"f8c7f9605872c11b"}},{"arxiv_id":"2311.07070","paper":"/paper/explain-then-translate-an-analysis-on","title":"Explain-then-Translate: An Analysis on Improving Program Translation with Self-generated Explanations","date":"2023-11-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pootiet/explain-then-translate","path":"CodeGenMirror/codegen_sources/model/contex_embed.py","file_url":"https://github.com/pootiet/explain-then-translate/blob/HEAD/CodeGenMirror/codegen_sources/model/contex_embed.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a61f428c6d2822f2","mcp_get_code":{"code_sha256":"a61f428c6d2822f2"}},{"arxiv_id":"2311.03236","paper":"/paper/out-of-distribution-detection-learning-with","title":"Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sources","date":"2023-11-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tmlr-group/ATOL","path":"utils/ot.py","file_url":"https://github.com/tmlr-group/ATOL/blob/HEAD/utils/ot.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"79f77411b14d1a67","mcp_get_code":{"code_sha256":"79f77411b14d1a67"}},{"arxiv_id":"2311.00660","paper":"/paper/tpsence-towards-artifact-free-realistic-rain","title":"TPSeNCE: Towards Artifact-Free Realistic Rain Generation for Deraining and Object Detection in Rain","date":"2023-11-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shenzheng2000/tpsence","path":"models/sinkhorn.py","file_url":"https://github.com/shenzheng2000/tpsence/blob/HEAD/models/sinkhorn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fb73c79b58608d62","mcp_get_code":{"code_sha256":"fb73c79b58608d62"}},{"arxiv_id":"2310.17622","paper":"/paper/combating-representation-learning-disparity-1","title":"Combating Representation Learning Disparity with Geometric Harmonization","date":"2023-10-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MediaBrain-SJTU/Geometric-Harmonization","path":"utils.py","file_url":"https://github.com/MediaBrain-SJTU/Geometric-Harmonization/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"38b1cfaaa3fc1906","mcp_get_code":{"code_sha256":"38b1cfaaa3fc1906"}},{"arxiv_id":"2309.12969","paper":"/paper/detect-every-thing-with-few-examples","title":"Detect Everything with Few Examples","date":"2023-09-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mlzxy/devit","path":"lib/prototype_learner.py","file_url":"https://github.com/mlzxy/devit/blob/HEAD/lib/prototype_learner.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f8c7f9605872c11b","mcp_get_code":{"code_sha256":"f8c7f9605872c11b"}},{"arxiv_id":"2308.11796","paper":"/paper/time-does-tell-self-supervised-time-tuning-of","title":"Time Does Tell: Self-Supervised Time-Tuning of Dense Image Representations","date":"2023-08-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SMSD75/Timetuning","path":"time_tuning.py","file_url":"https://github.com/SMSD75/Timetuning/blob/HEAD/time_tuning.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"0988ed5686f818dc","mcp_get_code":{"code_sha256":"0988ed5686f818dc"}},{"arxiv_id":"2304.14837","paper":"/paper/imp-iterative-matching-and-pose-estimation","title":"IMP: Iterative Matching and Pose Estimation with Adaptive Pooling","date":"2023-04-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"feixue94/imp-release","path":"nets/adgm.py","file_url":"https://github.com/feixue94/imp-release/blob/HEAD/nets/adgm.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"630be194366638dc","mcp_get_code":{"code_sha256":"630be194366638dc"}},{"arxiv_id":"2303.13800","paper":"/paper/aligning-step-by-step-instructional-diagrams","title":"Aligning Step-by-Step Instructional Diagrams to Video Demonstrations","date":"2023-03-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DavidZhang73/AssemblyVideoManualAlignment","path":"src/models/optimal_transport.py","file_url":"https://github.com/DavidZhang73/AssemblyVideoManualAlignment/blob/HEAD/src/models/optimal_transport.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8564c1ce2632bd6e","mcp_get_code":{"code_sha256":"8564c1ce2632bd6e"}},{"arxiv_id":"2302.03857","paper":"/paper/efficient-adversarial-contrastive-learning-1","title":"Efficient Adversarial Contrastive Learning via Robustness-Aware Coreset Selection","date":"2023-02-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"godxuxilie/efficient_acl_via_rcs","path":"ACL_RCS/ImageNet_32/RCS.py","file_url":"https://github.com/godxuxilie/efficient_acl_via_rcs/blob/HEAD/ACL_RCS/ImageNet_32/RCS.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"79f77411b14d1a67","mcp_get_code":{"code_sha256":"79f77411b14d1a67"}},{"arxiv_id":"2302.00796","paper":"/paper/unsupervised-entity-alignment-for-temporal","title":"Unsupervised Entity Alignment for Temporal Knowledge Graphs","date":"2023-02-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zju-daily/dualmatch","path":"seu_tkg.py","file_url":"https://github.com/zju-daily/dualmatch/blob/HEAD/seu_tkg.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":"ff5e3f83e9e31d8d","mcp_get_code":{"code_sha256":"ff5e3f83e9e31d8d"}},{"arxiv_id":"2301.13197","paper":"/paper/unlocking-slot-attention-by-changing-optimal","title":"Unlocking Slot Attention by Changing Optimal Transport Costs","date":"2023-01-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"davzha/mesh","path":"mesh.py","file_url":"https://github.com/davzha/mesh/blob/HEAD/mesh.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7b387f03d008ebab","mcp_get_code":{"code_sha256":"7b387f03d008ebab"}},{"arxiv_id":"2301.13197","paper":"/paper/unlocking-slot-attention-by-changing-optimal","title":"Unlocking Slot Attention by Changing Optimal Transport Costs","date":"2023-01-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"davzha/mesh","path":"mesh.py","file_url":"https://github.com/davzha/mesh/blob/HEAD/mesh.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b221f655428e68d1","mcp_get_code":{"code_sha256":"b221f655428e68d1"}},{"arxiv_id":"2210.17067","paper":"/paper/unified-optimal-transport-framework-for","title":"Unified Optimal Transport Framework for Universal Domain Adaptation","date":"2022-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"changwxx/uniot-for-unida","path":"utils/lib.py","file_url":"https://github.com/changwxx/uniot-for-unida/blob/HEAD/utils/lib.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2be40bf60ede15a3","mcp_get_code":{"code_sha256":"2be40bf60ede15a3"}},{"arxiv_id":"2209.10365","paper":"/paper/solar-sinkhorn-label-refinery-for-imbalanced","title":"SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learning","date":"2022-09-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hbzju/solar","path":"utils/utils_algo.py","file_url":"https://github.com/hbzju/solar/blob/HEAD/utils/utils_algo.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"20a223338dad54e7","mcp_get_code":{"code_sha256":"20a223338dad54e7"}},{"arxiv_id":"2209.10365","paper":"/paper/solar-sinkhorn-label-refinery-for-imbalanced","title":"SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learning","date":"2022-09-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hbzju/solar","path":"utils/utils_algo.py","file_url":"https://github.com/hbzju/solar/blob/HEAD/utils/utils_algo.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3d92a88b2f69ccf1","mcp_get_code":{"code_sha256":"3d92a88b2f69ccf1"}},{"arxiv_id":"2207.12795","paper":"/paper/static-and-dynamic-concepts-for-self","title":"Static and Dynamic Concepts for Self-supervised Video Representation Learning","date":"2022-07-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shvdiwnkozbw/Self-supervised-Video-Concept","path":"model.py","file_url":"https://github.com/shvdiwnkozbw/Self-supervised-Video-Concept/blob/HEAD/model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ede20b10087a299b","mcp_get_code":{"code_sha256":"ede20b10087a299b"}},{"arxiv_id":"2207.02968","paper":"/paper/unsupervised-manifold-alignment-with-joint","title":"Unsupervised Manifold Alignment with Joint Multidimensional Scaling","date":"2022-07-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"constantinosskitsas/Framework_GraphAlignment","path":"algorithms/MDS/joint_mds.py","file_url":"https://github.com/constantinosskitsas/Framework_GraphAlignment/blob/HEAD/algorithms/MDS/joint_mds.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2776a5c88ed0bf3b","mcp_get_code":{"code_sha256":"2776a5c88ed0bf3b"}},{"arxiv_id":"2205.14258","paper":"/paper/on-the-symmetries-of-deep-learning-models-and","title":"On the Symmetries of Deep Learning Models and their Internal Representations","date":"2022-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pnnl/modelsym","path":"model_symmetries/stitching/stitching.py","file_url":"https://github.com/pnnl/modelsym/blob/HEAD/model_symmetries/stitching/stitching.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"57f3995b8ea26d10","mcp_get_code":{"code_sha256":"57f3995b8ea26d10"}},{"arxiv_id":"2204.07141","paper":"/paper/masked-siamese-networks-for-label-efficient","title":"Masked Siamese Networks for Label-Efficient Learning","date":"2022-04-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lightly-ai/lightly","path":"lightly/loss/msn_loss.py","file_url":"https://github.com/lightly-ai/lightly/blob/HEAD/lightly/loss/msn_loss.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c1dff37f3b19bb53","mcp_get_code":{"code_sha256":"c1dff37f3b19bb53"}},{"arxiv_id":"2112.09445","paper":"/paper/data-efficient-language-supervised-zero-shot-2","title":"Data Efficient Language-supervised Zero-shot Recognition with Optimal Transport Distillation","date":"2021-12-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/otter","path":"models/model_util.py","file_url":"https://github.com/facebookresearch/otter/blob/HEAD/models/model_util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"470b932b453c7bbe","mcp_get_code":{"code_sha256":"470b932b453c7bbe"}},{"arxiv_id":"2106.06381","paper":"/paper/improving-pretrained-cross-lingual-language","title":"Improving Pretrained Cross-Lingual Language Models via Self-Labeled Word Alignment","date":"2021-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CZWin32768/XLM-Align","path":"word_aligner/xlmalign-ot-aligner.py","file_url":"https://github.com/CZWin32768/XLM-Align/blob/HEAD/word_aligner/xlmalign-ot-aligner.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c5bc5e64bf6f281c","mcp_get_code":{"code_sha256":"c5bc5e64bf6f281c"}},{"arxiv_id":"2101.03961","paper":"/paper/switch-transformers-scaling-to-trillion","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","date":"2021-01-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zyphra/blackmamba","path":"switch_mlp.py","file_url":"https://github.com/zyphra/blackmamba/blob/HEAD/switch_mlp.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bfbd162761e2e475","mcp_get_code":{"code_sha256":"bfbd162761e2e475"}},{"arxiv_id":"2009.13077","paper":"/paper/distribution-matching-for-crowd-counting","title":"Distribution Matching for Crowd Counting","date":"2020-09-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cvlab-stonybrook/DM-Count","path":"losses/ot_loss.py","file_url":"https://github.com/cvlab-stonybrook/DM-Count/blob/HEAD/losses/ot_loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4a7bb1df79ece9e0","mcp_get_code":{"code_sha256":"4a7bb1df79ece9e0"}},{"arxiv_id":"2007.06168","paper":"/paper/model-fusion-with-kullback-leibler-divergence","title":"Model Fusion with Kullback--Leibler Divergence","date":"2020-07-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IBM/KL-fusion","path":"src/fusion.py","file_url":"https://github.com/IBM/KL-fusion/blob/HEAD/src/fusion.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c30e8f6c51130d25","mcp_get_code":{"code_sha256":"c30e8f6c51130d25"}},{"arxiv_id":"2006.12065","paper":"/paper/an-optimal-transport-kernel-for-feature","title":"A Trainable Optimal Transport Embedding for Feature Aggregation and its Relationship to Attention","date":"2020-06-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"claying/OTK","path":"otk/layers.py","file_url":"https://github.com/claying/OTK/blob/HEAD/otk/layers.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"55a8cdfd0f911b6a","mcp_get_code":{"code_sha256":"55a8cdfd0f911b6a"}},{"arxiv_id":"2006.09882","paper":"/paper/unsupervised-learning-of-visual-features-by","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","date":"2020-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lightly-ai/lightly","path":"lightly/loss/swav_loss.py","file_url":"https://github.com/lightly-ai/lightly/blob/HEAD/lightly/loss/swav_loss.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"58db645a1b52ab84","mcp_get_code":{"code_sha256":"58db645a1b52ab84"}},{"arxiv_id":"2005.13111","paper":"/paper/rationalizing-text-matching-learning-sparse","title":"Rationalizing Text Matching: Learning Sparse Alignments via Optimal Transport","date":"2020-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"asappresearch/rationale-alignment","path":"sinkhorn/sinkhorn.py","file_url":"https://github.com/asappresearch/rationale-alignment/blob/HEAD/sinkhorn/sinkhorn.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8df4c2374ea066b4","mcp_get_code":{"code_sha256":"8df4c2374ea066b4"}},{"arxiv_id":"2003.13479","paper":"/paper/2003-13479","title":"RPM-Net: Robust Point Matching using Learned Features","date":"2020-03-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yewzijian/RPMNet","path":"src/models/rpmnet.py","file_url":"https://github.com/yewzijian/RPMNet/blob/HEAD/src/models/rpmnet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d9502fe2fe76bf06","mcp_get_code":{"code_sha256":"d9502fe2fe76bf06"}},{"arxiv_id":"2002.08276","paper":"/paper/partial-gromov-wasserstein-with-applications","title":"Partial Optimal Transport with Applications on Positive-Unlabeled Learning","date":"2020-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rflamary/POT","path":"ot/dr.py","file_url":"https://github.com/rflamary/POT/blob/HEAD/ot/dr.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"aa603000556ebca2","mcp_get_code":{"code_sha256":"aa603000556ebca2"}},{"arxiv_id":"1912.11545","paper":"/paper/barycenters-of-natural-images-constrained","title":"Barycenters of Natural Images -- Constrained Wasserstein Barycenters for Image Morphing","date":"2019-12-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"drorsimon/image_barycenters","path":"generate_morph.py","file_url":"https://github.com/drorsimon/image_barycenters/blob/HEAD/generate_morph.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"bc40642bd9af818c","mcp_get_code":{"code_sha256":"bc40642bd9af818c"}},{"arxiv_id":"1907.12059","paper":"/paper/wasserstein-fair-classification","title":"Wasserstein Fair Classification","date":"2019-07-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"deepmind/wasserstein_fairness","path":"wasserstein_fairness/optimal_transport.py","file_url":"https://github.com/deepmind/wasserstein_fairness/blob/HEAD/wasserstein_fairness/optimal_transport.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":"b2dcbd9e94bf9ac8","mcp_get_code":{"code_sha256":"b2dcbd9e94bf9ac8"}},{"arxiv_id":"1812.00271","paper":"/paper/learning-speaker-representations-with-mutual","title":"Learning Speaker Representations with Mutual Information","date":"2018-12-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Js-Mim/rl_singing_voice","path":"nn_modules/sk_iter.py","file_url":"https://github.com/Js-Mim/rl_singing_voice/blob/HEAD/nn_modules/sk_iter.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"38c98d98a1fbbfce","mcp_get_code":{"code_sha256":"38c98d98a1fbbfce"}},{"arxiv_id":"1706.07522","paper":"/paper/deep-hashing-network-for-unsupervised-domain","title":"Deep Hashing Network for Unsupervised Domain Adaptation","date":"2017-06-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"szubing/uniood","path":"methods/uniot.py","file_url":"https://github.com/szubing/uniood/blob/HEAD/methods/uniot.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2be40bf60ede15a3","mcp_get_code":{"code_sha256":"2be40bf60ede15a3"}},{"arxiv_id":"1306.0895","paper":"/paper/sinkhorn-distances-lightspeed-computation-of-1","title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances","date":"2013-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fwilliams/fml","path":"fml/functional.py","file_url":"https://github.com/fwilliams/fml/blob/HEAD/fml/functional.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f3e2495fbb139c89","mcp_get_code":{"code_sha256":"f3e2495fbb139c89"}},{"arxiv_id":"1306.0895","paper":"/paper/sinkhorn-distances-lightspeed-computation-of-1","title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances","date":"2013-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nicolasbolle/barycenters","path":"bary.py","file_url":"https://github.com/nicolasbolle/barycenters/blob/HEAD/bary.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"18b39009324da9d4","mcp_get_code":{"code_sha256":"18b39009324da9d4"}},{"arxiv_id":"1306.0895","paper":"/paper/sinkhorn-distances-lightspeed-computation-of-1","title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances","date":"2013-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fwilliams/point-cloud-utils","path":"point_cloud_utils/_sinkhorn.py","file_url":"https://github.com/fwilliams/point-cloud-utils/blob/HEAD/point_cloud_utils/_sinkhorn.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"79cdb3d17acfd5a1","mcp_get_code":{"code_sha256":"79cdb3d17acfd5a1"}},{"arxiv_id":"Zhou_When_Pixel_Difference_Patterns_Meet_ViT_PiDiViT_for_Few-Shot_Object_ICCV_2025_paper","paper":null,"title":"arXiv:Zhou_When_Pixel_Difference_Patterns_Meet_ViT_PiDiViT_for_Few-Shot_Object_ICCV_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Seaz9/PiDiViT","path":"lib/prototype_learner.py","file_url":"https://github.com/Seaz9/PiDiViT/blob/HEAD/lib/prototype_learner.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":"f8c7f9605872c11b","mcp_get_code":{"code_sha256":"f8c7f9605872c11b"}},{"arxiv_id":"Yang_Unifying_Top-down_and_Bottom-up_Scanpath_Prediction_Using_Transformers_CVPR_2024_paper","paper":null,"title":"arXiv:Yang_Unifying_Top-down_and_Bottom-up_Scanpath_Prediction_Using_Transformers_CVPR_2024_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"cvlab-stonybrook/HAT","path":"common/losses.py","file_url":"https://github.com/cvlab-stonybrook/HAT/blob/HEAD/common/losses.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"482fcf95e53c18d3","mcp_get_code":{"code_sha256":"482fcf95e53c18d3"}}]}