{"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/contrastive-loss","entry":"contrastive_loss","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":80,"n_papers_ran":60,"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":54,"n_samples_ran":35,"n_samples_fingerprinted":19,"n_places":84,"n_places_pointer_only":40,"by_status":{"ran_honours":1,"ran_violates":1,"ran_draft_wrong":13,"ran_fixture":5,"ran":15,"unverified":19},"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":"2608.20382","paper":"/paper/arxiv-2608-20382","title":"Decoupled Vision-Language System for Multimodal Understanding and Generation","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"YifanXu74/Libra","path":"libra/models/clip/modeling_clip.py","file_url":"https://github.com/YifanXu74/Libra/blob/HEAD/libra/models/clip/modeling_clip.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4675779aec92d6c0","mcp_get_code":{"code_sha256":"4675779aec92d6c0"}},{"arxiv_id":"2607.24688","paper":"/paper/arxiv-2607-24688","title":"Beyond Scale and Generation: Understanding Language Model-based Entity Matching","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"Jantory/llm-trained-matcher","path":"utils/models.py","file_url":"https://github.com/Jantory/llm-trained-matcher/blob/HEAD/utils/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f5b6bd9807a07466","mcp_get_code":{"code_sha256":"f5b6bd9807a07466"}},{"arxiv_id":"2607.24683","paper":"/paper/arxiv-2607-24683","title":"Co-Learning for Missing Arbitrary Modalities in Multi-modal Classification","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"fmenat/Co4Miss","path":"comiss/models/losses.py","file_url":"https://github.com/fmenat/Co4Miss/blob/HEAD/comiss/models/losses.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"97e4ae1a2e7254bb","mcp_get_code":{"code_sha256":"97e4ae1a2e7254bb"}},{"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/clip_loss.py","file_url":"https://github.com/junyi2005/vtamo/blob/HEAD/vtamo/clip_loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"1f93c0f3bc1dd120","mcp_get_code":{"code_sha256":"1f93c0f3bc1dd120"}},{"arxiv_id":"2606.15880","paper":"/paper/arxiv-2606-15880","title":"Deep Residual Injection for Full-Spectrum Forensic Signal Perception in Multimodal Large Language Models","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"KQL11/Deep-VRM","path":"ms-swift/swift/plugin/loss.py","file_url":"https://github.com/KQL11/Deep-VRM/blob/HEAD/ms-swift/swift/plugin/loss.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":"02dbdd50bfbcb0ae","mcp_get_code":{"code_sha256":"02dbdd50bfbcb0ae"}},{"arxiv_id":"2606.13007","paper":"/paper/arxiv-2606-13007","title":"scLLM-DSC: LLM-Knowledge Enhanced Cross-Modal Deep Structural Clustering for Single-Cell RNA Sequencing","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"XPgogogo/scLLM-DSC","path":"model/model.py","file_url":"https://github.com/XPgogogo/scLLM-DSC/blob/HEAD/model/model.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":"e5fdec8e06236e4d","mcp_get_code":{"code_sha256":"e5fdec8e06236e4d"}},{"arxiv_id":"2606.10284","paper":"/paper/arxiv-2606-10284","title":"Revisiting Positive Samples in Graph Contrastive Learning: From the Perspective of Message Passing","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"tengxiao1/GraphACL","path":"hete/model.py","file_url":"https://github.com/tengxiao1/GraphACL/blob/HEAD/hete/model.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bd248e252b9ee711","mcp_get_code":{"code_sha256":"bd248e252b9ee711"}},{"arxiv_id":"2605.07177","paper":"/paper/arxiv-2605-07177","title":"HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agents","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"DeepExperience/HyperEyes","path":"SFT/ms-swift-hypereyes/swift/plugin/loss.py","file_url":"https://github.com/DeepExperience/HyperEyes/blob/HEAD/SFT/ms-swift-hypereyes/swift/plugin/loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"02dbdd50bfbcb0ae","mcp_get_code":{"code_sha256":"02dbdd50bfbcb0ae"}},{"arxiv_id":"2604.00493","paper":"/paper/arxiv-2604-00493","title":"A Reasoning-Enabled Vision-Language Foundation Model for Chest X-ray Interpretation","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"YBZh/CheXOne","path":"swift/plugin/loss.py","file_url":"https://github.com/YBZh/CheXOne/blob/HEAD/swift/plugin/loss.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":"02dbdd50bfbcb0ae","mcp_get_code":{"code_sha256":"02dbdd50bfbcb0ae"}},{"arxiv_id":"2603.20955","paper":"/paper/arxiv-2603-20955","title":"Beyond Expression Similarity: Contrastive Learning Recovers Functional Gene Associations from Protein Interaction Structure","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"EridosAI/GeneticCAL","path":"paper/strengthening_results/run_01_node_split.py","file_url":"https://github.com/EridosAI/GeneticCAL/blob/HEAD/paper/strengthening_results/run_01_node_split.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cffe9ba22ca505ad","mcp_get_code":{"code_sha256":"cffe9ba22ca505ad"}},{"arxiv_id":"2603.10237","paper":"/paper/arxiv-2603-10237","title":"One Adapter for All: Towards Unified Representation in Step-Imbalanced Class-Incremental Learning","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"xiaoyanzhang1/One-A","path":"models/onea.py","file_url":"https://github.com/xiaoyanzhang1/One-A/blob/HEAD/models/onea.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":"402c4823b108bebc","mcp_get_code":{"code_sha256":"402c4823b108bebc"}},{"arxiv_id":"2602.23663","paper":"/paper/arxiv-2602-23663","title":"Disentangled Mode-Specific Representations for Tensor Time Series via Contrastive Learning","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"KoheiObata/MoST","path":"models/losses.py","file_url":"https://github.com/KoheiObata/MoST/blob/HEAD/models/losses.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"af74d156c2e5a696","mcp_get_code":{"code_sha256":"af74d156c2e5a696"}},{"arxiv_id":"2602.19146","paper":"/paper/arxiv-2602-19146","title":"VIGiA: Instructional Video Guidance via Dialogue Reasoning and Retrieval","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"dmgcsilva/vigia","path":"inference/model.py","file_url":"https://github.com/dmgcsilva/vigia/blob/HEAD/inference/model.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":"83ada93fd84968cc","mcp_get_code":{"code_sha256":"83ada93fd84968cc"}},{"arxiv_id":"2601.21426","paper":"/paper/arxiv-2601-21426","title":"MultiModal Fine-tuning with Synthetic Captions","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"s-enmt/MMFT","path":"utils/model_utils.py","file_url":"https://github.com/s-enmt/MMFT/blob/HEAD/utils/model_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"0104870a9a95d4ea","mcp_get_code":{"code_sha256":"0104870a9a95d4ea"}},{"arxiv_id":"2601.01526","paper":"/paper/arxiv-2601-01526","title":"BARE: Towards Bias-Aware and Reasoning-Enhanced One-Tower Visual Grounding","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Marloweeee/BARE","path":"utils/loss_utils.py","file_url":"https://github.com/Marloweeee/BARE/blob/HEAD/utils/loss_utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f2e5f28608115fa6","mcp_get_code":{"code_sha256":"f2e5f28608115fa6"}},{"arxiv_id":"2510.14741","paper":"/paper/arxiv-2510-14741","title":"DEXTER: Diffusion-Guided EXplanations with TExtual Reasoning for Vision Models","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"perceivelab/dexter","path":"dexter/models/modeling_clip.py","file_url":"https://github.com/perceivelab/dexter/blob/HEAD/dexter/models/modeling_clip.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":"4675779aec92d6c0","mcp_get_code":{"code_sha256":"4675779aec92d6c0"}},{"arxiv_id":"2507.04839","paper":"/paper/ripe-reinforcement-learning-on-unlabeled","title":"RIPE: Reinforcement Learning on Unlabeled Image Pairs for Robust Keypoint Extraction","date":"2025-07-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fraunhoferhhi/RIPE","path":"ripe/losses/contrastive_loss.py","file_url":"https://github.com/fraunhoferhhi/RIPE/blob/HEAD/ripe/losses/contrastive_loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"254d77ae91c12582","mcp_get_code":{"code_sha256":"254d77ae91c12582"}},{"arxiv_id":"2506.04624","paper":"/paper/static-word-embeddings-for-sentence-semantic","title":"Static Word Embeddings for Sentence Semantic Representation","date":"2025-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"twadada/swe4semantics","path":"train_xling.py","file_url":"https://github.com/twadada/swe4semantics/blob/HEAD/train_xling.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":"bc033863eb7b03a6","mcp_get_code":{"code_sha256":"bc033863eb7b03a6"}},{"arxiv_id":"2505.21040","paper":null,"title":"arXiv:2505.21040","date":null,"month_inferred_from_arxiv_id":"2025-05","title_source":null,"repo":"cwei01/FCKT","path":"bert/sentiment_modeling.py","file_url":"https://github.com/cwei01/FCKT/blob/HEAD/bert/sentiment_modeling.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":"82af44c9519a2dbf","mcp_get_code":{"code_sha256":"82af44c9519a2dbf"}},{"arxiv_id":"2505.13778","paper":"/paper/coin-counting-the-invisible-reasoning-tokens","title":"CoIn: Counting the Invisible Reasoning Tokens in Commercial Opaque LLM APIs","date":"2025-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"case-lab-umd/llm-auditing-coin","path":"3_Block2Answer/train/loss_func.py","file_url":"https://github.com/case-lab-umd/llm-auditing-coin/blob/HEAD/3_Block2Answer/train/loss_func.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"37e51a6ba577d8d9","mcp_get_code":{"code_sha256":"37e51a6ba577d8d9"}},{"arxiv_id":"2505.05071","paper":"/paper/fg-clip-fine-grained-visual-and-textual","title":"FG-CLIP: Fine-Grained Visual and Textual Alignment","date":"2025-05-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"360CVGroup/FG-CLIP","path":"fgclip2/model/strcs/fgclip2.py","file_url":"https://github.com/360CVGroup/FG-CLIP/blob/HEAD/fgclip2/model/strcs/fgclip2.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"54554dd514ac8105","mcp_get_code":{"code_sha256":"54554dd514ac8105"}},{"arxiv_id":"2503.11367","paper":"/paper/cornstarch-distributed-multimodal-training","title":"Cornstarch: Distributed Multimodal Training Must Be Multimodality-Aware","date":null,"month_inferred_from_arxiv_id":"2025-03","title_source":"archive","repo":"cornstarch-org/Cornstarch","path":"cornstarch/models/evaclip/modeling_evaclip.py","file_url":"https://github.com/cornstarch-org/Cornstarch/blob/HEAD/cornstarch/models/evaclip/modeling_evaclip.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4675779aec92d6c0","mcp_get_code":{"code_sha256":"4675779aec92d6c0"}},{"arxiv_id":"2502.14830","paper":"/paper/middle-layer-representation-alignment-for","title":"Middle-Layer Representation Alignment for Cross-Lingual Transfer in Fine-Tuned LLMs","date":"2025-02-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dannigt/mid-align","path":"src/transformers/models/align/modeling_align.py","file_url":"https://github.com/dannigt/mid-align/blob/HEAD/src/transformers/models/align/modeling_align.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":"d1d7fb60f123d370","mcp_get_code":{"code_sha256":"d1d7fb60f123d370"}},{"arxiv_id":"2411.10019","paper":"/paper/towards-utilising-a-range-of-neural","title":"Towards Utilising a Range of Neural Activations for Comprehending Representational Associations","date":"2024-11-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lauraaisling/MID-level-activations","path":"src/dsprites/models.py","file_url":"https://github.com/lauraaisling/MID-level-activations/blob/HEAD/src/dsprites/models.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"01e8f7f7f94c0bb5","mcp_get_code":{"code_sha256":"01e8f7f7f94c0bb5"}},{"arxiv_id":"2411.00683","paper":"/paper/taxabind-a-unified-embedding-space-for","title":"TaxaBind: A Unified Embedding Space for Ecological Applications","date":"2024-11-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mvrl/taxabind","path":"TaxaBind/EnvBind/model.py","file_url":"https://github.com/mvrl/taxabind/blob/HEAD/TaxaBind/EnvBind/model.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":"b000c0bc5e72377c","mcp_get_code":{"code_sha256":"b000c0bc5e72377c"}},{"arxiv_id":"2410.22149","paper":"/paper/capacity-control-is-an-effective-memorization","title":"Capacity Control is an Effective Memorization Mitigation Mechanism in Text-Conditional Diffusion Models","date":"2024-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"raman1121/diffusion_memorization_hpo","path":"difffit/modeling_clip.py","file_url":"https://github.com/raman1121/diffusion_memorization_hpo/blob/HEAD/difffit/modeling_clip.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":"4675779aec92d6c0","mcp_get_code":{"code_sha256":"4675779aec92d6c0"}},{"arxiv_id":"2410.10659","paper":"/paper/pcf-lift-panoptic-lifting-by-probabilistic","title":"PCF-Lift: Panoptic Lifting by Probabilistic Contrastive Fusion","date":"2024-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"runsong123/pcf-lift","path":"code/model/loss/loss.py","file_url":"https://github.com/runsong123/pcf-lift/blob/HEAD/code/model/loss/loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7cfbd12778d9a0db","mcp_get_code":{"code_sha256":"7cfbd12778d9a0db"}},{"arxiv_id":"2410.07157","paper":"/paper/instructg2i-synthesizing-images-from","title":"InstructG2I: Synthesizing Images from Multimodal Attributed Graphs","date":"2024-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"4675779aec92d6c0","mcp_get_code":{"code_sha256":"4675779aec92d6c0"}},{"arxiv_id":"2410.03176","paper":"/paper/investigating-and-mitigating-object","title":"Investigating and Mitigating Object Hallucinations in Pretrained Vision-Language (CLIP) Models","date":"2024-10-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Yufang-Liu/clip_hallucination","path":"finetune_clip/modeling_clip.py","file_url":"https://github.com/Yufang-Liu/clip_hallucination/blob/HEAD/finetune_clip/modeling_clip.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":"4675779aec92d6c0","mcp_get_code":{"code_sha256":"4675779aec92d6c0"}},{"arxiv_id":"2410.00334","paper":"/paper/preserving-generalization-of-language-models","title":"Preserving Generalization of Language models in Few-shot Continual Relation Extraction","date":"2024-10-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thanhnx12/CRE-via-MMI","path":"SCKD/main-llm-mmi.py","file_url":"https://github.com/thanhnx12/CRE-via-MMI/blob/HEAD/SCKD/main-llm-mmi.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4c858d28c511c74d","mcp_get_code":{"code_sha256":"4c858d28c511c74d"}},{"arxiv_id":"2409.19961","paper":"/paper/multimodal-llm-enhanced-cross-lingual-cross","title":"Multimodal LLM Enhanced Cross-lingual Cross-modal Retrieval","date":"2024-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lijiabei-7/leccr","path":"LECCR/models/clip_vit.py","file_url":"https://github.com/lijiabei-7/leccr/blob/HEAD/LECCR/models/clip_vit.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":"4675779aec92d6c0","mcp_get_code":{"code_sha256":"4675779aec92d6c0"}},{"arxiv_id":"2409.19865","paper":"/paper/tokenbinder-text-video-retrieval-with-one-to","title":"TokenBinder: Text-Video Retrieval with One-to-Many Alignment Paradigm","date":"2024-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bingqingzhang/TokenBinder","path":"src/modeling/CLIP.py","file_url":"https://github.com/bingqingzhang/TokenBinder/blob/HEAD/src/modeling/CLIP.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":"4675779aec92d6c0","mcp_get_code":{"code_sha256":"4675779aec92d6c0"}},{"arxiv_id":"2409.15657","paper":"/paper/mmpt-multimodal-prompt-tuning-for-zero-shot","title":"M$^2$PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning","date":"2024-09-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"william-wang618/m2pt","path":"M2PT/model/llava_archPT.py","file_url":"https://github.com/william-wang618/m2pt/blob/HEAD/M2PT/model/llava_archPT.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":"35caa662e2a8cf43","mcp_get_code":{"code_sha256":"35caa662e2a8cf43"}},{"arxiv_id":"2409.05929","paper":"/paper/alt-moe-multimodal-alignment-via-alternating","title":"M3-Jepa: Multimodal Alignment via Multi-directional MoE based on the JEPA framework","date":"2024-09-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HongyangLL/M3-JEPA","path":"src/loss_function.py","file_url":"https://github.com/HongyangLL/M3-JEPA/blob/HEAD/src/loss_function.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":"00d89ba2499c5d31","mcp_get_code":{"code_sha256":"00d89ba2499c5d31"}},{"arxiv_id":"2406.13327","paper":"/paper/part-aware-unified-representation-of-language-1","title":"Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition","date":"2024-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"azzh1/PURLS","path":"model/utils/losses.py","file_url":"https://github.com/azzh1/PURLS/blob/HEAD/model/utils/losses.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"29ad04a5f041d9d1","mcp_get_code":{"code_sha256":"29ad04a5f041d9d1"}},{"arxiv_id":"2406.11384","paper":"/paper/understanding-multi-granularity-for-open","title":"Understanding Multi-Granularity for Open-Vocabulary Part Segmentation","date":"2024-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kaist-cvml-lab/part-clipseg","path":"transformers/models/clipseg/modeling_clipseg.py","file_url":"https://github.com/kaist-cvml-lab/part-clipseg/blob/HEAD/transformers/models/clipseg/modeling_clipseg.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":"4675779aec92d6c0","mcp_get_code":{"code_sha256":"4675779aec92d6c0"}},{"arxiv_id":"2406.03720","paper":"/paper/jigmark-a-black-box-approach-for-enhancing","title":"JIGMARK: A Black-Box Approach for Enhancing Image Watermarks against Diffusion Model Edits","date":"2024-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pmzzs/JigMark","path":"utils.py","file_url":"https://github.com/pmzzs/JigMark/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":"224b2a54606c71f2","mcp_get_code":{"code_sha256":"224b2a54606c71f2"}},{"arxiv_id":"2405.10140","paper":"/paper/libra-building-decoupled-vision-system-on","title":"Libra: Building Decoupled Vision System on Large Language Models","date":"2024-05-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yifanxu74/libra","path":"libra/models/clip/modeling_clip.py","file_url":"https://github.com/yifanxu74/libra/blob/HEAD/libra/models/clip/modeling_clip.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4675779aec92d6c0","mcp_get_code":{"code_sha256":"4675779aec92d6c0"}},{"arxiv_id":"2405.02951","paper":"/paper/isearle-improving-textual-inversion-for-zero","title":"iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval","date":"2024-05-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"miccunifi/searle","path":"src/utils.py","file_url":"https://github.com/miccunifi/searle/blob/HEAD/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"f96edb7ca8fe54fe","mcp_get_code":{"code_sha256":"f96edb7ca8fe54fe"}},{"arxiv_id":"2402.18695","paper":"/paper/grounding-language-models-for-visual-entity","title":"Grounding Language Models for Visual Entity Recognition","date":"2024-02-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MrZilinXiao/AutoVER","path":"LLaVA/llava/model/language_model/llava_llama.py","file_url":"https://github.com/MrZilinXiao/AutoVER/blob/HEAD/LLaVA/llava/model/language_model/llava_llama.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"83ada93fd84968cc","mcp_get_code":{"code_sha256":"83ada93fd84968cc"}},{"arxiv_id":"2402.18115","paper":"/paper/univs-unified-and-universal-video","title":"UniVS: Unified and Universal Video Segmentation with Prompts as Queries","date":"2024-02-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"minghanli/univs","path":"univs/univs_prompt_longvideo.py","file_url":"https://github.com/minghanli/univs/blob/HEAD/univs/univs_prompt_longvideo.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bb2f0ddf9840604b","mcp_get_code":{"code_sha256":"bb2f0ddf9840604b"}},{"arxiv_id":"2402.10404","paper":"/paper/explaining-generative-diffusion-models-via","title":"Explaining generative diffusion models via visual analysis for interpretable decision-making process","date":"2024-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ian-jihoonpark/X-Diffusion","path":"models/clip_encoder.py","file_url":"https://github.com/ian-jihoonpark/X-Diffusion/blob/HEAD/models/clip_encoder.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":"4675779aec92d6c0","mcp_get_code":{"code_sha256":"4675779aec92d6c0"}},{"arxiv_id":"2312.03781","paper":"/paper/lite-mind-towards-efficient-and-versatile","title":"Lite-Mind: Towards Efficient and Robust Brain Representation Network","date":"2023-12-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gongzix/lite-mind","path":"src/engine.py","file_url":"https://github.com/gongzix/lite-mind/blob/HEAD/src/engine.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":"35caa662e2a8cf43","mcp_get_code":{"code_sha256":"35caa662e2a8cf43"}},{"arxiv_id":"2312.02252","paper":"/paper/large-language-models-as-consistent-story","title":"StoryGPT-V: Large Language Models as Consistent Story Visualizers","date":"2023-12-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xiaoqian-shen/StoryGPT-V","path":"gill/losses.py","file_url":"https://github.com/xiaoqian-shen/StoryGPT-V/blob/HEAD/gill/losses.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":"83ada93fd84968cc","mcp_get_code":{"code_sha256":"83ada93fd84968cc"}},{"arxiv_id":"2312.01998","paper":"/paper/language-only-efficient-training-of-zero-shot","title":"Language-only Efficient Training of Zero-shot Composed Image Retrieval","date":"2023-12-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"navervision/lincir","path":"utils.py","file_url":"https://github.com/navervision/lincir/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":"f96edb7ca8fe54fe","mcp_get_code":{"code_sha256":"f96edb7ca8fe54fe"}},{"arxiv_id":"2311.08396","paper":"/paper/zero-shot-audio-captioning-with-audio","title":"Zero-shot audio captioning with audio-language model guidance and audio context keywords","date":"2023-11-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"explainableml/zeraucap","path":"audio_captioning/language_model/loss_func.py","file_url":"https://github.com/explainableml/zeraucap/blob/HEAD/audio_captioning/language_model/loss_func.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"dbe18b03333fa2bc","mcp_get_code":{"code_sha256":"dbe18b03333fa2bc"}},{"arxiv_id":"2311.00136","paper":"/paper/neuroformer-multimodal-and-multitask","title":"Neuroformer: Multimodal and Multitask Generative Pretraining for Brain Data","date":"2023-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"a-antoniades/neuroformer","path":"neuroformer/modules.py","file_url":"https://github.com/a-antoniades/neuroformer/blob/HEAD/neuroformer/modules.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d496ef53516a57ca","mcp_get_code":{"code_sha256":"d496ef53516a57ca"}},{"arxiv_id":"2310.18884","paper":"/paper/simple-and-asymmetric-graph-contrastive-1","title":"Simple and Asymmetric Graph Contrastive Learning without Augmentations","date":"2023-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tengxiao1/graphacl","path":"hete/model.py","file_url":"https://github.com/tengxiao1/graphacl/blob/HEAD/hete/model.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bd248e252b9ee711","mcp_get_code":{"code_sha256":"bd248e252b9ee711"}},{"arxiv_id":"2310.14017","paper":"/paper/contrast-everything-a-hierarchical","title":"Contrast Everything: A Hierarchical Contrastive Framework for Medical Time-Series","date":"2023-10-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dl4mhealth/comet","path":"comet.py","file_url":"https://github.com/dl4mhealth/comet/blob/HEAD/comet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"016be840858ae4f4","mcp_get_code":{"code_sha256":"016be840858ae4f4"}},{"arxiv_id":"2310.10362","paper":"/paper/prompt-tuning-for-multi-view-graph","title":"Self-Pro: A Self-Prompt and Tuning Framework for Graph Neural Networks","date":"2023-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gongchenghua/self-pro","path":"Self-Pro/hete/model.py","file_url":"https://github.com/gongchenghua/self-pro/blob/HEAD/Self-Pro/hete/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"68394def69dae059","mcp_get_code":{"code_sha256":"68394def69dae059"}},{"arxiv_id":"2309.16429","paper":"/paper/diverse-and-aligned-audio-to-video-generation","title":"Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation","date":"2023-09-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"guyyariv/TempoTokens","path":"modules/text_encoder/modeling_clip_tempotokens.py","file_url":"https://github.com/guyyariv/TempoTokens/blob/HEAD/modules/text_encoder/modeling_clip_tempotokens.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":"4675779aec92d6c0","mcp_get_code":{"code_sha256":"4675779aec92d6c0"}},{"arxiv_id":"2306.02583","paper":"/paper/stable-diffusion-is-unstable-1","title":"Stable Diffusion is Unstable","date":"2023-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"duchengbin8/Stable_Diffusion_is_Unstable","path":"m_clip.py","file_url":"https://github.com/duchengbin8/Stable_Diffusion_is_Unstable/blob/HEAD/m_clip.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4675779aec92d6c0","mcp_get_code":{"code_sha256":"4675779aec92d6c0"}},{"arxiv_id":"2305.13050","paper":"/paper/audiotoken-adaptation-of-text-conditioned-1","title":"AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation","date":"2023-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"guyyariv/AudioToken","path":"modules/clip_text_model/modeling_clip.py","file_url":"https://github.com/guyyariv/AudioToken/blob/HEAD/modules/clip_text_model/modeling_clip.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":"4675779aec92d6c0","mcp_get_code":{"code_sha256":"4675779aec92d6c0"}},{"arxiv_id":"2305.06620","paper":"/paper/improving-continual-relation-extraction-by","title":"Improving Continual Relation Extraction by Distinguishing Analogous Semantics","date":"2023-05-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nju-websoft/CEAR","path":"aca.py","file_url":"https://github.com/nju-websoft/CEAR/blob/HEAD/aca.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"ec1bb1ccd4ab4788","mcp_get_code":{"code_sha256":"ec1bb1ccd4ab4788"}},{"arxiv_id":"2305.02677","paper":"/paper/caption-anything-interactive-image","title":"Caption Anything: Interactive Image Description with Diverse Multimodal Controls","date":"2023-05-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ttengwang/caption-anything","path":"caption_anything/captioner/modeling_blip.py","file_url":"https://github.com/ttengwang/caption-anything/blob/HEAD/caption_anything/captioner/modeling_blip.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"4675779aec92d6c0","mcp_get_code":{"code_sha256":"4675779aec92d6c0"}},{"arxiv_id":"2301.13823","paper":"/paper/grounding-language-models-to-images-for","title":"Grounding Language Models to Images for Multimodal Inputs and Outputs","date":"2023-01-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kohjingyu/fromage","path":"fromage/losses.py","file_url":"https://github.com/kohjingyu/fromage/blob/HEAD/fromage/losses.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"83ada93fd84968cc","mcp_get_code":{"code_sha256":"83ada93fd84968cc"}},{"arxiv_id":"2210.07795","paper":"/paper/efficientvlm-fast-and-accurate-vision","title":"EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive Pruning","date":"2022-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"swaggy-tn/efficientvlm","path":"efficient_models/eff_vit.py","file_url":"https://github.com/swaggy-tn/efficientvlm/blob/HEAD/efficient_models/eff_vit.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":false,"code_sha256_prefix":"4675779aec92d6c0","mcp_get_code":{"code_sha256":"4675779aec92d6c0"}},{"arxiv_id":"2210.02724","paper":"/paper/leveraging-instance-features-for-label","title":"Leveraging Instance Features for Label Aggregation in Programmatic Weak Supervision","date":"2022-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JieyuZ2/wrench","path":"wrench/endmodel/cosine.py","file_url":"https://github.com/JieyuZ2/wrench/blob/HEAD/wrench/endmodel/cosine.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":"8c515f7346076b72","mcp_get_code":{"code_sha256":"8c515f7346076b72"}},{"arxiv_id":"2210.01115","paper":"/paper/language-aware-soft-prompting-for-vision","title":"LASP: Text-to-Text Optimization for Language-Aware Soft Prompting of Vision & Language Models","date":"2022-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"1adrianb/lasp","path":"prompting/losses.py","file_url":"https://github.com/1adrianb/lasp/blob/HEAD/prompting/losses.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"321f0835087b7e17","mcp_get_code":{"code_sha256":"321f0835087b7e17"}},{"arxiv_id":"2210.00312","paper":"/paper/multimodal-analogical-reasoning-over","title":"Multimodal Analogical Reasoning over Knowledge Graphs","date":"2022-10-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zjunlp/MKGformer","path":"MKG/models/modeling_clip.py","file_url":"https://github.com/zjunlp/MKGformer/blob/HEAD/MKG/models/modeling_clip.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":"4675779aec92d6c0","mcp_get_code":{"code_sha256":"4675779aec92d6c0"}},{"arxiv_id":"2210.00312","paper":"/paper/multimodal-analogical-reasoning-over","title":"Multimodal Analogical Reasoning over Knowledge Graphs","date":"2022-10-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zjunlp/MKG_Analogy","path":"MarT/models/modeling_clip.py","file_url":"https://github.com/zjunlp/MKG_Analogy/blob/HEAD/MarT/models/modeling_clip.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f2e5f28608115fa6","mcp_get_code":{"code_sha256":"f2e5f28608115fa6"}},{"arxiv_id":"2209.06430","paper":"/paper/clip-vip-adapting-pre-trained-image-text","title":"CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment","date":"2022-09-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/xpretrain","path":"CLIP-ViP/src/modeling/CLIP_ViP.py","file_url":"https://github.com/microsoft/xpretrain/blob/HEAD/CLIP-ViP/src/modeling/CLIP_ViP.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":"4675779aec92d6c0","mcp_get_code":{"code_sha256":"4675779aec92d6c0"}},{"arxiv_id":"2208.14565","paper":"/paper/optimizing-bi-encoder-for-named-entity","title":"Optimizing Bi-Encoder for Named Entity Recognition via Contrastive Learning","date":"2022-08-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/binder","path":"src/model.py","file_url":"https://github.com/microsoft/binder/blob/HEAD/src/model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f7b4bc846f7c354c","mcp_get_code":{"code_sha256":"f7b4bc846f7c354c"}},{"arxiv_id":"2208.14565","paper":"/paper/optimizing-bi-encoder-for-named-entity","title":"Optimizing Bi-Encoder for Named Entity Recognition via Contrastive Learning","date":"2022-08-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/binder","path":"src/model.py","file_url":"https://github.com/microsoft/binder/blob/HEAD/src/model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"73ac50d5341bf380","mcp_get_code":{"code_sha256":"73ac50d5341bf380"}},{"arxiv_id":"2206.00621","paper":"/paper/cross-view-language-modeling-towards-unified","title":"Cross-View Language Modeling: Towards Unified Cross-Lingual Cross-Modal Pre-training","date":"2022-06-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zengyan-97/cclm","path":"models/clip_vit.py","file_url":"https://github.com/zengyan-97/cclm/blob/HEAD/models/clip_vit.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":false,"code_sha256_prefix":"4675779aec92d6c0","mcp_get_code":{"code_sha256":"4675779aec92d6c0"}},{"arxiv_id":"2202.06417","paper":"/paper/a-contrastive-framework-for-neural-text","title":"A Contrastive Framework for Neural Text Generation","date":"2022-02-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yxuansu/magic","path":"image_captioning/language_model/simctg.py","file_url":"https://github.com/yxuansu/magic/blob/HEAD/image_captioning/language_model/simctg.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"369dc33768fbe11b","mcp_get_code":{"code_sha256":"369dc33768fbe11b"}},{"arxiv_id":"2108.11717","paper":"/paper/glimpse-attend-and-explore-self-attention-for","title":"Glimpse-Attend-and-Explore: Self-Attention for Active Visual Exploration","date":"2021-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"soroushseifi/glimpse-attend-explore","path":"network_functions.py","file_url":"https://github.com/soroushseifi/glimpse-attend-explore/blob/HEAD/network_functions.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"02fc85da8a06ad83","mcp_get_code":{"code_sha256":"02fc85da8a06ad83"}},{"arxiv_id":"2107.00848","paper":"/paper/systematic-evaluation-of-causal-discovery-in-1","title":"Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning","date":"2021-07-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dido1998/CausalMBRL","path":"cswm/models/losses.py","file_url":"https://github.com/dido1998/CausalMBRL/blob/HEAD/cswm/models/losses.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4d34bf6b39947167","mcp_get_code":{"code_sha256":"4d34bf6b39947167"}},{"arxiv_id":"2105.10123","paper":"/paper/backdoor-attacks-on-self-supervised-learning","title":"Backdoor Attacks on Self-Supervised Learning","date":"2021-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"UMBCvision/SSL-Backdoor","path":"byol/methods/contrastive.py","file_url":"https://github.com/UMBCvision/SSL-Backdoor/blob/HEAD/byol/methods/contrastive.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ba00312b3d5b70dc","mcp_get_code":{"code_sha256":"ba00312b3d5b70dc"}},{"arxiv_id":"2103.00020","paper":"/paper/learning-transferable-visual-models-from","title":"Learning Transferable Visual Models From Natural Language Supervision","date":"2021-02-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"filipbasara0/simple-clip","path":"simple_clip/clip.py","file_url":"https://github.com/filipbasara0/simple-clip/blob/HEAD/simple_clip/clip.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":"4ea4d130ce4030a1","mcp_get_code":{"code_sha256":"4ea4d130ce4030a1"}},{"arxiv_id":"2101.04702","paper":"/paper/cross-modal-contrastive-learning-for-text-to","title":"Cross-Modal Contrastive Learning for Text-to-Image Generation","date":"2021-01-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-research/xmcgan_image_generation","path":"xmcgan/libml/attention_lib.py","file_url":"https://github.com/google-research/xmcgan_image_generation/blob/HEAD/xmcgan/libml/attention_lib.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ba3acab33b57ea69","mcp_get_code":{"code_sha256":"ba3acab33b57ea69"}},{"arxiv_id":"2010.08895","paper":"/paper/fourier-neural-operator-for-parametric-1","title":"Fourier Neural Operator for Parametric Partial Differential Equations","date":"2020-10-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sala-group/autows-bench-101","path":"wrench/endmodel/cosine.py","file_url":"https://github.com/sala-group/autows-bench-101/blob/HEAD/wrench/endmodel/cosine.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":"8c515f7346076b72","mcp_get_code":{"code_sha256":"8c515f7346076b72"}},{"arxiv_id":"2006.08386","paper":"/paper/coala-co-aligned-autoencoders-for-learning","title":"COALA: Co-Aligned Autoencoders for Learning Semantically Enriched Audio Representations","date":"2020-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xavierfav/coala","path":"dual_ae_trainer.py","file_url":"https://github.com/xavierfav/coala/blob/HEAD/dual_ae_trainer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7567a11b33565b39","mcp_get_code":{"code_sha256":"7567a11b33565b39"}},{"arxiv_id":"2002.05709","paper":"/paper/a-simple-framework-for-contrastive-learning","title":"A Simple Framework for Contrastive Learning of Visual Representations","date":"2020-02-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mdiephuis/simclr","path":"loss.py","file_url":"https://github.com/mdiephuis/simclr/blob/HEAD/loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"eb14839e65ee11cf","mcp_get_code":{"code_sha256":"eb14839e65ee11cf"}},{"arxiv_id":"2002.05709","paper":"/paper/a-simple-framework-for-contrastive-learning","title":"A Simple Framework for Contrastive Learning of Visual Representations","date":"2020-02-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"htdt/self-supervised","path":"methods/contrastive.py","file_url":"https://github.com/htdt/self-supervised/blob/HEAD/methods/contrastive.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ba00312b3d5b70dc","mcp_get_code":{"code_sha256":"ba00312b3d5b70dc"}},{"arxiv_id":"2002.05709","paper":"/paper/a-simple-framework-for-contrastive-learning","title":"A Simple Framework for Contrastive Learning of Visual Representations","date":"2020-02-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"asd08573064/SimCLR","path":"train_SSL.py","file_url":"https://github.com/asd08573064/SimCLR/blob/HEAD/train_SSL.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"eac22c52c3120485","mcp_get_code":{"code_sha256":"eac22c52c3120485"}},{"arxiv_id":"1907.11692","paper":"/paper/roberta-a-robustly-optimized-bert-pretraining","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","date":"2019-07-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"viethoang1512/kpa","path":"qs_kpa/baselines/tf_models.py","file_url":"https://github.com/viethoang1512/kpa/blob/HEAD/qs_kpa/baselines/tf_models.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":"a5f2db749ea77f58","mcp_get_code":{"code_sha256":"a5f2db749ea77f58"}},{"arxiv_id":"1805.00833","paper":"/paper/learnable-pins-cross-modal-embeddings-for","title":"Learnable PINs: Cross-Modal Embeddings for Person Identity","date":"2018-05-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"my-yy/learnable_pins","path":"utils/pair_selection_util.py","file_url":"https://github.com/my-yy/learnable_pins/blob/HEAD/utils/pair_selection_util.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a0ad7c051c1dd85d","mcp_get_code":{"code_sha256":"a0ad7c051c1dd85d"}},{"arxiv_id":"1503.03832","paper":"/paper/facenet-a-unified-embedding-for-face","title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","date":"2015-03-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fpleoni/its_all_in_the_family","path":"source/facenet_take_2.py","file_url":"https://github.com/fpleoni/its_all_in_the_family/blob/HEAD/source/facenet_take_2.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a29f1f1ec7d76f42","mcp_get_code":{"code_sha256":"a29f1f1ec7d76f42"}},{"arxiv_id":"1406.5298","paper":"/paper/semi-supervised-learning-with-deep-generative-1","title":"Semi-Supervised Learning with Deep Generative Models","date":"2014-06-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"trungnt13/odin-ai","path":"odin/backend/losses.py","file_url":"https://github.com/trungnt13/odin-ai/blob/HEAD/odin/backend/losses.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b854e50d4482e652","mcp_get_code":{"code_sha256":"b854e50d4482e652"}},{"arxiv_id":"aaai_28565","paper":null,"title":"arXiv:aaai_28565","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"zhangxulu1996/Compositional-Inversion","path":"model/modeling_clip.py","file_url":"https://github.com/zhangxulu1996/Compositional-Inversion/blob/HEAD/model/modeling_clip.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":"4675779aec92d6c0","mcp_get_code":{"code_sha256":"4675779aec92d6c0"}},{"arxiv_id":"aaai_26259","paper":null,"title":"arXiv:aaai_26259","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"stxupengyu/LSFA","path":"contrastive.py","file_url":"https://github.com/stxupengyu/LSFA/blob/HEAD/contrastive.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0574eb3c753300ed","mcp_get_code":{"code_sha256":"0574eb3c753300ed"}},{"arxiv_id":"2024.findings-emnlp.965","paper":null,"title":"arXiv:2024.findings-emnlp.965","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Chauncey-Jheng/PCRL-MRG","path":"llama_recipes/models/PCRL_llama/modeling_PCRL_llama.py","file_url":"https://github.com/Chauncey-Jheng/PCRL-MRG/blob/HEAD/llama_recipes/models/PCRL_llama/modeling_PCRL_llama.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":"512b42a683272e0d","mcp_get_code":{"code_sha256":"512b42a683272e0d"}},{"arxiv_id":"2023.findings-emnlp.698","paper":null,"title":"arXiv:2023.findings-emnlp.698","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"tommytyc/RSVP","path":"RSVP.py","file_url":"https://github.com/tommytyc/RSVP/blob/HEAD/RSVP.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1f867ab9eb1b3ddb","mcp_get_code":{"code_sha256":"1f867ab9eb1b3ddb"}}]}