{"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/attentionpool2d","entry":"AttentionPool2d","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":14,"n_papers_ran":13,"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":14,"n_samples_ran":13,"n_samples_fingerprinted":0,"n_places":14,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":13,"unverified":1},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2608.00147","paper":"/paper/arxiv-2608-00147","title":"RadPRISM: Schema-stratified radiology-report supervision for concept-disentangled image representations and visual grounding","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"Roypic/Benchmarkingattention","path":"models/mavl_model.py","file_url":"https://github.com/Roypic/Benchmarkingattention/blob/HEAD/models/mavl_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4cf44228614dd2bc","mcp_get_code":{"code_sha256":"4cf44228614dd2bc"}},{"arxiv_id":"2510.20162","paper":"/paper/arxiv-2510-20162","title":"TOMCAT : Test-time Comprehensive Knowledge Accumulation for Compositional Zero-Shot Learning","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"xud-yan/TOMCAT","path":"model/tomcat_bm.py","file_url":"https://github.com/xud-yan/TOMCAT/blob/HEAD/model/tomcat_bm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"da20926d9b005427","mcp_get_code":{"code_sha256":"da20926d9b005427"}},{"arxiv_id":"2510.18583","paper":"/paper/arxiv-2510-18583","title":"CovMatch: Cross-Covariance Guided Multimodal Dataset Distillation with Trainable Text Encoder","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"Yongalls/CovMatch","path":"src/model.py","file_url":"https://github.com/Yongalls/CovMatch/blob/HEAD/src/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"733f63bc89b6c510","mcp_get_code":{"code_sha256":"733f63bc89b6c510"}},{"arxiv_id":"2505.10289","paper":"/paper/msci-addressing-clip-s-inherent-limitations","title":"MSCI: Addressing CLIP's Inherent Limitations for Compositional Zero-Shot Learning","date":"2025-05-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ltpwy/MSCI","path":"MSCI/code/model/Mutifuse_new.py","file_url":"https://github.com/ltpwy/MSCI/blob/HEAD/MSCI/code/model/Mutifuse_new.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b6f745bb89c2225b","mcp_get_code":{"code_sha256":"b6f745bb89c2225b"}},{"arxiv_id":"2411.03313","paper":"/paper/classification-done-right-for-vision-language","title":"Classification Done Right for Vision-Language Pre-Training","date":"2024-11-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"x-cls/superclass","path":"opencls/open_clip/cls_model.py","file_url":"https://github.com/x-cls/superclass/blob/HEAD/opencls/open_clip/cls_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"785f7419f700fb21","mcp_get_code":{"code_sha256":"785f7419f700fb21"}},{"arxiv_id":"2403.07636","paper":"/paper/decomposing-disease-descriptions-for-enhanced","title":"Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Pre-training Framework","date":"2024-03-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HieuPhan33/MAVL","path":"Pretrain/models/model_MAVL.py","file_url":"https://github.com/HieuPhan33/MAVL/blob/HEAD/Pretrain/models/model_MAVL.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"989ccd27e10e989a","mcp_get_code":{"code_sha256":"989ccd27e10e989a"}},{"arxiv_id":"2309.12867","paper":"/paper/accurate-and-fast-compressed-video-captioning","title":"Accurate and Fast Compressed Video Captioning","date":"2023-09-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"acherstyx/CoCap","path":"cocap/modules/compressed_video/compressed_video_transformer.py","file_url":"https://github.com/acherstyx/CoCap/blob/HEAD/cocap/modules/compressed_video/compressed_video_transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7ad728e4c631a807","mcp_get_code":{"code_sha256":"7ad728e4c631a807"}},{"arxiv_id":"2306.09244","paper":"/paper/text-promptable-surgical-instrument","title":"Text Promptable Surgical Instrument Segmentation with Vision-Language Models","date":"2023-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"franciszzj/tp-sis","path":"model/segmenter.py","file_url":"https://github.com/franciszzj/tp-sis/blob/HEAD/model/segmenter.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"29bea1a18a0fa0d5","mcp_get_code":{"code_sha256":"29bea1a18a0fa0d5"}},{"arxiv_id":"2306.09200","paper":"/paper/chessgpt-bridging-policy-learning-and-1","title":"ChessGPT: Bridging Policy Learning and Language Modeling","date":"2023-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"waterhorse1/chessgpt","path":"chessclip/src/open_clip/model.py","file_url":"https://github.com/waterhorse1/chessgpt/blob/HEAD/chessclip/src/open_clip/model.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":"6fdc88f3b630d199","mcp_get_code":{"code_sha256":"6fdc88f3b630d199"}},{"arxiv_id":"2305.13500","paper":"/paper/learning-emotion-representations-from-verbal-1","title":"Learning Emotion Representations from Verbal and Nonverbal Communication","date":"2023-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Xeaver/EmotionCLIP","path":"src/models/base.py","file_url":"https://github.com/Xeaver/EmotionCLIP/blob/HEAD/src/models/base.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c31ea380cbe12461","mcp_get_code":{"code_sha256":"c31ea380cbe12461"}},{"arxiv_id":"2304.02012","paper":"/paper/egc-image-generation-and-classification-via-a","title":"EGC: Image Generation and Classification via a Diffusion Energy-Based Model","date":"2023-04-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"GuoQiushan/EGC","path":"guided_diffusion/unet.py","file_url":"https://github.com/GuoQiushan/EGC/blob/HEAD/guided_diffusion/unet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5eab1eccceac91bf","mcp_get_code":{"code_sha256":"5eab1eccceac91bf"}},{"arxiv_id":"2303.14369","paper":"/paper/video-text-as-game-players-hierarchical","title":"Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning","date":"2023-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jpthu17/dicosa","path":"tvr/models/modeling.py","file_url":"https://github.com/jpthu17/dicosa/blob/HEAD/tvr/models/modeling.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":"9dbc40efee885693","mcp_get_code":{"code_sha256":"9dbc40efee885693"}},{"arxiv_id":"2303.12501","paper":"/paper/cross-modal-implicit-relation-reasoning-and","title":"Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval","date":"2023-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"anosorae/irra","path":"model/build.py","file_url":"https://github.com/anosorae/irra/blob/HEAD/model/build.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"03b49fee1c4ea883","mcp_get_code":{"code_sha256":"03b49fee1c4ea883"}},{"arxiv_id":"2025.findings-emnlp.28","paper":null,"title":"arXiv:2025.findings-emnlp.28","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"BUAAPY/ProPy","path":"modules/clip_propy.py","file_url":"https://github.com/BUAAPY/ProPy/blob/HEAD/modules/clip_propy.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1371958d4e89f57a","mcp_get_code":{"code_sha256":"1371958d4e89f57a"}}]}