{"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/multiheadattention-3","entry":"_MultiheadAttention","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":5,"n_papers_ran":4,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":5,"n_samples_ran":4,"n_samples_fingerprinted":1,"n_places":5,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":4,"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":"2602.18473","paper":"/paper/arxiv-2602-18473","title":"Decentralized Attention Fails Centralized Signals: Rethinking Transformers for Medical Time Series","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"networkslab/MTST","path":"layers/MTST_backbone.py","file_url":"https://github.com/networkslab/MTST/blob/HEAD/layers/MTST_backbone.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e9eb773ce4f3188f","mcp_get_code":{"code_sha256":"e9eb773ce4f3188f"}},{"arxiv_id":"2602.00596","paper":"/paper/arxiv-2602-00596","title":"Kernelized Edge Attention: Addressing Semantic Attention Blurring in Temporal Graph Neural Networks","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"shenyangHuang/TGB","path":"modules/sthn.py","file_url":"https://github.com/shenyangHuang/TGB/blob/HEAD/modules/sthn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3817d890b2e0ce53","mcp_get_code":{"code_sha256":"3817d890b2e0ce53"}},{"arxiv_id":"2502.16284","paper":"/paper/molspectra-pre-training-3d-molecular","title":"MolSpectra: Pre-training 3D Molecular Representation with Multi-modal Energy Spectra","date":"2025-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"azureleon1/molspectra","path":"torchmdnet/models/Sp.py","file_url":"https://github.com/azureleon1/molspectra/blob/HEAD/torchmdnet/models/Sp.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"441db23d80d94d29","mcp_get_code":{"code_sha256":"441db23d80d94d29"}},{"arxiv_id":"2405.16877","paper":"/paper/are-self-attentions-effective-for-time-series","title":"Are Self-Attentions Effective for Time Series Forecasting?","date":"2024-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dongbeank/cats","path":"models/CATS.py","file_url":"https://github.com/dongbeank/cats/blob/HEAD/models/CATS.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"928f4380b09f0830","mcp_get_code":{"code_sha256":"928f4380b09f0830"}},{"arxiv_id":"2211.14730","paper":"/paper/a-time-series-is-worth-64-words-long-term","title":"A Time Series is Worth 64 Words: Long-term Forecasting with Transformers","date":"2022-11-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuqinie98/patchtst","path":"PatchTST_supervised/layers/PatchTST_backbone.py","file_url":"https://github.com/yuqinie98/patchtst/blob/HEAD/PatchTST_supervised/layers/PatchTST_backbone.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":"db1784f091843709","mcp_get_code":{"code_sha256":"db1784f091843709"}}]}