{"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/multiheadedselfattention","entry":"MultiHeadedSelfAttention","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":5,"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":7,"n_samples_ran":7,"n_samples_fingerprinted":1,"n_places":7,"n_places_pointer_only":5,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":7,"unverified":0},"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":"2405.20666","paper":"/paper/masa-motion-aware-masked-autoencoder-with","title":"MASA: Motion-aware Masked Autoencoder with Semantic Alignment for Sign Language Recognition","date":"2024-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sakura2233565548/masa","path":"moco/GCN_Transformer_mask.py","file_url":"https://github.com/sakura2233565548/masa/blob/HEAD/moco/GCN_Transformer_mask.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3a946d8e45ee55b7","mcp_get_code":{"code_sha256":"3a946d8e45ee55b7"}},{"arxiv_id":"2010.11929","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"arkel23/PyTorch-Pretrained-ViT","path":"pytorch_pretrained_vit/model.py","file_url":"https://github.com/arkel23/PyTorch-Pretrained-ViT/blob/HEAD/pytorch_pretrained_vit/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f248ced0066cd0ab","mcp_get_code":{"code_sha256":"f248ced0066cd0ab"}},{"arxiv_id":"2010.11929","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lukemelas/PyTorch-Pretrained-ViT","path":"pytorch_pretrained_vit/model.py","file_url":"https://github.com/lukemelas/PyTorch-Pretrained-ViT/blob/HEAD/pytorch_pretrained_vit/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"12cebc72988df8e2","mcp_get_code":{"code_sha256":"12cebc72988df8e2"}},{"arxiv_id":"1909.11942","paper":"/paper/albert-a-lite-bert-for-self-supervised","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","date":"2019-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"graykode/ALBERT-Pytorch","path":"models.py","file_url":"https://github.com/graykode/ALBERT-Pytorch/blob/HEAD/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8734ddba5f76437a","mcp_get_code":{"code_sha256":"8734ddba5f76437a"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dhlee347/pytorchic-bert","path":"models.py","file_url":"https://github.com/dhlee347/pytorchic-bert/blob/HEAD/models.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":"05a7a0d5018b97f8","mcp_get_code":{"code_sha256":"05a7a0d5018b97f8"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lukemelas/PyTorch-Pretrained-ViT","path":"pytorch_pretrained_vit/transformer.py","file_url":"https://github.com/lukemelas/PyTorch-Pretrained-ViT/blob/HEAD/pytorch_pretrained_vit/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a68a2e0de8f9eed1","mcp_get_code":{"code_sha256":"a68a2e0de8f9eed1"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"arkel23/PyTorch-Pretrained-ViT","path":"pytorch_pretrained_vit/transformer.py","file_url":"https://github.com/arkel23/PyTorch-Pretrained-ViT/blob/HEAD/pytorch_pretrained_vit/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"63f68b042024feb4","mcp_get_code":{"code_sha256":"63f68b042024feb4"}}]}