{"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/attention-layer","entry":"attention_layer","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":9,"n_papers_ran":2,"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":22,"n_samples_ran":2,"n_samples_fingerprinted":0,"n_places":22,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":2,"unverified":20},"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":"2210.16646","paper":"/paper/breaking-the-symmetry-resolving-symmetry","title":"Breaking the Symmetry: Resolving Symmetry Ambiguities in Equivariant Neural Networks","date":"2022-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sidhikabalachandar/oavnn","path":"model.py","file_url":"https://github.com/sidhikabalachandar/oavnn/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1d0922219a132b52","mcp_get_code":{"code_sha256":"1d0922219a132b52"}},{"arxiv_id":"2009.07258","paper":"/paper/bert-qe-contextualized-query-expansion-for","title":"BERT-QE: Contextualized Query Expansion for Document Re-ranking","date":"2020-09-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zh-zheng/BERT-QE","path":"functions.py","file_url":"https://github.com/zh-zheng/BERT-QE/blob/HEAD/functions.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":"19d5694b63733ac3","mcp_get_code":{"code_sha256":"19d5694b63733ac3"}},{"arxiv_id":"2004.11579","paper":"/paper/probabilistically-masked-language-model","title":"Probabilistically Masked Language Model Capable of Autoregressive Generation in Arbitrary Word Order","date":"2020-04-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"huawei-noah/Pretrained-Language-Model","path":"PMLM/interactive_conditional_samples_sincos_acrostic.py","file_url":"https://github.com/huawei-noah/Pretrained-Language-Model/blob/HEAD/PMLM/interactive_conditional_samples_sincos_acrostic.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3e9d8117d432e11f","mcp_get_code":{"code_sha256":"3e9d8117d432e11f"}},{"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":"brightmart/albert_zh","path":"modeling_google.py","file_url":"https://github.com/brightmart/albert_zh/blob/HEAD/modeling_google.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"154407ccae03925e","mcp_get_code":{"code_sha256":"154407ccae03925e"}},{"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":"TeamLab/bert-gcn-for-paper-citation","path":"modeling.py","file_url":"https://github.com/TeamLab/bert-gcn-for-paper-citation/blob/HEAD/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"62ba879682ced155","mcp_get_code":{"code_sha256":"62ba879682ced155"}},{"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":"DeligientSloth/bert-tensorflow","path":"modeling.py","file_url":"https://github.com/DeligientSloth/bert-tensorflow/blob/HEAD/modeling.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":"d16dcfaecf4647ad","mcp_get_code":{"code_sha256":"d16dcfaecf4647ad"}},{"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":"Satan012/BERT","path":"modeling.py","file_url":"https://github.com/Satan012/BERT/blob/HEAD/modeling.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":"f648a4567745fd52","mcp_get_code":{"code_sha256":"f648a4567745fd52"}},{"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":"h4ste/oscar","path":"modeling.py","file_url":"https://github.com/h4ste/oscar/blob/HEAD/modeling.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":"e2b4886c5ce3dcec","mcp_get_code":{"code_sha256":"e2b4886c5ce3dcec"}},{"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":"guoyaohua/BERT-Classifier","path":"modeling.py","file_url":"https://github.com/guoyaohua/BERT-Classifier/blob/HEAD/modeling.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":"3962b885663c0edd","mcp_get_code":{"code_sha256":"3962b885663c0edd"}},{"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":"pengshuyuan/Bert","path":"modeling.py","file_url":"https://github.com/pengshuyuan/Bert/blob/HEAD/modeling.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":"c18bd0ef8d750675","mcp_get_code":{"code_sha256":"c18bd0ef8d750675"}},{"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":"zsweet/BERT_zsw","path":"modeling.py","file_url":"https://github.com/zsweet/BERT_zsw/blob/HEAD/modeling.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":"74d797f5a80810b0","mcp_get_code":{"code_sha256":"74d797f5a80810b0"}},{"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":"deepmipt/bert","path":"bert_dp/modeling.py","file_url":"https://github.com/deepmipt/bert/blob/HEAD/bert_dp/modeling.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":"0003cab2e9992161","mcp_get_code":{"code_sha256":"0003cab2e9992161"}},{"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":"haidershaour/bert","path":"modeling.py","file_url":"https://github.com/haidershaour/bert/blob/HEAD/modeling.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":"6e650585e8d0a755","mcp_get_code":{"code_sha256":"6e650585e8d0a755"}},{"arxiv_id":"1710.10903","paper":"/paper/graph-attention-networks","title":"Graph Attention Networks","date":"2017-10-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liu6zijian/simplified-gcn-model","path":"gat.py","file_url":"https://github.com/liu6zijian/simplified-gcn-model/blob/HEAD/gat.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6ece140d37c4f3d6","mcp_get_code":{"code_sha256":"6ece140d37c4f3d6"}},{"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":"yydai/bert_test","path":"modeling.py","file_url":"https://github.com/yydai/bert_test/blob/HEAD/modeling.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":"0bae2227c100acf4","mcp_get_code":{"code_sha256":"0bae2227c100acf4"}},{"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":"SCismycat/bert_code_view","path":"modeling.py","file_url":"https://github.com/SCismycat/bert_code_view/blob/HEAD/modeling.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":"a633080fd26110de","mcp_get_code":{"code_sha256":"a633080fd26110de"}},{"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":"semal/bert","path":"bert/core/modeling.py","file_url":"https://github.com/semal/bert/blob/HEAD/bert/core/modeling.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":"d1db9d5c54d70ef9","mcp_get_code":{"code_sha256":"d1db9d5c54d70ef9"}},{"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":"MichaelZhouwang/LMlexsub","path":"modeling.py","file_url":"https://github.com/MichaelZhouwang/LMlexsub/blob/HEAD/modeling.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":"186bace8787aeea4","mcp_get_code":{"code_sha256":"186bace8787aeea4"}},{"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":"ricardordb/bert","path":"modeling.py","file_url":"https://github.com/ricardordb/bert/blob/HEAD/modeling.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":"0a96d33613063c14","mcp_get_code":{"code_sha256":"0a96d33613063c14"}},{"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":"appcoreopc/berty","path":"modeling.py","file_url":"https://github.com/appcoreopc/berty/blob/HEAD/modeling.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":"3a42641307ce9cfa","mcp_get_code":{"code_sha256":"3a42641307ce9cfa"}},{"arxiv_id":"2023.acl-long.693","paper":null,"title":"arXiv:2023.acl-long.693","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"AI4Bharat/IndicBERT","path":"train/modeling.py","file_url":"https://github.com/AI4Bharat/IndicBERT/blob/HEAD/train/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6e2f8a86932a499b","mcp_get_code":{"code_sha256":"6e2f8a86932a499b"}},{"arxiv_id":"2021.acl-long.233","paper":null,"title":"arXiv:2021.acl-long.233","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"ACL2020SpellGCN/SpellGCN","path":"modeling.py","file_url":"https://github.com/ACL2020SpellGCN/SpellGCN/blob/HEAD/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"333a4e02334f1f77","mcp_get_code":{"code_sha256":"333a4e02334f1f77"}}]}