{"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/layer-norm-and-dropout","entry":"layer_norm_and_dropout","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":6,"n_papers_ran":1,"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":11,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":11,"n_places_pointer_only":4,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":10},"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":"2105.11210","paper":"/paper/structurallm-structural-pre-training-for-form","title":"StructuralLM: Structural Pre-training for Form Understanding","date":"2021-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alibaba/AliceMind","path":"StructuralLM/modeling.py","file_url":"https://github.com/alibaba/AliceMind/blob/HEAD/StructuralLM/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":"58bed10d69223f15","mcp_get_code":{"code_sha256":"58bed10d69223f15"}},{"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":"15f847b95346c6d2","mcp_get_code":{"code_sha256":"15f847b95346c6d2"}},{"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":"4e61fb4457fa4a37","mcp_get_code":{"code_sha256":"4e61fb4457fa4a37"}},{"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":"appcoreopc/berty","path":"modeling.py","file_url":"https://github.com/appcoreopc/berty/blob/HEAD/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"80bc5181b671b9a1","mcp_get_code":{"code_sha256":"80bc5181b671b9a1"}},{"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":"61cb05022cc82f2b","mcp_get_code":{"code_sha256":"61cb05022cc82f2b"}},{"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":"82dc008a899111c5","mcp_get_code":{"code_sha256":"82dc008a899111c5"}},{"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":"cf1f91679b130b04","mcp_get_code":{"code_sha256":"cf1f91679b130b04"}},{"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":"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":"92ef7ef36a321f62","mcp_get_code":{"code_sha256":"92ef7ef36a321f62"}},{"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":"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":"69ead5ac4ce92603","mcp_get_code":{"code_sha256":"69ead5ac4ce92603"}},{"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":"e49e3e61dc0f7f67","mcp_get_code":{"code_sha256":"e49e3e61dc0f7f67"}},{"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":"62a741eb766dea2f","mcp_get_code":{"code_sha256":"62a741eb766dea2f"}}]}