{"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/bertpretrainingheads","entry":"BertPreTrainingHeads","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":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":5,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"unverified":4},"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":"2107.14596","paper":"/paper/multi-stage-pre-training-over-simplified","title":"Multi-stage Pre-training over Simplified Multimodal Pre-training Models","date":"2021-07-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lttsmn/LXMERT-S","path":"Desktop/LXMERT_S/src/lxrt/modeling.py","file_url":"https://github.com/lttsmn/LXMERT-S/blob/HEAD/Desktop/LXMERT_S/src/lxrt/modeling.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b73e9276dedf22b1","mcp_get_code":{"code_sha256":"b73e9276dedf22b1"}},{"arxiv_id":"2011.05268","paper":"/paper/towards-interpretable-natural-language","title":"Towards Interpretable Natural Language Understanding with Explanations as Latent Variables","date":"2020-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JamesHujy/ELV","path":"ELV_re/s2s_ft/modeling_decoding.py","file_url":"https://github.com/JamesHujy/ELV/blob/HEAD/ELV_re/s2s_ft/modeling_decoding.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9ab2eef8291e2fb8","mcp_get_code":{"code_sha256":"9ab2eef8291e2fb8"}},{"arxiv_id":"2006.06195","paper":"/paper/large-scale-adversarial-training-for-vision","title":"Large-Scale Adversarial Training for Vision-and-Language Representation Learning","date":"2020-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhegan27/LXMERT-AdvTrain","path":"src/lxrt/modeling.py","file_url":"https://github.com/zhegan27/LXMERT-AdvTrain/blob/HEAD/src/lxrt/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"781e8b75f1ca0f7c","mcp_get_code":{"code_sha256":"781e8b75f1ca0f7c"}},{"arxiv_id":"1909.10351","paper":"/paper/190910351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","date":"2019-09-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"huawei-noah/Pretrained-Language-Model","path":"TinyBERT/transformer/modeling.py","file_url":"https://github.com/huawei-noah/Pretrained-Language-Model/blob/HEAD/TinyBERT/transformer/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f41c936d29d457a8","mcp_get_code":{"code_sha256":"f41c936d29d457a8"}},{"arxiv_id":"1908.02265","paper":"/paper/vilbert-pretraining-task-agnostic","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","date":"2019-08-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jiasenlu/vilbert_beta","path":"vilbert/vilbert.py","file_url":"https://github.com/jiasenlu/vilbert_beta/blob/HEAD/vilbert/vilbert.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2003aba9b6ab5ca4","mcp_get_code":{"code_sha256":"2003aba9b6ab5ca4"}}]}