{"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/bertconfig","entry":"BertConfig","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":14,"n_papers_ran":11,"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":23,"n_samples_ran":18,"n_samples_fingerprinted":0,"n_places":23,"n_places_pointer_only":10,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":18,"unverified":5},"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":"2601.15771","paper":"/paper/arxiv-2601-15771","title":"Rethinking Drug-Drug Interaction Modeling as Generalizable Relation Learning","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"SZU-ADDG/GenRel-DDI","path":"model.py","file_url":"https://github.com/SZU-ADDG/GenRel-DDI/blob/HEAD/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3fd5731ffbaa0c66","mcp_get_code":{"code_sha256":"3fd5731ffbaa0c66"}},{"arxiv_id":"2305.12074","paper":"/paper/disco-distilled-student-models-co-training","title":"DisCo: Distilled Student Models Co-training for Semi-supervised Text Mining","date":"2023-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"litesslhub/disco","path":"src/model.py","file_url":"https://github.com/litesslhub/disco/blob/HEAD/src/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8a0ead5ea99529e1","mcp_get_code":{"code_sha256":"8a0ead5ea99529e1"}},{"arxiv_id":"2301.13155","paper":"/paper/advancing-radiograph-representation-learning","title":"Advancing Radiograph Representation Learning with Masked Record Modeling","date":"2023-01-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rl4m/mrm-pytorch","path":"model_mrm.py","file_url":"https://github.com/rl4m/mrm-pytorch/blob/HEAD/model_mrm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9829b3690392ef17","mcp_get_code":{"code_sha256":"9829b3690392ef17"}},{"arxiv_id":"2210.15332","paper":"/paper/dial2vec-self-guided-contrastive-learning-of","title":"Dial2vec: Self-Guided Contrastive Learning of Unsupervised Dialogue Embeddings","date":"2022-10-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AlibabaResearch/DAMO-ConvAI","path":"dial2vec/modeling_bert.py","file_url":"https://github.com/AlibabaResearch/DAMO-ConvAI/blob/HEAD/dial2vec/modeling_bert.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e64c9e8361c93aaa","mcp_get_code":{"code_sha256":"e64c9e8361c93aaa"}},{"arxiv_id":"2105.13648","paper":"/paper/cross-lingual-abstractive-summarization-with","title":"Cross-Lingual Abstractive Summarization with Limited Parallel Resources","date":"2021-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"WoodenWhite/MCLAS","path":"src/models/model_builder.py","file_url":"https://github.com/WoodenWhite/MCLAS/blob/HEAD/src/models/model_builder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3b1c36eea2104045","mcp_get_code":{"code_sha256":"3b1c36eea2104045"}},{"arxiv_id":"2105.03761","paper":"/paper/e-vil-a-dataset-and-benchmark-for-natural","title":"e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks","date":"2021-05-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"maximek3/e-ViL","path":"src/modeling.py","file_url":"https://github.com/maximek3/e-ViL/blob/HEAD/src/modeling.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0521d08772217a27","mcp_get_code":{"code_sha256":"0521d08772217a27"}},{"arxiv_id":"2104.08821","paper":"/paper/simcse-simple-contrastive-learning-of","title":"SimCSE: Simple Contrastive Learning of Sentence Embeddings","date":"2021-04-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jeongukjae/KR-BERT-SimCSE","path":"model.py","file_url":"https://github.com/jeongukjae/KR-BERT-SimCSE/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d286e6c33947de1a","mcp_get_code":{"code_sha256":"d286e6c33947de1a"}},{"arxiv_id":"2101.08106","paper":"/paper/learning-to-augment-for-data-scarce-domain","title":"Learning to Augment for Data-Scarce Domain BERT Knowledge Distillation","date":"2021-01-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"huawei-noah/Pretrained-Language-Model","path":"AutoTinyBERT/transformer/modeling_super_kd.py","file_url":"https://github.com/huawei-noah/Pretrained-Language-Model/blob/HEAD/AutoTinyBERT/transformer/modeling_super_kd.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"92bb80eba426ec5f","mcp_get_code":{"code_sha256":"92bb80eba426ec5f"}},{"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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cfcccfa363b0d97d","mcp_get_code":{"code_sha256":"cfcccfa363b0d97d"}},{"arxiv_id":"2004.13278","paper":"/paper/vd-bert-a-unified-vision-and-dialog","title":"VD-BERT: A Unified Vision and Dialog Transformer with BERT","date":"2020-04-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salesforce/VD-BERT","path":"pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/salesforce/VD-BERT/blob/HEAD/pytorch_pretrained_bert/modeling.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"270c717db63a62be","mcp_get_code":{"code_sha256":"270c717db63a62be"}},{"arxiv_id":"1908.07490","paper":"/paper/lxmert-learning-cross-modality-encoder","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","date":"2019-08-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ghazaleh-mahmoodi/lxmert_compression","path":"lxmert/src/lxrt/modeling.py","file_url":"https://github.com/ghazaleh-mahmoodi/lxmert_compression/blob/HEAD/lxmert/src/lxrt/modeling.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5324d31f8ea9ca59","mcp_get_code":{"code_sha256":"5324d31f8ea9ca59"}},{"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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f1288247bde85379","mcp_get_code":{"code_sha256":"f1288247bde85379"}},{"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":"cedrickchee/pytorch-pretrained-BERT","path":"pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/cedrickchee/pytorch-pretrained-BERT/blob/HEAD/pytorch_pretrained_bert/modeling.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":"96be08a7a7030f60","mcp_get_code":{"code_sha256":"96be08a7a7030f60"}},{"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":"derronxu/sparsebert","path":"SparseBERT/main_functions/transformer/modeling.py","file_url":"https://github.com/derronxu/sparsebert/blob/HEAD/SparseBERT/main_functions/transformer/modeling.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8a8e46e7b74bcec6","mcp_get_code":{"code_sha256":"8a8e46e7b74bcec6"}},{"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":"lonePatient/ERNIE-text-classification-pytorch","path":"pyernie/model/ernie/modeling.py","file_url":"https://github.com/lonePatient/ERNIE-text-classification-pytorch/blob/HEAD/pyernie/model/ernie/modeling.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4c8dd71a74ae58f4","mcp_get_code":{"code_sha256":"4c8dd71a74ae58f4"}},{"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":"wyf-python/Bert-Pytorch-TextClassification","path":"pytorch_pretrained/modeling.py","file_url":"https://github.com/wyf-python/Bert-Pytorch-TextClassification/blob/HEAD/pytorch_pretrained/modeling.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2f1e6f999036c38d","mcp_get_code":{"code_sha256":"2f1e6f999036c38d"}},{"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":"mkavim/finetune_bert","path":"finetune/modeling_bert.py","file_url":"https://github.com/mkavim/finetune_bert/blob/HEAD/finetune/modeling_bert.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":"aac15b5f40a6b617","mcp_get_code":{"code_sha256":"aac15b5f40a6b617"}},{"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":"EuphoriaYan/bert_component","path":"layers/bert_basic_model.py","file_url":"https://github.com/EuphoriaYan/bert_component/blob/HEAD/layers/bert_basic_model.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":"0f2b876d0df17a8b","mcp_get_code":{"code_sha256":"0f2b876d0df17a8b"}},{"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":"Impavidity/relogic","path":"relogic/logickit/inference/modeling.py","file_url":"https://github.com/Impavidity/relogic/blob/HEAD/relogic/logickit/inference/modeling.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"63b06d1b6c72a14c","mcp_get_code":{"code_sha256":"63b06d1b6c72a14c"}},{"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":"cybertronai/megatron-lm","path":"model/modeling.py","file_url":"https://github.com/cybertronai/megatron-lm/blob/HEAD/model/modeling.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"afc98bcdd9563e99","mcp_get_code":{"code_sha256":"afc98bcdd9563e99"}},{"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":"KnightZhang625/BERT_TF","path":"model_official.py","file_url":"https://github.com/KnightZhang625/BERT_TF/blob/HEAD/model_official.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":"3d815ae093b291de","mcp_get_code":{"code_sha256":"3d815ae093b291de"}},{"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":"maknotavailable/pytorch-pretrained-bert","path":"pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/maknotavailable/pytorch-pretrained-bert/blob/HEAD/pytorch_pretrained_bert/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":"740f60e01d11ace6","mcp_get_code":{"code_sha256":"740f60e01d11ace6"}},{"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":"hiun/learning-transformers","path":"modeling_bert.py","file_url":"https://github.com/hiun/learning-transformers/blob/HEAD/modeling_bert.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b50b37e6b22472ce","mcp_get_code":{"code_sha256":"b50b37e6b22472ce"}}]}