{"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/bertattention","entry":"BertAttention","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":28,"n_papers_ran":9,"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":38,"n_samples_ran":11,"n_samples_fingerprinted":7,"n_places":38,"n_places_pointer_only":17,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":11,"unverified":27},"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":"2603.05969","paper":"/paper/arxiv-2603-05969","title":"Imagine How To Change: Explicit Procedure Modeling for Change Captioning","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"BlueberryOreo/ProCap","path":"src/rtransformer/model.py","file_url":"https://github.com/BlueberryOreo/ProCap/blob/HEAD/src/rtransformer/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3617108a2e6ec403","mcp_get_code":{"code_sha256":"3617108a2e6ec403"}},{"arxiv_id":"2511.21416","paper":"/paper/arxiv-2511-21416","title":"Odin: Oriented Dual-module Integration for Text-rich Network Representation Learning","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":"hongkaifeng/Odin","path":"src/OpenLP/models/Graphformer ME.py","file_url":"https://github.com/hongkaifeng/Odin/blob/HEAD/src/OpenLP/models/Graphformer%20ME.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"15dfdc5559b52462","mcp_get_code":{"code_sha256":"15dfdc5559b52462"}},{"arxiv_id":"2505.19525","paper":"/paper/rethinking-gating-mechanism-in-sparse-moe","title":"Rethinking Gating Mechanism in Sparse MoE: Handling Arbitrary Modality Inputs with Confidence-Guided Gate","date":"2025-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zehuiwu/MMML","path":"utils/cross_attn_encoder.py","file_url":"https://github.com/zehuiwu/MMML/blob/HEAD/utils/cross_attn_encoder.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8bd97889b987d97e","mcp_get_code":{"code_sha256":"8bd97889b987d97e"}},{"arxiv_id":"2501.17403","paper":"/paper/general-scene-adaptation-for-vision-and","title":"General Scene Adaptation for Vision-and-Language Navigation","date":"2025-01-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"honghd16/gsa-vln","path":"GR-DUET/map_nav_src/models/vilmodel.py","file_url":"https://github.com/honghd16/gsa-vln/blob/HEAD/GR-DUET/map_nav_src/models/vilmodel.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c35512e4d250fe83","mcp_get_code":{"code_sha256":"c35512e4d250fe83"}},{"arxiv_id":"2405.00390","paper":"/paper/cofipara-a-coarse-to-fine-paradigm-for","title":"CofiPara: A Coarse-to-fine Paradigm for Multimodal Sarcasm Target Identification with Large Multimodal Models","date":"2024-05-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wjq-learning/MSTI","path":"model.py","file_url":"https://github.com/wjq-learning/MSTI/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7302832cca671b08","mcp_get_code":{"code_sha256":"7302832cca671b08"}},{"arxiv_id":"2402.13040","paper":"/paper/text-guided-molecule-generation-with","title":"Text-Guided Molecule Generation with Diffusion Language Model","date":"2024-02-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Deno-V/tgm-dlm","path":"improved-diffusion/improved_diffusion/transformer_model.py","file_url":"https://github.com/Deno-V/tgm-dlm/blob/HEAD/improved-diffusion/improved_diffusion/transformer_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"95d638062692e25c","mcp_get_code":{"code_sha256":"95d638062692e25c"}},{"arxiv_id":"2308.12587","paper":"/paper/grounded-entity-landmark-adaptive-pre","title":"Grounded Entity-Landmark Adaptive Pre-training for Vision-and-Language Navigation","date":"2023-08-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"csir1996/vln-gela","path":"ada_pretrain_src/model/pretrain_cmt.py","file_url":"https://github.com/csir1996/vln-gela/blob/HEAD/ada_pretrain_src/model/pretrain_cmt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f11fe3d331f06585","mcp_get_code":{"code_sha256":"f11fe3d331f06585"}},{"arxiv_id":"2305.12268","paper":"/paper/patton-language-model-pretraining-on-text","title":"Patton: Language Model Pretraining on Text-Rich Networks","date":"2023-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PeterGriffinJin/Patton","path":"src/OpenLP/models/Graphformer.py","file_url":"https://github.com/PeterGriffinJin/Patton/blob/HEAD/src/OpenLP/models/Graphformer.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":"34e08dc60e1055a0","mcp_get_code":{"code_sha256":"34e08dc60e1055a0"}},{"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":"46e5a377bdd96a41","mcp_get_code":{"code_sha256":"46e5a377bdd96a41"}},{"arxiv_id":"2305.03602","paper":"/paper/a-dual-semantic-aware-recurrent-global","title":"A Dual Semantic-Aware Recurrent Global-Adaptive Network For Vision-and-Language Navigation","date":"2023-05-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CrystalSixone/DSRG","path":"finetune_src/models/vilmodel.py","file_url":"https://github.com/CrystalSixone/DSRG/blob/HEAD/finetune_src/models/vilmodel.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b38b941722e63d29","mcp_get_code":{"code_sha256":"b38b941722e63d29"}},{"arxiv_id":"2304.08682","paper":"/paper/learning-situation-hyper-graphs-for-video","title":"Learning Situation Hyper-Graphs for Video Question Answering","date":"2023-04-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aurooj/SHG-VQA","path":"AGQA/src/lxrt/modeling_capsbert.py","file_url":"https://github.com/aurooj/SHG-VQA/blob/HEAD/AGQA/src/lxrt/modeling_capsbert.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5294ad4cfb6fd592","mcp_get_code":{"code_sha256":"5294ad4cfb6fd592"}},{"arxiv_id":"2303.15796","paper":"/paper/kerm-knowledge-enhanced-reasoning-for-vision","title":"KERM: Knowledge Enhanced Reasoning for Vision-and-Language Navigation","date":"2023-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"XiangyangLi20/KERM","path":"knowledge_nav_src/models/vilmodel.py","file_url":"https://github.com/XiangyangLi20/KERM/blob/HEAD/knowledge_nav_src/models/vilmodel.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fac097958060a4ef","mcp_get_code":{"code_sha256":"fac097958060a4ef"}},{"arxiv_id":"2303.08409","paper":"/paper/lana-a-language-capable-navigator-for","title":"Lana: A Language-Capable Navigator for Instruction Following and Generation","date":"2023-03-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wxh1996/lana-vln","path":"finetune_src/models/vilmodel_cmt_lana.py","file_url":"https://github.com/wxh1996/lana-vln/blob/HEAD/finetune_src/models/vilmodel_cmt_lana.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"972bc2726cd67bc8","mcp_get_code":{"code_sha256":"972bc2726cd67bc8"}},{"arxiv_id":"2210.08714","paper":"/paper/selective-query-guided-debiasing-network-for","title":"Selective Query-guided Debiasing for Video Corpus Moment Retrieval","date":"2022-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dbstjswo505/SQuiDNet","path":"model/squidnet.py","file_url":"https://github.com/dbstjswo505/SQuiDNet/blob/HEAD/model/squidnet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"28e6bf1ccec147fb","mcp_get_code":{"code_sha256":"28e6bf1ccec147fb"}},{"arxiv_id":"2210.08465","paper":"/paper/character-centric-story-visualization-via","title":"Character-Centric Story Visualization via Visual Planning and Token Alignment","date":"2022-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"adymaharana/VLCStoryGan","path":"vlcgan/model.py","file_url":"https://github.com/adymaharana/VLCStoryGan/blob/HEAD/vlcgan/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7758e2dc60da7479","mcp_get_code":{"code_sha256":"7758e2dc60da7479"}},{"arxiv_id":"2205.00274","paper":"/paper/clues-before-answers-generation-enhanced","title":"Clues Before Answers: Generation-Enhanced Multiple-Choice QA","date":"2022-04-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nju-websoft/GenMC","path":"model/modeling_genmc.py","file_url":"https://github.com/nju-websoft/GenMC/blob/HEAD/model/modeling_genmc.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":"7ccd797d6076b7bf","mcp_get_code":{"code_sha256":"7ccd797d6076b7bf"}},{"arxiv_id":"2203.15125","paper":"/paper/text2pos-text-to-point-cloud-cross-modal","title":"Text2Pos: Text-to-Point-Cloud Cross-Modal Localization","date":"2022-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kevin301342/cmmloc","path":"models/coarse/cell_retrieval.py","file_url":"https://github.com/kevin301342/cmmloc/blob/HEAD/models/coarse/cell_retrieval.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"565f1b7b15ab3e88","mcp_get_code":{"code_sha256":"565f1b7b15ab3e88"}},{"arxiv_id":"2203.14040","paper":"/paper/visual-abductive-reasoning","title":"Visual Abductive Reasoning","date":"2022-03-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leonnnop/var","path":"src/model/mainmodel.py","file_url":"https://github.com/leonnnop/var/blob/HEAD/src/model/mainmodel.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8a110cded88738a8","mcp_get_code":{"code_sha256":"8a110cded88738a8"}},{"arxiv_id":"2110.13309","paper":"/paper/history-aware-multimodal-transformer-for","title":"History Aware Multimodal Transformer for Vision-and-Language Navigation","date":"2021-10-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cshizhe/vln-hamt","path":"finetune_src/models/vilmodel_cmt.py","file_url":"https://github.com/cshizhe/vln-hamt/blob/HEAD/finetune_src/models/vilmodel_cmt.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"13836f9b26886d79","mcp_get_code":{"code_sha256":"13836f9b26886d79"}},{"arxiv_id":"2108.00061","paper":"/paper/mtvr-multilingual-moment-retrieval-in-videos","title":"MTVR: Multilingual Moment Retrieval in Videos","date":"2021-07-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jayleicn/mTVRetrieval","path":"baselines/mxml/model_xml_shared.py","file_url":"https://github.com/jayleicn/mTVRetrieval/blob/HEAD/baselines/mxml/model_xml_shared.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d7fb7167ff474aeb","mcp_get_code":{"code_sha256":"d7fb7167ff474aeb"}},{"arxiv_id":"2106.14019","paper":"/paper/umic-an-unreferenced-metric-for-image","title":"UMIC: An Unreferenced Metric for Image Captioning via Contrastive Learning","date":"2021-06-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hwanheelee1993/UMIC","path":"model/ce.py","file_url":"https://github.com/hwanheelee1993/UMIC/blob/HEAD/model/ce.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"eb099be49425d23f","mcp_get_code":{"code_sha256":"eb099be49425d23f"}},{"arxiv_id":"2103.03493","paper":"/paper/causal-attention-for-vision-language-tasks","title":"Causal Attention for Vision-Language Tasks","date":"2021-03-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yangxuntu/lxmertcatt","path":"src/lxrt/modeling.py","file_url":"https://github.com/yangxuntu/lxmertcatt/blob/HEAD/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":"b8c495ff176f844a","mcp_get_code":{"code_sha256":"b8c495ff176f844a"}},{"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":"79fb582753417716","mcp_get_code":{"code_sha256":"79fb582753417716"}},{"arxiv_id":"2010.08210","paper":"/paper/coarse-to-fine-pre-training-for-named-entity","title":"Coarse-to-Fine Pre-training for Named Entity Recognition","date":"2020-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"strawberryx/CoFEE","path":"model/bert_mrc_ner_cluster.py","file_url":"https://github.com/strawberryx/CoFEE/blob/HEAD/model/bert_mrc_ner_cluster.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bfa8da12483938a3","mcp_get_code":{"code_sha256":"bfa8da12483938a3"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a37aa2973e8e5c9f","mcp_get_code":{"code_sha256":"a37aa2973e8e5c9f"}},{"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":"04726b79ddfafc13","mcp_get_code":{"code_sha256":"04726b79ddfafc13"}},{"arxiv_id":"1907.11692","paper":"/paper/roberta-a-robustly-optimized-bert-pretraining","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","date":"2019-07-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"GeorgeLuImmortal/Hierarchical-BERT-Model-with-Limited-Labelled-Data","path":"run_hbm.py","file_url":"https://github.com/GeorgeLuImmortal/Hierarchical-BERT-Model-with-Limited-Labelled-Data/blob/HEAD/run_hbm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ad7f6e57dedf08aa","mcp_get_code":{"code_sha256":"ad7f6e57dedf08aa"}},{"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":"itsShnik/adaptively-finetuning-transformers","path":"lxmert/src/lxrt/modeling.py","file_url":"https://github.com/itsShnik/adaptively-finetuning-transformers/blob/HEAD/lxmert/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":"4d9cbea89cdaecc9","mcp_get_code":{"code_sha256":"4d9cbea89cdaecc9"}},{"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":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"e84e69f096395645","mcp_get_code":{"code_sha256":"e84e69f096395645"}},{"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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"149f493786f28d23","mcp_get_code":{"code_sha256":"149f493786f28d23"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"330e30e5ccfcc515","mcp_get_code":{"code_sha256":"330e30e5ccfcc515"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5416853a8be3a2d7","mcp_get_code":{"code_sha256":"5416853a8be3a2d7"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"978bca45efc60c53","mcp_get_code":{"code_sha256":"978bca45efc60c53"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f5bafea439ee7a6d","mcp_get_code":{"code_sha256":"f5bafea439ee7a6d"}},{"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":"ganeshjawahar/interpret_bert","path":"tpdn/unsuptree_modeler.py","file_url":"https://github.com/ganeshjawahar/interpret_bert/blob/HEAD/tpdn/unsuptree_modeler.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"236bedbe3bb10ca4","mcp_get_code":{"code_sha256":"236bedbe3bb10ca4"}},{"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":"yifding/hetseq","path":"hetseq/bert_modeling.py","file_url":"https://github.com/yifding/hetseq/blob/HEAD/hetseq/bert_modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0cb54ae12a698d67","mcp_get_code":{"code_sha256":"0cb54ae12a698d67"}},{"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":"han-shi/SparseBERT","path":"modeling.py","file_url":"https://github.com/han-shi/SparseBERT/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":"e12264c69d5f6ed1","mcp_get_code":{"code_sha256":"e12264c69d5f6ed1"}},{"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":"charles9n/bert-sklearn","path":"bert_sklearn/model/pytorch_pretrained/modeling.py","file_url":"https://github.com/charles9n/bert-sklearn/blob/HEAD/bert_sklearn/model/pytorch_pretrained/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":"b05a22e3a42e7e59","mcp_get_code":{"code_sha256":"b05a22e3a42e7e59"}}]}