{"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/prune-linear-layer","entry":"prune_linear_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":40,"n_papers_ran":32,"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":15,"n_samples_ran":8,"n_samples_fingerprinted":0,"n_places":41,"n_places_pointer_only":11,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":6,"ran_fixture":0,"ran":2,"unverified":7},"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":"2411.00311","paper":"/paper/c2a-client-customized-adaptation-for","title":"C2A: Client-Customized Adaptation for Parameter-Efficient Federated Learning","date":"2024-11-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yeachan-kr/c2a","path":"transformer_utils.py","file_url":"https://github.com/yeachan-kr/c2a/blob/HEAD/transformer_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d12f44df51b174b1","mcp_get_code":{"code_sha256":"d12f44df51b174b1"}},{"arxiv_id":"2406.03792","paper":"/paper/light-peft-lightening-parameter-efficient","title":"Light-PEFT: Lightening Parameter-Efficient Fine-Tuning via Early Pruning","date":"2024-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gccnlp/light-peft","path":"peft/src/peft/tuners/lora.py","file_url":"https://github.com/gccnlp/light-peft/blob/HEAD/peft/src/peft/tuners/lora.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9d6a7aa341c6be64","mcp_get_code":{"code_sha256":"9d6a7aa341c6be64"}},{"arxiv_id":"2405.10974","paper":"/paper/bottleneck-minimal-indexing-for-generative","title":"Bottleneck-Minimal Indexing for Generative Document Retrieval","date":"2024-05-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kduxin/Bottleneck-Minimal-Indexing","path":"NCIRetriever/nci_transformers/modeling_utils.py","file_url":"https://github.com/kduxin/Bottleneck-Minimal-Indexing/blob/HEAD/NCIRetriever/nci_transformers/modeling_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b3504e72ce1153fe","mcp_get_code":{"code_sha256":"b3504e72ce1153fe"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"63bf3ad9c297ab92","mcp_get_code":{"code_sha256":"63bf3ad9c297ab92"}},{"arxiv_id":"2312.12470","paper":"/paper/rotated-multi-scale-interaction-network-for","title":"Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image Segmentation","date":"2023-12-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lsan2401/rmsin","path":"bert/modeling_utils.py","file_url":"https://github.com/lsan2401/rmsin/blob/HEAD/bert/modeling_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a37615738b3ddcd3","mcp_get_code":{"code_sha256":"a37615738b3ddcd3"}},{"arxiv_id":"2312.12198","paper":"/paper/mask-grounding-for-referring-image","title":"Mask Grounding for Referring Image Segmentation","date":"2023-12-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yxchng/mask-grounding","path":"bert/modeling_utils.py","file_url":"https://github.com/yxchng/mask-grounding/blob/HEAD/bert/modeling_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"code_sha256_prefix":"a37615738b3ddcd3","mcp_get_code":{"code_sha256":"a37615738b3ddcd3"}},{"arxiv_id":"2309.01017","paper":"/paper/contrastive-grouping-with-transformer-for-1","title":"Contrastive Grouping with Transformer for Referring Image Segmentation","date":"2023-09-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"toneyaya/cgformer","path":"bert/modeling_utils.py","file_url":"https://github.com/toneyaya/cgformer/blob/HEAD/bert/modeling_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a37615738b3ddcd3","mcp_get_code":{"code_sha256":"a37615738b3ddcd3"}},{"arxiv_id":"2308.13853","paper":"/paper/beyond-one-to-one-rethinking-the-referring","title":"Beyond One-to-One: Rethinking the Referring Image Segmentation","date":"2023-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"toggle1995/RIS-DMMI","path":"bert/modeling_utils.py","file_url":"https://github.com/toggle1995/RIS-DMMI/blob/HEAD/bert/modeling_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a37615738b3ddcd3","mcp_get_code":{"code_sha256":"a37615738b3ddcd3"}},{"arxiv_id":"2305.14007","paper":"/paper/when-does-aggregating-multiple-skills-with","title":"When Does Aggregating Multiple Skills with Multi-Task Learning Work? A Case Study in Financial NLP","date":"2023-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"EdisonNi-hku/MTL4Finance","path":"code/models/modeling_task_embeddings.py","file_url":"https://github.com/EdisonNi-hku/MTL4Finance/blob/HEAD/code/models/modeling_task_embeddings.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d30d6c3098df2c42","mcp_get_code":{"code_sha256":"d30d6c3098df2c42"}},{"arxiv_id":"2210.09545","paper":"/paper/fine-mixing-mitigating-backdoors-in-fine","title":"Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models","date":"2022-10-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"huggingface/pytorch-transformers","path":"src/transformers/pytorch_utils.py","file_url":"https://github.com/huggingface/pytorch-transformers/blob/HEAD/src/transformers/pytorch_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"24ece331635f4b38","mcp_get_code":{"code_sha256":"24ece331635f4b38"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"409d011257a2b23b","mcp_get_code":{"code_sha256":"409d011257a2b23b"}},{"arxiv_id":"2203.11591","paper":"/paper/hop-history-and-order-aware-pre-training-for","title":"HOP: History-and-Order Aware Pre-training for Vision-and-Language Navigation","date":"2022-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yanyuanqiao/hop-vln","path":"tasks/pretrain/modeling_utils.py","file_url":"https://github.com/yanyuanqiao/hop-vln/blob/HEAD/tasks/pretrain/modeling_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d30d6c3098df2c42","mcp_get_code":{"code_sha256":"d30d6c3098df2c42"}},{"arxiv_id":"2110.12567","paper":"/paper/alignment-attention-by-matching-key-and-query","title":"Alignment Attention by Matching Key and Query Distributions","date":"2021-10-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"szhang42/alignment_attention","path":"src/transformers/modeling_albert.py","file_url":"https://github.com/szhang42/alignment_attention/blob/HEAD/src/transformers/modeling_albert.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9d6a7aa341c6be64","mcp_get_code":{"code_sha256":"9d6a7aa341c6be64"}},{"arxiv_id":"2110.00855","paper":"/paper/survtrace-transformers-for-survival-analysis","title":"SurvTRACE: Transformers for Survival Analysis with Competing Events","date":"2021-10-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RyanWangZf/SurvTRACE","path":"survtrace/modeling_bert.py","file_url":"https://github.com/RyanWangZf/SurvTRACE/blob/HEAD/survtrace/modeling_bert.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5366c196cf596807","mcp_get_code":{"code_sha256":"5366c196cf596807"}},{"arxiv_id":"2108.10904","paper":"/paper/simvlm-simple-visual-language-model","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","date":"2021-08-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"FerryHuang/SimVLM","path":"simvlm/modeling_simvlm.py","file_url":"https://github.com/FerryHuang/SimVLM/blob/HEAD/simvlm/modeling_simvlm.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"52de2aaa15da0643","mcp_get_code":{"code_sha256":"52de2aaa15da0643"}},{"arxiv_id":"2106.11310","paper":"/paper/towards-long-form-video-understanding-1","title":"Towards Long-Form Video Understanding","date":"2021-06-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chaoyuaw/lvu","path":"src/models/modeling_utils.py","file_url":"https://github.com/chaoyuaw/lvu/blob/HEAD/src/models/modeling_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d30d6c3098df2c42","mcp_get_code":{"code_sha256":"d30d6c3098df2c42"}},{"arxiv_id":"2106.08087","paper":"/paper/cblue-a-chinese-biomedical-language","title":"CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark","date":"2021-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cbluebenchmark/cblue","path":"cblue/models/zen/modeling.py","file_url":"https://github.com/cbluebenchmark/cblue/blob/HEAD/cblue/models/zen/modeling.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d30d6c3098df2c42","mcp_get_code":{"code_sha256":"d30d6c3098df2c42"}},{"arxiv_id":"2104.04039","paper":"/paper/plug-and-blend-a-framework-for-controllable","title":"Plug-and-Blend: A Framework for Controllable Story Generation with Blended Control Codes","date":"2021-03-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xxbidiao/plug-and-blend","path":"gedi_helpers/modeling_utils.py","file_url":"https://github.com/xxbidiao/plug-and-blend/blob/HEAD/gedi_helpers/modeling_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d30d6c3098df2c42","mcp_get_code":{"code_sha256":"d30d6c3098df2c42"}},{"arxiv_id":"2011.01513","paper":"/paper/charbert-character-aware-pre-trained-language","title":"CharBERT: Character-aware Pre-trained Language Model","date":"2020-11-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wtma/CharBERT","path":"modeling/modeling_utils.py","file_url":"https://github.com/wtma/CharBERT/blob/HEAD/modeling/modeling_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d30d6c3098df2c42","mcp_get_code":{"code_sha256":"d30d6c3098df2c42"}},{"arxiv_id":"2010.05607","paper":"/paper/the-elephant-in-the-interpretability-room-why","title":"The elephant in the interpretability room: Why use attention as explanation when we have saliency methods?","date":"2020-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jessevig/bertviz","path":"bertviz/transformers_neuron_view/modeling_utils.py","file_url":"https://github.com/jessevig/bertviz/blob/HEAD/bertviz/transformers_neuron_view/modeling_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d30d6c3098df2c42","mcp_get_code":{"code_sha256":"d30d6c3098df2c42"}},{"arxiv_id":"2009.06367","paper":"/paper/gedi-generative-discriminator-guided-sequence","title":"GeDi: Generative Discriminator Guided Sequence Generation","date":"2020-09-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salesforce/GeDi","path":"modeling_utils.py","file_url":"https://github.com/salesforce/GeDi/blob/HEAD/modeling_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"d30d6c3098df2c42","mcp_get_code":{"code_sha256":"d30d6c3098df2c42"}},{"arxiv_id":"2007.06028","paper":"/paper/tera-self-supervised-learning-of-transformer","title":"TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech","date":"2020-07-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Pandade1997/tera_asvproof","path":"transformer/model.py","file_url":"https://github.com/Pandade1997/tera_asvproof/blob/HEAD/transformer/model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d30d6c3098df2c42","mcp_get_code":{"code_sha256":"d30d6c3098df2c42"}},{"arxiv_id":"2007.02439","paper":"/paper/pretrained-generalized-autoregressive-model","title":"Pretrained Generalized Autoregressive Model with Adaptive Probabilistic Label Clusters for Extreme Multi-label Text Classification","date":"2020-07-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"huiyegit/APLC_XLNet","path":"code/pytorch_transformers/modeling_utils.py","file_url":"https://github.com/huiyegit/APLC_XLNet/blob/HEAD/code/pytorch_transformers/modeling_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d30d6c3098df2c42","mcp_get_code":{"code_sha256":"d30d6c3098df2c42"}},{"arxiv_id":"2005.00796","paper":"/paper/a-simple-language-model-for-task-oriented","title":"A Simple Language Model for Task-Oriented Dialogue","date":"2020-05-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salesforce/simpletod","path":"models/modeling_utils.py","file_url":"https://github.com/salesforce/simpletod/blob/HEAD/models/modeling_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"d30d6c3098df2c42","mcp_get_code":{"code_sha256":"d30d6c3098df2c42"}},{"arxiv_id":"2005.00558","paper":"/paper/pointer-constrained-text-generation-via","title":"POINTER: Constrained Progressive Text Generation via Insertion-based Generative Pre-training","date":"2020-05-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dreasysnail/POINTER","path":"pytorch_transformers/modeling_utils.py","file_url":"https://github.com/dreasysnail/POINTER/blob/HEAD/pytorch_transformers/modeling_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d30d6c3098df2c42","mcp_get_code":{"code_sha256":"d30d6c3098df2c42"}},{"arxiv_id":"2005.00200","paper":"/paper/hero-hierarchical-encoder-for-video-language","title":"HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training","date":"2020-05-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"linjieli222/HERO","path":"model/modeling_utils.py","file_url":"https://github.com/linjieli222/HERO/blob/HEAD/model/modeling_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"57947ced49b189c3","mcp_get_code":{"code_sha256":"57947ced49b189c3"}},{"arxiv_id":"2004.05707","paper":"/paper/vgcn-bert-augmenting-bert-with-graph","title":"VGCN-BERT: Augmenting BERT with Graph Embedding for Text Classification","date":"2020-04-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Louis-udm/VGCN-BERT","path":"old_version/pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/Louis-udm/VGCN-BERT/blob/HEAD/old_version/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":"393af350cd7381f6","mcp_get_code":{"code_sha256":"393af350cd7381f6"}},{"arxiv_id":"2002.01685","paper":"/paper/parsing-as-pretraining","title":"Parsing as Pretraining","date":"2020-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"huggingface/pytorch-pretrained-BERT","path":"src/transformers/pytorch_utils.py","file_url":"https://github.com/huggingface/pytorch-pretrained-BERT/blob/HEAD/src/transformers/pytorch_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"24ece331635f4b38","mcp_get_code":{"code_sha256":"24ece331635f4b38"}},{"arxiv_id":"1911.03584","paper":"/paper/on-the-relationship-between-self-attention-1","title":"On the Relationship between Self-Attention and Convolutional Layers","date":"2019-11-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"epfml/attention-cnn","path":"models/bert.py","file_url":"https://github.com/epfml/attention-cnn/blob/HEAD/models/bert.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":"2f516ae7fc833c82","mcp_get_code":{"code_sha256":"2f516ae7fc833c82"}},{"arxiv_id":"1911.00720","paper":"/paper/zen-pre-training-chinese-text-encoder","title":"ZEN: Pre-training Chinese Text Encoder Enhanced by N-gram Representations","date":"2019-11-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SVAIGBA/TwASP","path":"pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/SVAIGBA/TwASP/blob/HEAD/pytorch_pretrained_bert/modeling.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d30d6c3098df2c42","mcp_get_code":{"code_sha256":"d30d6c3098df2c42"}},{"arxiv_id":"1910.12638","paper":"/paper/mockingjay-unsupervised-speech-representation","title":"Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders","date":"2019-10-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"samirsahoo007/Audio-and-Speech-Processing","path":"mockingjay/model.py","file_url":"https://github.com/samirsahoo007/Audio-and-Speech-Processing/blob/HEAD/mockingjay/model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d30d6c3098df2c42","mcp_get_code":{"code_sha256":"d30d6c3098df2c42"}},{"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":"Soikonomou/albert_final","path":"src/model/ALBERT/modeling_utils.py","file_url":"https://github.com/Soikonomou/albert_final/blob/HEAD/src/model/ALBERT/modeling_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d30d6c3098df2c42","mcp_get_code":{"code_sha256":"d30d6c3098df2c42"}},{"arxiv_id":"1909.05311","paper":"/paper/graph-based-reasoning-over-heterogeneous","title":"Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering","date":"2019-09-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DecstionBack/AAAI_2020_CommonsenseQA","path":"pytorch_transformers/modeling_utils.py","file_url":"https://github.com/DecstionBack/AAAI_2020_CommonsenseQA/blob/HEAD/pytorch_transformers/modeling_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d30d6c3098df2c42","mcp_get_code":{"code_sha256":"d30d6c3098df2c42"}},{"arxiv_id":"1906.08237","paper":"/paper/xlnet-generalized-autoregressive-pretraining","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","date":"2019-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"samwisegamjeee/pytorch-transformers","path":"pytorch_transformers/modeling_utils.py","file_url":"https://github.com/samwisegamjeee/pytorch-transformers/blob/HEAD/pytorch_transformers/modeling_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d30d6c3098df2c42","mcp_get_code":{"code_sha256":"d30d6c3098df2c42"}},{"arxiv_id":"1906.08230","paper":"/paper/evaluating-protein-transfer-learning-with","title":"Evaluating Protein Transfer Learning with TAPE","date":"2019-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"songlab-cal/tape","path":"tape/models/modeling_utils.py","file_url":"https://github.com/songlab-cal/tape/blob/HEAD/tape/models/modeling_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"d30d6c3098df2c42","mcp_get_code":{"code_sha256":"d30d6c3098df2c42"}},{"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_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f4f4879066931500","mcp_get_code":{"code_sha256":"f4f4879066931500"}},{"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":"andi611/Mockingjay-Speech-Representation","path":"mockingjay/model.py","file_url":"https://github.com/andi611/Mockingjay-Speech-Representation/blob/HEAD/mockingjay/model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d30d6c3098df2c42","mcp_get_code":{"code_sha256":"d30d6c3098df2c42"}},{"arxiv_id":"aaai_5722","paper":null,"title":"arXiv:aaai_5722","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"microsoft/Distilled-Sentence-Embedding","path":"pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/microsoft/Distilled-Sentence-Embedding/blob/HEAD/pytorch_pretrained_bert/modeling.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d30d6c3098df2c42","mcp_get_code":{"code_sha256":"d30d6c3098df2c42"}},{"arxiv_id":"2024.findings-naacl.32","paper":null,"title":"arXiv:2024.findings-naacl.32","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"SnowYJ/sem_syn_separation","path":"optimus_separate_graph_sem_syntax_fuse_gpt2/pytorch_transformers/modeling_utils.py","file_url":"https://github.com/SnowYJ/sem_syn_separation/blob/HEAD/optimus_separate_graph_sem_syntax_fuse_gpt2/pytorch_transformers/modeling_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d30d6c3098df2c42","mcp_get_code":{"code_sha256":"d30d6c3098df2c42"}},{"arxiv_id":"2023.acl-long.264","paper":null,"title":"arXiv:2023.acl-long.264","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"DAMO-NLP-SG/MVCR","path":"src/pytorch_utils.py","file_url":"https://github.com/DAMO-NLP-SG/MVCR/blob/HEAD/src/pytorch_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"763d53d145dbacb5","mcp_get_code":{"code_sha256":"763d53d145dbacb5"}},{"arxiv_id":"2021.emnlp-main.154","paper":null,"title":"arXiv:2021.emnlp-main.154","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Hazelsuko07/TextHide","path":"transformers_hide/modeling_utils.py","file_url":"https://github.com/Hazelsuko07/TextHide/blob/HEAD/transformers_hide/modeling_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b3504e72ce1153fe","mcp_get_code":{"code_sha256":"b3504e72ce1153fe"}}]}