{"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/positionwisefeedforward","entry":"PositionwiseFeedForward","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":36,"n_papers_ran":35,"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":56,"n_samples_ran":53,"n_samples_fingerprinted":18,"n_places":56,"n_places_pointer_only":33,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":53,"unverified":3},"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":"2608.10240","paper":"/paper/arxiv-2608-10240","title":"Sequential Modality Dropout for Robust Multi-Modal Sequential Recommendation *","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"guanqun-yang/SMD","path":"smd/model.py","file_url":"https://github.com/guanqun-yang/SMD/blob/HEAD/smd/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e5bce0d87d8da24a","mcp_get_code":{"code_sha256":"e5bce0d87d8da24a"}},{"arxiv_id":"2603.25752","paper":"/paper/arxiv-2603-25752","title":"Relational graph-driven differential denoising and diffusion attention fusion for multimodal conversation emotion recognition","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"liuying2023912/ReDiFu","path":"model.py","file_url":"https://github.com/liuying2023912/ReDiFu/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4f0b486a3ee98606","mcp_get_code":{"code_sha256":"4f0b486a3ee98606"}},{"arxiv_id":"2603.15774","paper":"/paper/arxiv-2603-15774","title":"Domain Adaptation Without the Compute Burden for Efficient Whole Slide Image Analysis","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"umarikkar/eWSI","path":"models/wsi_models.py","file_url":"https://github.com/umarikkar/eWSI/blob/HEAD/models/wsi_models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ada0c80b6bd1eba6","mcp_get_code":{"code_sha256":"ada0c80b6bd1eba6"}},{"arxiv_id":"2505.16298","paper":"/paper/flow-matching-based-sequential-recommender","title":"Flow Matching based Sequential Recommender Model","date":"2025-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"FengLiu-1/FMRec","path":"src/fmrec.py","file_url":"https://github.com/FengLiu-1/FMRec/blob/HEAD/src/fmrec.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"83bf41e37a4efe7c","mcp_get_code":{"code_sha256":"83bf41e37a4efe7c"}},{"arxiv_id":"2503.07635","paper":"/paper/cross-modal-causal-relation-alignment-for-1","title":"Cross-modal Causal Relation Alignment for Video Question Grounding","date":"2025-03-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"WissingChen/CRA-GQA","path":"models/cra.py","file_url":"https://github.com/WissingChen/CRA-GQA/blob/HEAD/models/cra.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"45ddeb3b36bed730","mcp_get_code":{"code_sha256":"45ddeb3b36bed730"}},{"arxiv_id":"2502.10408","paper":"/paper/knowledge-tracing-in-programming-education","title":"Knowledge Tracing in Programming Education Integrating Students' Questions","date":"2025-01-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"holi-lab/SQKT","path":"main/blocks/encoder_layer.py","file_url":"https://github.com/holi-lab/SQKT/blob/HEAD/main/blocks/encoder_layer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3f04f961d1a1a3dd","mcp_get_code":{"code_sha256":"3f04f961d1a1a3dd"}},{"arxiv_id":"2501.16825","paper":"/paper/can-transformers-learn-full-bayesian","title":"Can Transformers Learn Full Bayesian Inference in Context?","date":"2025-01-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"arikreuter/icl_for_full_bayesian_inference","path":"LinearRegression/Models/Transformer_CNF.py","file_url":"https://github.com/arikreuter/icl_for_full_bayesian_inference/blob/HEAD/LinearRegression/Models/Transformer_CNF.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c8a3be75f1c48e47","mcp_get_code":{"code_sha256":"c8a3be75f1c48e47"}},{"arxiv_id":"2411.07527","paper":"/paper/prompt-enhanced-network-for-hateful-meme","title":"Prompt-enhanced Network for Hateful Meme Classification","date":"2024-11-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"juszzi/Pen","path":"Pen/rela_encoder.py","file_url":"https://github.com/juszzi/Pen/blob/HEAD/Pen/rela_encoder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"310aa085b41983d9","mcp_get_code":{"code_sha256":"310aa085b41983d9"}},{"arxiv_id":"2411.04554","paper":"/paper/peri-midformer-periodic-pyramid-transformer","title":"Peri-midFormer: Periodic Pyramid Transformer for Time Series Analysis","date":"2024-11-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"WuQiangXDU/Peri-midFormer","path":"model/PerimidFormer.py","file_url":"https://github.com/WuQiangXDU/Peri-midFormer/blob/HEAD/model/PerimidFormer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e988889f2e24b89d","mcp_get_code":{"code_sha256":"e988889f2e24b89d"}},{"arxiv_id":"2410.13117","paper":"/paper/preference-diffusion-for-recommendation","title":"Preference Diffusion for Recommendation","date":"2024-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lswhim/preferdiff","path":"models/PreferDiff/_model.py","file_url":"https://github.com/lswhim/preferdiff/blob/HEAD/models/PreferDiff/_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"89f25d4ab4d600e3","mcp_get_code":{"code_sha256":"89f25d4ab4d600e3"}},{"arxiv_id":"2406.09899","paper":"/paper/learning-solution-aware-transformers-for","title":"Learning Solution-Aware Transformers for Efficiently Solving Quadratic Assignment Problem","date":"2024-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pkutan/sawt","path":"ActorCriticNetwork_qap_mixEncoder.py","file_url":"https://github.com/pkutan/sawt/blob/HEAD/ActorCriticNetwork_qap_mixEncoder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9c08d66abe21cb78","mcp_get_code":{"code_sha256":"9c08d66abe21cb78"}},{"arxiv_id":"2406.08173","paper":"/paper/semi-supervised-spoken-language","title":"Semi-Supervised Spoken Language Glossification","date":"2024-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yaohj11/S3LG","path":"model/seq2seq/encoder.py","file_url":"https://github.com/yaohj11/S3LG/blob/HEAD/model/seq2seq/encoder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"40933e301bb2d3be","mcp_get_code":{"code_sha256":"40933e301bb2d3be"}},{"arxiv_id":"2405.03943","paper":"/paper/predictive-modeling-with-temporal-graphical","title":"Predictive Modeling with Temporal Graphical Representation on Electronic Health Records","date":"2024-05-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"The-Real-JerryChen/TRANS","path":"models/Seqmodels.py","file_url":"https://github.com/The-Real-JerryChen/TRANS/blob/HEAD/models/Seqmodels.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e1041c5cf014c687","mcp_get_code":{"code_sha256":"e1041c5cf014c687"}},{"arxiv_id":"2404.13478","paper":"/paper/deep-se-3-equivariant-geometric-reasoning-for","title":"Deep SE(3)-Equivariant Geometric Reasoning for Precise Placement Tasks","date":"2024-04-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"r-pad/taxpose","path":"taxpose/nets/transformer_flow.py","file_url":"https://github.com/r-pad/taxpose/blob/HEAD/taxpose/nets/transformer_flow.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"49c1ccb5ad835ec4","mcp_get_code":{"code_sha256":"49c1ccb5ad835ec4"}},{"arxiv_id":"2404.05218","paper":"/paper/multi-agent-long-term-3d-human-pose","title":"Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning","date":"2024-04-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Jaewoo97/T2P","path":"models/lightningModel_T2P.py","file_url":"https://github.com/Jaewoo97/T2P/blob/HEAD/models/lightningModel_T2P.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"26d72c0390d2b9a9","mcp_get_code":{"code_sha256":"26d72c0390d2b9a9"}},{"arxiv_id":"2310.19727","paper":"/paper/generating-medical-instructions-with","title":"Generating Medical Prescriptions with Conditional Transformer","date":"2023-10-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hecta-uom/label-to-text-transformer","path":"Models/EncDecTransformer/Models.py","file_url":"https://github.com/hecta-uom/label-to-text-transformer/blob/HEAD/Models/EncDecTransformer/Models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fcc2d8bf7194efb7","mcp_get_code":{"code_sha256":"fcc2d8bf7194efb7"}},{"arxiv_id":"2305.19271","paper":"/paper/concise-answers-to-complex-questions","title":"Concise Answers to Complex Questions: Summarization of Long-form Answers","date":"2023-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"acpotluri/lfqa_summary","path":"model/PreSumm/src/models/encoder.py","file_url":"https://github.com/acpotluri/lfqa_summary/blob/HEAD/model/PreSumm/src/models/encoder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0ba6c9ba01f4abd2","mcp_get_code":{"code_sha256":"0ba6c9ba01f4abd2"}},{"arxiv_id":"2304.11335","paper":"/paper/two-birds-one-stone-a-unified-framework-for","title":"Two Birds, One Stone: A Unified Framework for Joint Learning of Image and Video Style Transfers","date":"2023-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NevSNev/UniST","path":"models/transformer/Models.py","file_url":"https://github.com/NevSNev/UniST/blob/HEAD/models/transformer/Models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fbe61734f350ca10","mcp_get_code":{"code_sha256":"fbe61734f350ca10"}},{"arxiv_id":"2303.14348","paper":"/paper/zero-shot-everything-sketch-based-image","title":"Zero-Shot Everything Sketch-Based Image Retrieval, and in Explainable Style","date":"2023-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"buptLinfy/ZSE-SBIR","path":"model/model.py","file_url":"https://github.com/buptLinfy/ZSE-SBIR/blob/HEAD/model/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2d97255bca4d10bc","mcp_get_code":{"code_sha256":"2d97255bca4d10bc"}},{"arxiv_id":"2303.05725","paper":"/paper/cvt-slr-contrastive-visual-textual","title":"CVT-SLR: Contrastive Visual-Textual Transformation for Sign Language Recognition with Variational Alignment","date":"2023-03-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"binbinjiang/CVT-SLR","path":"cvtslr_model.py","file_url":"https://github.com/binbinjiang/CVT-SLR/blob/HEAD/cvtslr_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bef5f1e882f94aa7","mcp_get_code":{"code_sha256":"bef5f1e882f94aa7"}},{"arxiv_id":"2210.00313","paper":"/paper/crisp-curriculum-based-sequential-neural","title":"CRISP: Curriculum based Sequential Neural Decoders for Polar Code Family","date":"2022-10-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hebbarashwin/neural_polar_decoder","path":"models.py","file_url":"https://github.com/hebbarashwin/neural_polar_decoder/blob/HEAD/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"86babeb581f77b1a","mcp_get_code":{"code_sha256":"86babeb581f77b1a"}},{"arxiv_id":"2207.09644","paper":"/paper/hierarchically-self-supervised-transformer","title":"Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning","date":"2022-07-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuxiaochen1103/Hi-TRS","path":"model/Hi_TRS.py","file_url":"https://github.com/yuxiaochen1103/Hi-TRS/blob/HEAD/model/Hi_TRS.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":"c43b3abbac05b81b","mcp_get_code":{"code_sha256":"c43b3abbac05b81b"}},{"arxiv_id":"2203.07628","paper":"/paper/p-stmo-pre-trained-spatial-temporal-many-to","title":"P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimation","date":"2022-03-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"paTRICK-swk/P-STMO","path":"model/stmo_pretrain.py","file_url":"https://github.com/paTRICK-swk/P-STMO/blob/HEAD/model/stmo_pretrain.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cb80183aeec842d5","mcp_get_code":{"code_sha256":"cb80183aeec842d5"}},{"arxiv_id":"2202.13024","paper":"/paper/assist-towards-label-noise-robust-dialogue-1","title":"ASSIST: Towards Label Noise-Robust Dialogue State Tracking","date":"2022-02-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"smartyfh/dst-assist","path":"STAR/models/DST.py","file_url":"https://github.com/smartyfh/dst-assist/blob/HEAD/STAR/models/DST.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1e655eaebd58dfd6","mcp_get_code":{"code_sha256":"1e655eaebd58dfd6"}},{"arxiv_id":"2202.04298","paper":"/paper/image-difference-captioning-with-pre-training","title":"Image Difference Captioning with Pre-training and Contrastive Learning","date":"2022-02-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yaolinli/IDC","path":"bird/modules_pretrain_bird.py","file_url":"https://github.com/yaolinli/IDC/blob/HEAD/bird/modules_pretrain_bird.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7b01671a89b20337","mcp_get_code":{"code_sha256":"7b01671a89b20337"}},{"arxiv_id":"2109.05160","paper":"/paper/streamhover-livestream-transcript","title":"StreamHover: Livestream Transcript Summarization and Annotation","date":"2021-09-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ucfnlp/streamhover","path":"src/modeling_bertvqvae.py","file_url":"https://github.com/ucfnlp/streamhover/blob/HEAD/src/modeling_bertvqvae.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a632b48286d1529b","mcp_get_code":{"code_sha256":"a632b48286d1529b"}},{"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":"053f83a8a313ebf7","mcp_get_code":{"code_sha256":"053f83a8a313ebf7"}},{"arxiv_id":"2103.01863","paper":"/paper/data-augmentation-for-abstractive-query","title":"Data Augmentation for Abstractive Query-Focused Multi-Document Summarization","date":"2021-03-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ramakanth-pasunuru/QmdsCnnIr","path":"src/abstractive/transformer_encoder.py","file_url":"https://github.com/ramakanth-pasunuru/QmdsCnnIr/blob/HEAD/src/abstractive/transformer_encoder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"615f570cc33bdbff","mcp_get_code":{"code_sha256":"615f570cc33bdbff"}},{"arxiv_id":"2102.07108","paper":"/paper/cate-computation-aware-neural-architecture","title":"CATE: Computation-aware Neural Architecture Encoding with Transformers","date":"2021-02-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MSU-MLSys-Lab/CATE","path":"layers/transformer.py","file_url":"https://github.com/MSU-MLSys-Lab/CATE/blob/HEAD/layers/transformer.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":"73d36f4b75757093","mcp_get_code":{"code_sha256":"73d36f4b75757093"}},{"arxiv_id":"2010.16056","paper":"/paper/generating-radiology-reports-via-memory","title":"Generating Radiology Reports via Memory-driven Transformer","date":"2020-10-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cuhksz-nlp/R2Gen","path":"modules/encoder_decoder.py","file_url":"https://github.com/cuhksz-nlp/R2Gen/blob/HEAD/modules/encoder_decoder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"31ac554b956f2c39","mcp_get_code":{"code_sha256":"31ac554b956f2c39"}},{"arxiv_id":"2006.04558","paper":"/paper/fastspeech-2-fast-and-high-quality-end-to-end","title":"FastSpeech 2: Fast and High-Quality End-to-End Text to Speech","date":"2020-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OlaWod/my-fastspeech2","path":"model/model.py","file_url":"https://github.com/OlaWod/my-fastspeech2/blob/HEAD/model/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"06c86d0f5a38e81d","mcp_get_code":{"code_sha256":"06c86d0f5a38e81d"}},{"arxiv_id":"2005.10636","paper":"/paper/graph-based-self-supervised-program-repair","title":"Graph-based, Self-Supervised Program Repair from Diagnostic Feedback","date":"2020-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"michiyasunaga/DrRepair","path":"model/repairer/model/attention_zoo.py","file_url":"https://github.com/michiyasunaga/DrRepair/blob/HEAD/model/repairer/model/attention_zoo.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"675f1cb139ebf772","mcp_get_code":{"code_sha256":"675f1cb139ebf772"}},{"arxiv_id":"2002.03912","paper":"/paper/a-probabilistic-formulation-of-unsupervised-1","title":"A Probabilistic Formulation of Unsupervised Text Style Transfer","date":"2020-02-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thu-coai/NAST","path":"styletransformer/transformer.py","file_url":"https://github.com/thu-coai/NAST/blob/HEAD/styletransformer/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"94350806140c9d40","mcp_get_code":{"code_sha256":"94350806140c9d40"}},{"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":"xinyooo/ALBERT4Rec","path":"models/albert_modules/albert.py","file_url":"https://github.com/xinyooo/ALBERT4Rec/blob/HEAD/models/albert_modules/albert.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b0a2ed9c8469e733","mcp_get_code":{"code_sha256":"b0a2ed9c8469e733"}},{"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":"fanchenyou/transformer-study","path":"transformer_bert_from_scratch_5.py","file_url":"https://github.com/fanchenyou/transformer-study/blob/HEAD/transformer_bert_from_scratch_5.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"708bd2d8037a185a","mcp_get_code":{"code_sha256":"708bd2d8037a185a"}},{"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":"wenhuchen/HDSA-Dialog","path":"transformer/Transformer.py","file_url":"https://github.com/wenhuchen/HDSA-Dialog/blob/HEAD/transformer/Transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c47eb374e0a8f194","mcp_get_code":{"code_sha256":"c47eb374e0a8f194"}},{"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":"linlei1214/SITS-BERT","path":"code/model/bert.py","file_url":"https://github.com/linlei1214/SITS-BERT/blob/HEAD/code/model/bert.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bb6ffa608bbf657a","mcp_get_code":{"code_sha256":"bb6ffa608bbf657a"}},{"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":"tbmoon/LANL_Earthquake_Prediction","path":"models.py","file_url":"https://github.com/tbmoon/LANL_Earthquake_Prediction/blob/HEAD/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8ca2995c70fac925","mcp_get_code":{"code_sha256":"8ca2995c70fac925"}},{"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":"WenYanger/General-Transformer-Pytorch","path":"Transformer.py","file_url":"https://github.com/WenYanger/General-Transformer-Pytorch/blob/HEAD/Transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"583bf56f778b678c","mcp_get_code":{"code_sha256":"583bf56f778b678c"}},{"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":"Rudedaisy/attention-is-all-you-need-pytorch","path":"transformer/Models.py","file_url":"https://github.com/Rudedaisy/attention-is-all-you-need-pytorch/blob/HEAD/transformer/Models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e2f9a8814c83e9c2","mcp_get_code":{"code_sha256":"e2f9a8814c83e9c2"}},{"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":"emanuele-progr/PSSP","path":"transformer.py","file_url":"https://github.com/emanuele-progr/PSSP/blob/HEAD/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0e3b92e0684cdafe","mcp_get_code":{"code_sha256":"0e3b92e0684cdafe"}},{"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":"maxjcohen/transformer","path":"tst/transformer.py","file_url":"https://github.com/maxjcohen/transformer/blob/HEAD/tst/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"486e9a9a09cbf295","mcp_get_code":{"code_sha256":"486e9a9a09cbf295"}},{"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":"liqichen6688/duo-attention","path":"transformer/Models.py","file_url":"https://github.com/liqichen6688/duo-attention/blob/HEAD/transformer/Models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3f8ebf0cc8ec619a","mcp_get_code":{"code_sha256":"3f8ebf0cc8ec619a"}},{"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":"MohamedAbdelsalam9/TT-Transformer","path":"transformer/Models.py","file_url":"https://github.com/MohamedAbdelsalam9/TT-Transformer/blob/HEAD/transformer/Models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1dd2bd9e74a21753","mcp_get_code":{"code_sha256":"1dd2bd9e74a21753"}},{"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":"ArdalanM/nlp-benchmarks","path":"src/transformer/net.py","file_url":"https://github.com/ArdalanM/nlp-benchmarks/blob/HEAD/src/transformer/net.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b77b511f5a7d8cb3","mcp_get_code":{"code_sha256":"b77b511f5a7d8cb3"}},{"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":"SeoroMin/transformer_pytorch_ver2","path":"transformer/Models.py","file_url":"https://github.com/SeoroMin/transformer_pytorch_ver2/blob/HEAD/transformer/Models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"59c10ff7631302cc","mcp_get_code":{"code_sha256":"59c10ff7631302cc"}},{"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":"Fuchai/language","path":"deeplearning/modeltran.py","file_url":"https://github.com/Fuchai/language/blob/HEAD/deeplearning/modeltran.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"083dd65cb15695f9","mcp_get_code":{"code_sha256":"083dd65cb15695f9"}},{"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":"harvardnlp/annotated-transformer","path":"the_annotated_transformer.py","file_url":"https://github.com/harvardnlp/annotated-transformer/blob/HEAD/the_annotated_transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a8d2219ac8ec7146","mcp_get_code":{"code_sha256":"a8d2219ac8ec7146"}},{"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":"yanqi1811/attention-is-all-you-need","path":"transformer/Models.py","file_url":"https://github.com/yanqi1811/attention-is-all-you-need/blob/HEAD/transformer/Models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c50111aa9f26fffb","mcp_get_code":{"code_sha256":"c50111aa9f26fffb"}},{"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":"kolloldas/torchnlp","path":"torchnlp/modules/transformer/layers.py","file_url":"https://github.com/kolloldas/torchnlp/blob/HEAD/torchnlp/modules/transformer/layers.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":"0f93a85f3e656b7f","mcp_get_code":{"code_sha256":"0f93a85f3e656b7f"}},{"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":"kotu931226/classifier_transformer_pytorch","path":"model.py","file_url":"https://github.com/kotu931226/classifier_transformer_pytorch/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ab073a092d8942cf","mcp_get_code":{"code_sha256":"ab073a092d8942cf"}},{"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":"moon23k/Transformer_Anchors","path":"model/scratch_model.py","file_url":"https://github.com/moon23k/Transformer_Anchors/blob/HEAD/model/scratch_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a8f32ef8ab2a43b1","mcp_get_code":{"code_sha256":"a8f32ef8ab2a43b1"}},{"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":"keonlee9420/Parallel-Tacotron2","path":"model/blocks.py","file_url":"https://github.com/keonlee9420/Parallel-Tacotron2/blob/HEAD/model/blocks.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8de76ac05ed6c255","mcp_get_code":{"code_sha256":"8de76ac05ed6c255"}},{"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":"stevinc/Transformer_Timeseries","path":"models/transformer/transformer.py","file_url":"https://github.com/stevinc/Transformer_Timeseries/blob/HEAD/models/transformer/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f5193eab5eb0653d","mcp_get_code":{"code_sha256":"f5193eab5eb0653d"}},{"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":"hyunwookl/testam","path":"model.py","file_url":"https://github.com/hyunwookl/testam/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a047ded78438c656","mcp_get_code":{"code_sha256":"a047ded78438c656"}},{"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":"Iwontbecreative/Abstractive-summarization-OpenNMT","path":"onmt/modules/Transformer.py","file_url":"https://github.com/Iwontbecreative/Abstractive-summarization-OpenNMT/blob/HEAD/onmt/modules/Transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4c5b5d661b4f81c9","mcp_get_code":{"code_sha256":"4c5b5d661b4f81c9"}}]}