{"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/selfattention","entry":"SelfAttention","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":66,"n_papers_ran":48,"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":74,"n_samples_ran":53,"n_samples_fingerprinted":10,"n_places":74,"n_places_pointer_only":30,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":53,"unverified":21},"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":"2608.19735","paper":"/paper/arxiv-2608-19735","title":"RecPFN: Prior-Fitted Networks for In-Context-Based Recommendations","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"SAP-samples/tabular-ai-recpfn","path":"src/architecture/recpfn.py","file_url":"https://github.com/SAP-samples/tabular-ai-recpfn/blob/HEAD/src/architecture/recpfn.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":"d769cfcf49ce4a01","mcp_get_code":{"code_sha256":"d769cfcf49ce4a01"}},{"arxiv_id":"2608.01839","paper":"/paper/arxiv-2608-01839","title":"tFUSOperator: Operator Learning for Transcranial Focused Ultrasound Digital Twins","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"CMME-Lab/tFUSOperator","path":"models/model.py","file_url":"https://github.com/CMME-Lab/tFUSOperator/blob/HEAD/models/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5045ed55ca7c16d6","mcp_get_code":{"code_sha256":"5045ed55ca7c16d6"}},{"arxiv_id":"2606.26549","paper":"/paper/arxiv-2606-26549","title":"PMDformer: Patch-Mean Decoupling Information Transformer for Long-term Forecasting","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"aohu1105/PMDformer","path":"model/PMDformer.py","file_url":"https://github.com/aohu1105/PMDformer/blob/HEAD/model/PMDformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a8b5200d1575c3a0","mcp_get_code":{"code_sha256":"a8b5200d1575c3a0"}},{"arxiv_id":"2606.17584","paper":"/paper/arxiv-2606-17584","title":"Root-Selecting Fixed-Point Inversion for Rectified Flows via Trajectory Straightness","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"seminkim/selfix","path":"src/flux/sampling.py","file_url":"https://github.com/seminkim/selfix/blob/HEAD/src/flux/sampling.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":"0b8453ea4488f39a","mcp_get_code":{"code_sha256":"0b8453ea4488f39a"}},{"arxiv_id":"2606.02221","paper":"/paper/arxiv-2606-02221","title":"CORE-MTL: Rethinking Gradient Balancing via Causal Orthogonal Representations","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"Hope-Rita/CORE-MTL","path":"models/causal_model.py","file_url":"https://github.com/Hope-Rita/CORE-MTL/blob/HEAD/models/causal_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2a237155525da629","mcp_get_code":{"code_sha256":"2a237155525da629"}},{"arxiv_id":"2605.20188","paper":"/paper/arxiv-2605-20188","title":"GraphDiffMed: Knowledge-Constrained Differential Attention with Pharmacological Graph Priors for Medication Recommendation","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"saxenakrati09/GraphDiffMed","path":"src/modules/GraphDiffMed.py","file_url":"https://github.com/saxenakrati09/GraphDiffMed/blob/HEAD/src/modules/GraphDiffMed.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cbc1e928132dfbcd","mcp_get_code":{"code_sha256":"cbc1e928132dfbcd"}},{"arxiv_id":"2605.01220","paper":"/paper/arxiv-2605-01220","title":"Visual Implicit Autoregressive Modeling","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"mobiushy/VIAR","path":"models/basic_var.py","file_url":"https://github.com/mobiushy/VIAR/blob/HEAD/models/basic_var.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"50d550228a616be7","mcp_get_code":{"code_sha256":"50d550228a616be7"}},{"arxiv_id":"2604.15377","paper":"/paper/arxiv-2604-15377","title":"M3R: Localized Rainfall Nowcasting with Meteorology-Informed MultiModal Attention","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"Sanjeev97/M3Rain","path":"models/m3.py","file_url":"https://github.com/Sanjeev97/M3Rain/blob/HEAD/models/m3.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c23ad2b0cf64d690","mcp_get_code":{"code_sha256":"c23ad2b0cf64d690"}},{"arxiv_id":"2604.13472","paper":"/paper/arxiv-2604-13472","title":"Bridging MARL to SARL: An Order-Independent Multi-Agent Transformer via Latent Consensus","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"PKU-MARL/Multi-Agent-Transformer","path":"mat/algorithms/mat/algorithm/ma_transformer.py","file_url":"https://github.com/PKU-MARL/Multi-Agent-Transformer/blob/HEAD/mat/algorithms/mat/algorithm/ma_transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"508634b69e88baa8","mcp_get_code":{"code_sha256":"508634b69e88baa8"}},{"arxiv_id":"2603.12716","paper":"/paper/arxiv-2603-12716","title":"UNIStainNet: Foundation-Model-Guided Virtual Staining of H&E to IHC","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"facevoid/UNIStainNet","path":"src/models/generator.py","file_url":"https://github.com/facevoid/UNIStainNet/blob/HEAD/src/models/generator.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bb1077eb6cfa4df4","mcp_get_code":{"code_sha256":"bb1077eb6cfa4df4"}},{"arxiv_id":"2603.11691","paper":"/paper/arxiv-2603-11691","title":"INTERLEAVED RECURSIVE STRUCTURE TRANSFORMER FOR OFFLINE MULTI-TASK MULTI-AGENT REINFORCEMENT LEARNING","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"Jiwonjeon9603/Stairs-Former","path":"src/utils/transformer.py","file_url":"https://github.com/Jiwonjeon9603/Stairs-Former/blob/HEAD/src/utils/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"678d327a0f9e0478","mcp_get_code":{"code_sha256":"678d327a0f9e0478"}},{"arxiv_id":"2603.03312","paper":"/paper/arxiv-2603-03312","title":"Escaping the BLEU Trap: A Signal-Grounded Framework with Decoupled Semantic Guidance for EEG-to-Text Decoding","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"xmed-lab/SemKey","path":"model/semkey_parallel.py","file_url":"https://github.com/xmed-lab/SemKey/blob/HEAD/model/semkey_parallel.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5fb31b7fb7dcea79","mcp_get_code":{"code_sha256":"5fb31b7fb7dcea79"}},{"arxiv_id":"2602.08322","paper":"/paper/arxiv-2602-08322","title":"A Generative Model for Joint Multiple Intent Detection and Slot Filling","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"LooperXX/AGIF","path":"models/module.py","file_url":"https://github.com/LooperXX/AGIF/blob/HEAD/models/module.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"GPL-2.0","inline_ok":false,"code_sha256_prefix":"d3edde00bba31ab3","mcp_get_code":{"code_sha256":"d3edde00bba31ab3"}},{"arxiv_id":"2602.00883","paper":"/paper/arxiv-2602-00883","title":"DIAMOND: Directed Inference for Artifact Mitigation in Flow Matching Models","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"ali-vilab/DiffDoctor","path":"src/flux/sampling.py","file_url":"https://github.com/ali-vilab/DiffDoctor/blob/HEAD/src/flux/sampling.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"64127abf54837b48","mcp_get_code":{"code_sha256":"64127abf54837b48"}},{"arxiv_id":"2601.19561","paper":"/paper/arxiv-2601-19561","title":"AROMMA: Unifying Olfactory Embeddings for Single Molecules and Mixtures","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"DGIST-Distributed-AI-Lab/aromma","path":"src/model/framework.py","file_url":"https://github.com/DGIST-Distributed-AI-Lab/aromma/blob/HEAD/src/model/framework.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e0161c37de5bf2da","mcp_get_code":{"code_sha256":"e0161c37de5bf2da"}},{"arxiv_id":"2601.17215","paper":"/paper/arxiv-2601-17215","title":"JetFormer: A Scalable and Efficient Transformer for Jet Tagging from Offline Analysis to FPGA Triggers","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"walkieq/JetFormer","path":"transformer/src/net.py","file_url":"https://github.com/walkieq/JetFormer/blob/HEAD/transformer/src/net.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6f17c3b47eab149a","mcp_get_code":{"code_sha256":"6f17c3b47eab149a"}},{"arxiv_id":"2601.11190","paper":"/paper/arxiv-2601-11190","title":"DOREMI: Optimizing Long Tail Predictions in Document-Level Relation Extraction ⋆","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"mntlra/DOREMI","path":"src/models/ContextAware.py","file_url":"https://github.com/mntlra/DOREMI/blob/HEAD/src/models/ContextAware.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"52a0529fb694069e","mcp_get_code":{"code_sha256":"52a0529fb694069e"}},{"arxiv_id":"2510.11321","paper":"/paper/arxiv-2510-11321","title":"HiMaCon: Discovering Hierarchical Manipulation Concepts from Unlabeled Multi-Modal Data","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"zrllrz/HiMaCon","path":"src/hminfocon.py","file_url":"https://github.com/zrllrz/HiMaCon/blob/HEAD/src/hminfocon.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"13cfb4beb66982da","mcp_get_code":{"code_sha256":"13cfb4beb66982da"}},{"arxiv_id":"2504.02160","paper":"/paper/less-to-more-generalization-unlocking-more","title":"Less-to-More Generalization: Unlocking More Controllability by In-Context Generation","date":"2025-04-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bytedance/UNO","path":"uno/flux/pipeline.py","file_url":"https://github.com/bytedance/UNO/blob/HEAD/uno/flux/pipeline.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":"3d23efb955326633","mcp_get_code":{"code_sha256":"3d23efb955326633"}},{"arxiv_id":"2504.01941","paper":"/paper/end-to-end-driving-with-online-trajectory","title":"End-to-End Driving with Online Trajectory Evaluation via BEV World Model","date":"2025-04-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liyingyanucas/wote","path":"navsim/agents/WoTE/WoTE_model.py","file_url":"https://github.com/liyingyanucas/wote/blob/HEAD/navsim/agents/WoTE/WoTE_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0d6f5b6295b5a19c","mcp_get_code":{"code_sha256":"0d6f5b6295b5a19c"}},{"arxiv_id":"2503.18938","paper":"/paper/adaworld-learning-adaptable-world-models-with","title":"AdaWorld: Learning Adaptable World Models with Latent Actions","date":"2025-03-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"little-podi/adaworld","path":"lam/lam/modules/lam.py","file_url":"https://github.com/little-podi/adaworld/blob/HEAD/lam/lam/modules/lam.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":"b1d5f5dfa4ddac49","mcp_get_code":{"code_sha256":"b1d5f5dfa4ddac49"}},{"arxiv_id":"2502.19962","paper":"/paper/recon-enhancing-true-correspondence-1","title":"ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning","date":"2025-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qxzha/ReCon","path":"models/SGRAF.py","file_url":"https://github.com/qxzha/ReCon/blob/HEAD/models/SGRAF.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d4d6173d6e5117e7","mcp_get_code":{"code_sha256":"d4d6173d6e5117e7"}},{"arxiv_id":"2502.17363","paper":"/paper/kv-edit-training-free-image-editing-for","title":"KV-Edit: Training-Free Image Editing for Precise Background Preservation","date":"2025-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Xilluill/KV-Edit","path":"models/kv_edit.py","file_url":"https://github.com/Xilluill/KV-Edit/blob/HEAD/models/kv_edit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0c92e50f90ae4f64","mcp_get_code":{"code_sha256":"0c92e50f90ae4f64"}},{"arxiv_id":"2502.10425","paper":"/paper/neuron-platonic-intrinsic-representation-from","title":"Neuron Platonic Intrinsic Representation From Dynamics Using Contrastive Learning","date":"2025-02-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ww20hust/NeurPIR","path":"src/models/encoder.py","file_url":"https://github.com/ww20hust/NeurPIR/blob/HEAD/src/models/encoder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f3a7127917231ebd","mcp_get_code":{"code_sha256":"f3a7127917231ebd"}},{"arxiv_id":"2502.04320","paper":"/paper/conceptattention-diffusion-transformers-learn","title":"ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features","date":"2025-02-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"helblazer811/ConceptAttention","path":"concept_attention/flux/dit_block.py","file_url":"https://github.com/helblazer811/ConceptAttention/blob/HEAD/concept_attention/flux/dit_block.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"44b8130635f7bada","mcp_get_code":{"code_sha256":"44b8130635f7bada"}},{"arxiv_id":"2502.01105","paper":"/paper/layertracer-cognitive-aligned-layered-svg","title":"LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer","date":"2025-02-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"showlab/LayerTracer","path":"library/flux_models.py","file_url":"https://github.com/showlab/LayerTracer/blob/HEAD/library/flux_models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"597cb2e18f1492d8","mcp_get_code":{"code_sha256":"597cb2e18f1492d8"}},{"arxiv_id":"2501.09054","paper":"/paper/neurop-diff-continuous-remote-sensing-image","title":"NeurOp-Diff:Continuous Remote Sensing Image Super-Resolution via Neural Operator Diffusion","date":"2025-01-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zerono000/NeurOp-Diff","path":"models/diffusion.py","file_url":"https://github.com/zerono000/NeurOp-Diff/blob/HEAD/models/diffusion.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c8584d0a7fb92793","mcp_get_code":{"code_sha256":"c8584d0a7fb92793"}},{"arxiv_id":"2410.06264","paper":"/paper/think-while-you-generate-discrete-diffusion","title":"Think While You Generate: Discrete Diffusion with Planned Denoising","date":"2024-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liusulin/ddpd","path":"text8/model_planner.py","file_url":"https://github.com/liusulin/ddpd/blob/HEAD/text8/model_planner.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ab7bf8223903c9b6","mcp_get_code":{"code_sha256":"ab7bf8223903c9b6"}},{"arxiv_id":"2407.02309","paper":"/paper/semantically-guided-representation-learning","title":"Semantically Guided Representation Learning For Action Anticipation","date":"2024-07-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ADiko1997/S-GEAR","path":"models/base_model_ts.py","file_url":"https://github.com/ADiko1997/S-GEAR/blob/HEAD/models/base_model_ts.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4d0ab14d77dfb105","mcp_get_code":{"code_sha256":"4d0ab14d77dfb105"}},{"arxiv_id":"2406.09997","paper":"/paper/towards-scalable-and-versatile-weight-space","title":"Towards Scalable and Versatile Weight Space Learning","date":"2024-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hsg-aiml/sane","path":"src/SANE/models/def_AE.py","file_url":"https://github.com/hsg-aiml/sane/blob/HEAD/src/SANE/models/def_AE.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e81937cece236ca0","mcp_get_code":{"code_sha256":"e81937cece236ca0"}},{"arxiv_id":"2406.04329","paper":"/paper/simplified-and-generalized-masked-diffusion","title":"Simplified and Generalized Masked Diffusion for Discrete Data","date":"2024-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-deepmind/md4","path":"md4/models/diffusion/md4.py","file_url":"https://github.com/google-deepmind/md4/blob/HEAD/md4/models/diffusion/md4.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":"daf4ef755a1978a3","mcp_get_code":{"code_sha256":"daf4ef755a1978a3"}},{"arxiv_id":"2404.10939","paper":"/paper/more-room-for-language-investigating-the","title":"More Room for Language: Investigating the Effect of Retrieval on Language Models","date":"2024-04-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ltgoslo/more-room-for-language","path":"pretraining/model.py","file_url":"https://github.com/ltgoslo/more-room-for-language/blob/HEAD/pretraining/model.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":"34fd7ee81a1f04a3","mcp_get_code":{"code_sha256":"34fd7ee81a1f04a3"}},{"arxiv_id":"2404.01740","paper":"/paper/weakly-supervised-audio-separation-via-bi","title":"Weakly-supervised Audio Separation via Bi-modal Semantic Similarity","date":"2024-04-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/bimodalaudioseparation","path":"models/cond_unet_attn.py","file_url":"https://github.com/microsoft/bimodalaudioseparation/blob/HEAD/models/cond_unet_attn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fee297065b6d46a5","mcp_get_code":{"code_sha256":"fee297065b6d46a5"}},{"arxiv_id":"2402.12138","paper":"/paper/perceiving-longer-sequences-with-bi","title":"Perceiving Longer Sequences With Bi-Directional Cross-Attention Transformers","date":"2024-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mrkshllr/bixt","path":"timm/models/bixt.py","file_url":"https://github.com/mrkshllr/bixt/blob/HEAD/timm/models/bixt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"82dbf42759abac64","mcp_get_code":{"code_sha256":"82dbf42759abac64"}},{"arxiv_id":"2402.08393","paper":"/paper/nfgtransformer-equivariant-representation","title":"NfgTransformer: Equivariant Representation Learning for Normal-form Games","date":null,"month_inferred_from_arxiv_id":"2024-02","title_source":"archive","repo":"google-deepmind/nfg_transformer","path":"nfg_transformer/network.py","file_url":"https://github.com/google-deepmind/nfg_transformer/blob/HEAD/nfg_transformer/network.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":"82aeead71a0a530e","mcp_get_code":{"code_sha256":"82aeead71a0a530e"}},{"arxiv_id":"2311.04434","paper":null,"title":"arXiv:2311.04434","date":null,"month_inferred_from_arxiv_id":"2023-11","title_source":null,"repo":"spatialdatasciencegroup/HST","path":"utils/bandLayers.py","file_url":"https://github.com/spatialdatasciencegroup/HST/blob/HEAD/utils/bandLayers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f9d57ee00ebe68a0","mcp_get_code":{"code_sha256":"f9d57ee00ebe68a0"}},{"arxiv_id":"2310.01690","paper":"/paper/forecasting-tropical-cyclones-with-cascaded","title":"Forecasting Tropical Cyclones with Cascaded Diffusion Models","date":"2023-10-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nathzi1505/forecast-diffmodels","path":"imagen/modules.py","file_url":"https://github.com/nathzi1505/forecast-diffmodels/blob/HEAD/imagen/modules.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9e6b6e12b1ec4d34","mcp_get_code":{"code_sha256":"9e6b6e12b1ec4d34"}},{"arxiv_id":"2309.11222","paper":"/paper/generalized-few-shot-point-cloud-segmentation","title":"Generalized Few-Shot Point Cloud Segmentation Via Geometric Words","date":"2023-09-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Pixie8888/GFS-3DSeg_GWs","path":"model/capl.py","file_url":"https://github.com/Pixie8888/GFS-3DSeg_GWs/blob/HEAD/model/capl.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2c362a2ad0aa0a9f","mcp_get_code":{"code_sha256":"2c362a2ad0aa0a9f"}},{"arxiv_id":"2308.08942","paper":"/paper/auxiliary-tasks-benefit-3d-skeleton-based","title":"Auxiliary Tasks Benefit 3D Skeleton-based Human Motion Prediction","date":"2023-08-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MediaBrain-SJTU/AuxFormer","path":"model/model.py","file_url":"https://github.com/MediaBrain-SJTU/AuxFormer/blob/HEAD/model/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"39d376502182d85a","mcp_get_code":{"code_sha256":"39d376502182d85a"}},{"arxiv_id":"2308.05095","paper":"/paper/layoutllm-t2i-eliciting-layout-guidance-from","title":"LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image Generation","date":"2023-08-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"layoutllm-t2i/layoutllm-t2i","path":"GLIGEN/ldm/modules/diffusionmodules/gligen_combine_layout.py","file_url":"https://github.com/layoutllm-t2i/layoutllm-t2i/blob/HEAD/GLIGEN/ldm/modules/diffusionmodules/gligen_combine_layout.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"35a9d16404c55eee","mcp_get_code":{"code_sha256":"35a9d16404c55eee"}},{"arxiv_id":"2306.15794","paper":"/paper/hyenadna-long-range-genomic-sequence-modeling","title":"HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution","date":"2023-06-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"frederikkemarin/bend","path":"bend/models/hyena_dna.py","file_url":"https://github.com/frederikkemarin/bend/blob/HEAD/bend/models/hyena_dna.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"f745e0dbcc9bb059","mcp_get_code":{"code_sha256":"f745e0dbcc9bb059"}},{"arxiv_id":"2306.07957","paper":"/paper/hidden-biases-of-end-to-end-driving-models","title":"Hidden Biases of End-to-End Driving Models","date":"2023-06-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"autonomousvision/carla_garage","path":"team_code/transfuser.py","file_url":"https://github.com/autonomousvision/carla_garage/blob/HEAD/team_code/transfuser.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"85cfd6ab309be0b8","mcp_get_code":{"code_sha256":"85cfd6ab309be0b8"}},{"arxiv_id":"2306.02006","paper":"/paper/ma2cl-masked-attentive-contrastive-learning","title":"MA2CL:Masked Attentive Contrastive Learning for Multi-Agent Reinforcement Learning","date":"2023-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ustchlsong/ma2cl","path":"algorithms/ma_transformer.py","file_url":"https://github.com/ustchlsong/ma2cl/blob/HEAD/algorithms/ma_transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4a5fcc8f9eab1543","mcp_get_code":{"code_sha256":"4a5fcc8f9eab1543"}},{"arxiv_id":"2209.00588","paper":"/paper/transformers-are-sample-efficient-world","title":"Transformers are Sample-Efficient World Models","date":"2022-09-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eloialonso/iris","path":"src/models/world_model.py","file_url":"https://github.com/eloialonso/iris/blob/HEAD/src/models/world_model.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":"f16fd90513419812","mcp_get_code":{"code_sha256":"f16fd90513419812"}},{"arxiv_id":"2203.13131","paper":"/paper/make-a-scene-scene-based-text-to-image","title":"Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors","date":"2022-03-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CasualGANPapers/Make-A-Scene","path":"models/transformer.py","file_url":"https://github.com/CasualGANPapers/Make-A-Scene/blob/HEAD/models/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"910b60593238b32f","mcp_get_code":{"code_sha256":"910b60593238b32f"}},{"arxiv_id":"2203.03825","paper":"/paper/incorporating-hierarchy-into-text-encoder-a","title":"Incorporating Hierarchy into Text Encoder: a Contrastive Learning Approach for Hierarchical Text Classification","date":"2022-03-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wzh9969/contrastive-htc","path":"model/contrast.py","file_url":"https://github.com/wzh9969/contrastive-htc/blob/HEAD/model/contrast.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"985ecde4944a60ab","mcp_get_code":{"code_sha256":"985ecde4944a60ab"}},{"arxiv_id":"2203.00867","paper":"/paper/incremental-transformer-structure-enhanced","title":"Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encoding","date":"2022-03-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DQiaole/ZITS_inpainting","path":"src/models/TSR_model.py","file_url":"https://github.com/DQiaole/ZITS_inpainting/blob/HEAD/src/models/TSR_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"96c2a9a4d1843cec","mcp_get_code":{"code_sha256":"96c2a9a4d1843cec"}},{"arxiv_id":"2202.00449","paper":"/paper/evaluating-feature-attribution-an-information","title":"A Consistent and Efficient Evaluation Strategy for Attribution Methods","date":"2022-02-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tleemann/road_evaluation","path":"road/road.py","file_url":"https://github.com/tleemann/road_evaluation/blob/HEAD/road/road.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b28b45f46cb768f9","mcp_get_code":{"code_sha256":"b28b45f46cb768f9"}},{"arxiv_id":"2112.04426","paper":"/paper/improving-language-models-by-retrieving-from","title":"Improving language models by retrieving from trillions of tokens","date":"2021-12-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"labmlai/annotated_deep_learning_paper_implementations","path":"labml_nn/transformers/retro/model.py","file_url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/HEAD/labml_nn/transformers/retro/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4c4fa4155f57fc48","mcp_get_code":{"code_sha256":"4c4fa4155f57fc48"}},{"arxiv_id":"2112.01641","paper":"/paper/hamiltonian-prior-to-disentangle-content-and","title":"Hamiltonian latent operators for content and motion disentanglement in image sequences","date":"2021-12-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mdasifkhan/halo","path":"model.py","file_url":"https://github.com/mdasifkhan/halo/blob/HEAD/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2c97c8872892a8f0","mcp_get_code":{"code_sha256":"2c97c8872892a8f0"}},{"arxiv_id":"2110.13214","paper":"/paper/iconqa-a-new-benchmark-for-abstract-diagram","title":"IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning","date":"2021-10-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lupantech/iconqa","path":"models/patch_transformer.py","file_url":"https://github.com/lupantech/iconqa/blob/HEAD/models/patch_transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b5225e9c0e0545db","mcp_get_code":{"code_sha256":"b5225e9c0e0545db"}},{"arxiv_id":"2108.12630","paper":"/paper/groupformer-group-activity-recognition-with","title":"GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal Transformer","date":"2021-08-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xueyee/GroupFormer","path":"group/models/cluster_transformer.py","file_url":"https://github.com/xueyee/GroupFormer/blob/HEAD/group/models/cluster_transformer.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":"76f9cb9ada2064dc","mcp_get_code":{"code_sha256":"76f9cb9ada2064dc"}},{"arxiv_id":"2107.14795","paper":"/paper/perceiver-io-a-general-architecture-for","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","date":"2021-07-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"esceptico/perceiver-io","path":"src/perceiver_io/perceiver.py","file_url":"https://github.com/esceptico/perceiver-io/blob/HEAD/src/perceiver_io/perceiver.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0a3f8489bfe3c981","mcp_get_code":{"code_sha256":"0a3f8489bfe3c981"}},{"arxiv_id":"2107.10060","paper":"/paper/cgans-with-auxiliary-discriminative","title":"Conditional GANs with Auxiliary Discriminative Classifier","date":"2021-07-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"POSTECH-CVLab/PyTorch-StudioGAN","path":"src/models/big_resnet_deep_studiogan.py","file_url":"https://github.com/POSTECH-CVLab/PyTorch-StudioGAN/blob/HEAD/src/models/big_resnet_deep_studiogan.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"a2f89876065d8307","mcp_get_code":{"code_sha256":"a2f89876065d8307"}},{"arxiv_id":"2106.11149","paper":"/paper/oadtr-online-action-detection-with","title":"OadTR: Online Action Detection with Transformers","date":"2021-06-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wangxiang1230/OadTR","path":"transformer_models/Transformer.py","file_url":"https://github.com/wangxiang1230/OadTR/blob/HEAD/transformer_models/Transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9c45f031bb45ad67","mcp_get_code":{"code_sha256":"9c45f031bb45ad67"}},{"arxiv_id":"2104.09224","paper":"/paper/multi-modal-fusion-transformer-for-end-to-end","title":"Multi-Modal Fusion Transformer for End-to-End Autonomous Driving","date":"2021-04-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Kin-Zhang/mmfn","path":"team_code/benchmarks/transfuser/model.py","file_url":"https://github.com/Kin-Zhang/mmfn/blob/HEAD/team_code/benchmarks/transfuser/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6141dbd1107c57fd","mcp_get_code":{"code_sha256":"6141dbd1107c57fd"}},{"arxiv_id":"2101.06635","paper":"/paper/context-aware-attentional-pooling-cap-for","title":"Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification","date":"2021-01-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ArdhenduBehera/cap","path":"SelfAttention.py","file_url":"https://github.com/ArdhenduBehera/cap/blob/HEAD/SelfAttention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6fa32f316d84dd85","mcp_get_code":{"code_sha256":"6fa32f316d84dd85"}},{"arxiv_id":"2010.11929","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"asyml/vision-transformer-pytorch","path":"src/model.py","file_url":"https://github.com/asyml/vision-transformer-pytorch/blob/HEAD/src/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"3dffc591a6481874","mcp_get_code":{"code_sha256":"3dffc591a6481874"}},{"arxiv_id":"2010.11929","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"s-chh/pytorch-scratch-vision-transformer-vit","path":"model.py","file_url":"https://github.com/s-chh/pytorch-scratch-vision-transformer-vit/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"af6edd8062f762fa","mcp_get_code":{"code_sha256":"af6edd8062f762fa"}},{"arxiv_id":"2010.03768","paper":"/paper/alfworld-aligning-text-and-embodied","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","date":"2020-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alfworld/alfworld","path":"alfworld/agents/modules/model.py","file_url":"https://github.com/alfworld/alfworld/blob/HEAD/alfworld/agents/modules/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4b8de7bded2e4118","mcp_get_code":{"code_sha256":"4b8de7bded2e4118"}},{"arxiv_id":"2006.15020","paper":"/paper/pre-training-via-paraphrasing","title":"Pre-training via Paraphrasing","date":"2020-06-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/marge-pytorch","path":"marge_pytorch/marge_pytorch.py","file_url":"https://github.com/lucidrains/marge-pytorch/blob/HEAD/marge_pytorch/marge_pytorch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2420acac5ce29a6d","mcp_get_code":{"code_sha256":"2420acac5ce29a6d"}},{"arxiv_id":"2006.11239","paper":"/paper/denoising-diffusion-probabilistic-models","title":"Denoising Diffusion Probabilistic Models","date":"2020-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CW-Huang/sdeflow-light","path":"lib/models/unet.py","file_url":"https://github.com/CW-Huang/sdeflow-light/blob/HEAD/lib/models/unet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"acc61062a727fa80","mcp_get_code":{"code_sha256":"acc61062a727fa80"}},{"arxiv_id":"2005.06312","paper":"/paper/reasoning-with-latent-structure-refinement","title":"Reasoning with Latent Structure Refinement for Document-Level Relation Extraction","date":"2020-05-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nanguoshun/LSR","path":"code/models/lsr.py","file_url":"https://github.com/nanguoshun/LSR/blob/HEAD/code/models/lsr.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9002f9968c2d49b3","mcp_get_code":{"code_sha256":"9002f9968c2d49b3"}},{"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":"ShivamRajSharma/Transformer-Architectures-From-Scratch","path":"BERT.py","file_url":"https://github.com/ShivamRajSharma/Transformer-Architectures-From-Scratch/blob/HEAD/BERT.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"64910f05f8cd9c7d","mcp_get_code":{"code_sha256":"64910f05f8cd9c7d"}},{"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":"benywon/ChineseBert","path":"model.py","file_url":"https://github.com/benywon/ChineseBert/blob/HEAD/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2fac2c94f3edf404","mcp_get_code":{"code_sha256":"2fac2c94f3edf404"}},{"arxiv_id":"1807.03819","paper":"/paper/universal-transformers","title":"Universal Transformers","date":"2018-07-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cfiken/universal_transformer","path":"model/ut.py","file_url":"https://github.com/cfiken/universal_transformer/blob/HEAD/model/ut.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"72219f63ad9d256a","mcp_get_code":{"code_sha256":"72219f63ad9d256a"}},{"arxiv_id":"1806.09055","paper":"/paper/darts-differentiable-architecture-search","title":"DARTS: Differentiable Architecture Search","date":"2018-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"anonNo2/MulTeacher-KD","path":"models/search_cnn.py","file_url":"https://github.com/anonNo2/MulTeacher-KD/blob/HEAD/models/search_cnn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"54e27a823121bcae","mcp_get_code":{"code_sha256":"54e27a823121bcae"}},{"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":"Wolfie8935/Implementation-of-Attention-is-all-you-need","path":"transformer_from_scratch.py","file_url":"https://github.com/Wolfie8935/Implementation-of-Attention-is-all-you-need/blob/HEAD/transformer_from_scratch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"59f151a9deed2bf4","mcp_get_code":{"code_sha256":"59f151a9deed2bf4"}},{"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":"EmilioTyl/transformers_from_scratch","path":"src/models/transformer_modules.py","file_url":"https://github.com/EmilioTyl/transformers_from_scratch/blob/HEAD/src/models/transformer_modules.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"138f04131e65c57b","mcp_get_code":{"code_sha256":"138f04131e65c57b"}},{"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":"jelifysh/Transformers","path":"transformers.py","file_url":"https://github.com/jelifysh/Transformers/blob/HEAD/transformers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7171816268dfd8f8","mcp_get_code":{"code_sha256":"7171816268dfd8f8"}},{"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":"adi2103/AML-CoVe","path":"NMT/Encoder.py","file_url":"https://github.com/adi2103/AML-CoVe/blob/HEAD/NMT/Encoder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"41081ea63abf65f1","mcp_get_code":{"code_sha256":"41081ea63abf65f1"}},{"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":"Rami97rgb/French-to-English-Translator","path":"model.py","file_url":"https://github.com/Rami97rgb/French-to-English-Translator/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":"4c8cf0d91eac07eb","mcp_get_code":{"code_sha256":"4c8cf0d91eac07eb"}},{"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":"sarthaxxxxx/Attention-is-all-you-need","path":"Transformer.py","file_url":"https://github.com/sarthaxxxxx/Attention-is-all-you-need/blob/HEAD/Transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4691e9b9cc4ba615","mcp_get_code":{"code_sha256":"4691e9b9cc4ba615"}},{"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":"souvikshanku/translit-former","path":"model.py","file_url":"https://github.com/souvikshanku/translit-former/blob/HEAD/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a8d02586f01c1fcd","mcp_get_code":{"code_sha256":"a8d02586f01c1fcd"}}]}