{"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/multiheadattention","entry":"MultiHeadAttention","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":124,"n_papers_ran":104,"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":191,"n_samples_ran":157,"n_samples_fingerprinted":40,"n_places":191,"n_places_pointer_only":90,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":157,"unverified":34},"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":"e8fb7d71d397d69a","mcp_get_code":{"code_sha256":"e8fb7d71d397d69a"}},{"arxiv_id":"2607.13164","paper":"/paper/arxiv-2607-13164","title":"Text2Sign: A Single-GPU Diffusion Baseline for Text-to-Sign Language Video Generation","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"xiaruize0911/text2sign","path":"pipeline.py","file_url":"https://github.com/xiaruize0911/text2sign/blob/HEAD/pipeline.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"293f6bb9a3443b33","mcp_get_code":{"code_sha256":"293f6bb9a3443b33"}},{"arxiv_id":"2607.13103","paper":"/paper/arxiv-2607-13103","title":"Disentangling Knowledge States with Ability and Proficiency Modeling for Knowledge Tracing","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"ThaliaBee/PAKT","path":"models/pakt.py","file_url":"https://github.com/ThaliaBee/PAKT/blob/HEAD/models/pakt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6da5bc6eb1a67242","mcp_get_code":{"code_sha256":"6da5bc6eb1a67242"}},{"arxiv_id":"2607.11656","paper":"/paper/arxiv-2607-11656","title":"Imputation-free transformer learning enables robust Alzheimer's disease prediction and calibrated uncertainty quantification across heterogeneous clinical cohorts","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"cschneuw/nitrogen","path":"src/model/naim.py","file_url":"https://github.com/cschneuw/nitrogen/blob/HEAD/src/model/naim.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ec74803c9714475b","mcp_get_code":{"code_sha256":"ec74803c9714475b"}},{"arxiv_id":"2606.30875","paper":"/paper/arxiv-2606-30875","title":"The Label Imitation Game: Turing Test Network for Zero-Shot Pseudo-Label Pruning","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"voxel51/ttn","path":"ttn/ttn_model.py","file_url":"https://github.com/voxel51/ttn/blob/HEAD/ttn/ttn_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b6dacbbedec24e56","mcp_get_code":{"code_sha256":"b6dacbbedec24e56"}},{"arxiv_id":"2606.00081","paper":"/paper/arxiv-2606-00081","title":"DAStatFormer: A Hybrid Multibranch Transformer with Statistical Feature Integration for DAS-Based Pattern Recognitions","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"MichelD-git/DAStatFormer","path":"DAStatFomer.py","file_url":"https://github.com/MichelD-git/DAStatFormer/blob/HEAD/DAStatFomer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9ef1094e7a165682","mcp_get_code":{"code_sha256":"9ef1094e7a165682"}},{"arxiv_id":"2605.28209","paper":"/paper/arxiv-2605-28209","title":"Robust Contrastive Graph Clustering with Adaptive Local-Global Integration","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"vege12138/w2","path":"model.py","file_url":"https://github.com/vege12138/w2/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":"da82440b0808f767","mcp_get_code":{"code_sha256":"da82440b0808f767"}},{"arxiv_id":"2605.26502","paper":"/paper/arxiv-2605-26502","title":"PRISM: Position-encoded Regressive Inverse Spectral Model for Multilayer Thin-Film Design","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"wang-henry4/prism","path":"prism/model/prefix_material_thk_model.py","file_url":"https://github.com/wang-henry4/prism/blob/HEAD/prism/model/prefix_material_thk_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"69d7cf87d5434b4c","mcp_get_code":{"code_sha256":"69d7cf87d5434b4c"}},{"arxiv_id":"2605.13672","paper":"/paper/arxiv-2605-13672","title":"SpurAudio: A Benchmark for Studying Shortcut Learning in Few-Shot Audio Classification","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"Jerryaa98/SpurAudio","path":"libfewshot_core/model/metric/feat.py","file_url":"https://github.com/Jerryaa98/SpurAudio/blob/HEAD/libfewshot_core/model/metric/feat.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"abb0132a11948e66","mcp_get_code":{"code_sha256":"abb0132a11948e66"}},{"arxiv_id":"2604.19368","paper":"/paper/arxiv-2604-19368","title":"Mind2Drive: Predicting Driver Intentions from EEG in Real-world On-Road Driving","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"galosaimi/Mind2Drive","path":"models/eegconformer.py","file_url":"https://github.com/galosaimi/Mind2Drive/blob/HEAD/models/eegconformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bc4ae1ad1876dd20","mcp_get_code":{"code_sha256":"bc4ae1ad1876dd20"}},{"arxiv_id":"2603.26515","paper":"/paper/arxiv-2603-26515","title":"JAL-Turn: Joint Acoustic-Linguistic Modeling for Real-Time and Robust Turn-Taking Detection in Full-Duplex Spoken Dialogue Systems","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"inokoj/VAP-Realtime","path":"vap_realtime/model.py","file_url":"https://github.com/inokoj/VAP-Realtime/blob/HEAD/vap_realtime/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"77041e75fb11ebf7","mcp_get_code":{"code_sha256":"77041e75fb11ebf7"}},{"arxiv_id":"2603.24366","paper":"/paper/arxiv-2603-24366","title":"CoordLight: Learning Decentralized Coordination for Network-Wide Traffic Signal Control","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"marmotlab/CoordLight","path":"Models/CoordLightModel.py","file_url":"https://github.com/marmotlab/CoordLight/blob/HEAD/Models/CoordLightModel.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a76fb898ce3994a8","mcp_get_code":{"code_sha256":"a76fb898ce3994a8"}},{"arxiv_id":"2602.16914","paper":"/paper/arxiv-2602-16914","title":"A statistical perspective on transformers for small longitudinal cohort data","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"kianaf/MiniTransformer","path":"src/transformers.py","file_url":"https://github.com/kianaf/MiniTransformer/blob/HEAD/src/transformers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f47429e7508e10fd","mcp_get_code":{"code_sha256":"f47429e7508e10fd"}},{"arxiv_id":"2602.00596","paper":"/paper/arxiv-2602-00596","title":"Kernelized Edge Attention: Addressing Semantic Attention Blurring in Temporal Graph Neural Networks","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"yule-BUAA/DyGLib","path":"models/modules.py","file_url":"https://github.com/yule-BUAA/DyGLib/blob/HEAD/models/modules.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d6264ffe9f545d50","mcp_get_code":{"code_sha256":"d6264ffe9f545d50"}},{"arxiv_id":"2601.21948","paper":"/paper/arxiv-2601-21948","title":"Deep Models, Shallow Alignment: Uncovering the Granularity Mismatch in Neural Decoding","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"yangdu-neuroai/shallow-alignment","path":"module/eeg_encoder/model.py","file_url":"https://github.com/yangdu-neuroai/shallow-alignment/blob/HEAD/module/eeg_encoder/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4a2c161d1b6b9637","mcp_get_code":{"code_sha256":"4a2c161d1b6b9637"}},{"arxiv_id":"2601.20072","paper":"/paper/arxiv-2601-20072","title":"Semi-Supervised Masked Autoencoders: Unlocking Vision Transformer Potential with Limited Data","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"atik666/ssmae","path":"ssmae.py","file_url":"https://github.com/atik666/ssmae/blob/HEAD/ssmae.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a68b851d53be71ff","mcp_get_code":{"code_sha256":"a68b851d53be71ff"}},{"arxiv_id":"2510.23577","paper":"/paper/arxiv-2510-23577","title":"TAMI: Taming Heterogeneity in Temporal Interactions for Temporal Graph Link Prediction","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"Alleinx/TAMI_temporal_graph","path":"models/MemoryModel.py","file_url":"https://github.com/Alleinx/TAMI_temporal_graph/blob/HEAD/models/MemoryModel.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7ff8165c5ece0ae5","mcp_get_code":{"code_sha256":"7ff8165c5ece0ae5"}},{"arxiv_id":"2510.23295","paper":"/paper/arxiv-2510-23295","title":"Predicting symbolic ODEs from multiple trajectories","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"yakupemresahin/mio","path":"mio/model/transformer.py","file_url":"https://github.com/yakupemresahin/mio/blob/HEAD/mio/model/transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e6e3f83e5cfd62a2","mcp_get_code":{"code_sha256":"e6e3f83e5cfd62a2"}},{"arxiv_id":"2510.08445","paper":"/paper/arxiv-2510-08445","title":"Synthetic Series-Symbol Data Generation for Time Series Foundation Models","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"wwhenxuan/SymTime","path":"models/pretrain_model.py","file_url":"https://github.com/wwhenxuan/SymTime/blob/HEAD/models/pretrain_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"394f2672bffaba81","mcp_get_code":{"code_sha256":"394f2672bffaba81"}},{"arxiv_id":"2509.01200","paper":"/paper/arxiv-2509-01200","title":"SimulMEGA: MoE Routers are Advanced Policy Makers for Simultaneous Speech Translation","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"nethermanpro/simulmega","path":"models/simulmegastt/net/decoder.py","file_url":"https://github.com/nethermanpro/simulmega/blob/HEAD/models/simulmegastt/net/decoder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"077f5e16f8652ee7","mcp_get_code":{"code_sha256":"077f5e16f8652ee7"}},{"arxiv_id":"2508.16112","paper":"/paper/arxiv-2508-16112","title":"IR-Agent: Expert-Inspired LLM Agents for Structure Elucidation from Infrared Spectra","date":null,"month_inferred_from_arxiv_id":"2025-08","title_source":"syntology","repo":"HeewoongNoh/IR-Agent","path":"models/translator.py","file_url":"https://github.com/HeewoongNoh/IR-Agent/blob/HEAD/models/translator.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c162facec10d46c9","mcp_get_code":{"code_sha256":"c162facec10d46c9"}},{"arxiv_id":"2507.00880","paper":null,"title":"arXiv:2507.00880","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"XuRuihan/NNFormer","path":"neuralformer/models/encoders/neuralformer.py","file_url":"https://github.com/XuRuihan/NNFormer/blob/HEAD/neuralformer/models/encoders/neuralformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"812fc3e634d85df9","mcp_get_code":{"code_sha256":"812fc3e634d85df9"}},{"arxiv_id":"2506.13366","paper":"/paper/enhancing-goal-oriented-proactive-dialogue","title":"Enhancing Goal-oriented Proactive Dialogue Systems via Consistency Reflection and Correction","date":"2025-06-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhyidi/CRC","path":"model/Planner.py","file_url":"https://github.com/zhyidi/CRC/blob/HEAD/model/Planner.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":"b05865273b70e31c","mcp_get_code":{"code_sha256":"b05865273b70e31c"}},{"arxiv_id":"2506.09215","paper":null,"title":"arXiv:2506.09215","date":null,"month_inferred_from_arxiv_id":"2025-06","title_source":null,"repo":"agbrothers/pooling","path":"pooling/nn/pool.py","file_url":"https://github.com/agbrothers/pooling/blob/HEAD/pooling/nn/pool.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f2903d3479df3a54","mcp_get_code":{"code_sha256":"f2903d3479df3a54"}},{"arxiv_id":"2505.17114","paper":"/paper/raven-query-guided-representation-alignment","title":"RAVEN: Query-Guided Representation Alignment for Question Answering over Audio, Video, Embedded Sensors, and Natural Language","date":"2025-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"BASHLab/RAVEN","path":"raven/model/allignment.py","file_url":"https://github.com/BASHLab/RAVEN/blob/HEAD/raven/model/allignment.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"code_sha256_prefix":"83b8dabfd5c880c8","mcp_get_code":{"code_sha256":"83b8dabfd5c880c8"}},{"arxiv_id":"2505.13489","paper":"/paper/contrastive-cross-course-knowledge-tracing","title":"Contrastive Cross-Course Knowledge Tracing via Concept Graph Guided Knowledge Transfer","date":"2025-05-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DQYZHWK/TransKT","path":"model/TransKT.py","file_url":"https://github.com/DQYZHWK/TransKT/blob/HEAD/model/TransKT.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7f49a12274975f04","mcp_get_code":{"code_sha256":"7f49a12274975f04"}},{"arxiv_id":"2505.10289","paper":"/paper/msci-addressing-clip-s-inherent-limitations","title":"MSCI: Addressing CLIP's Inherent Limitations for Compositional Zero-Shot Learning","date":"2025-05-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ltpwy/MSCI","path":"MSCI/code/model/Mutifuse_new.py","file_url":"https://github.com/ltpwy/MSCI/blob/HEAD/MSCI/code/model/Mutifuse_new.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4ec77f7241f49ff4","mcp_get_code":{"code_sha256":"4ec77f7241f49ff4"}},{"arxiv_id":"2504.16275","paper":"/paper/quantum-doubly-stochastic-transformers","title":"Quantum Doubly Stochastic Transformers","date":"2025-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"michaelsdr/sinkformers","path":"nlp-tutorial/text-classification-transformer/model_sym.py","file_url":"https://github.com/michaelsdr/sinkformers/blob/HEAD/nlp-tutorial/text-classification-transformer/model_sym.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5bcf16df9e4b0c26","mcp_get_code":{"code_sha256":"5bcf16df9e4b0c26"}},{"arxiv_id":"2503.13012","paper":"/paper/test-time-domain-generalization-via-universe","title":"Test-Time Domain Generalization via Universe Learning: A Multi-Graph Matching Approach for Medical Image Segmentation","date":"2025-03-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Yore0/TTDG-MGM","path":"adapteacher/modeling/GModule/multi_graph_matching.py","file_url":"https://github.com/Yore0/TTDG-MGM/blob/HEAD/adapteacher/modeling/GModule/multi_graph_matching.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"379e1862072096af","mcp_get_code":{"code_sha256":"379e1862072096af"}},{"arxiv_id":"2503.04151","paper":null,"title":"arXiv:2503.04151","date":null,"month_inferred_from_arxiv_id":"2025-03","title_source":null,"repo":"SubmissionsIn/RML","path":"RML+NRCH/RML_network.py","file_url":"https://github.com/SubmissionsIn/RML/blob/HEAD/RML%2BNRCH/RML_network.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0184227dae2b2a3a","mcp_get_code":{"code_sha256":"0184227dae2b2a3a"}},{"arxiv_id":"2503.00205","paper":"/paper/analoggenie-a-generative-engine-for-automatic","title":"AnalogGenie: A Generative Engine for Automatic Discovery of Analog Circuit Topologies","date":"2025-02-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xz-group/analoggenie","path":"Models/GPT.py","file_url":"https://github.com/xz-group/analoggenie/blob/HEAD/Models/GPT.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"06e29fbb537270a7","mcp_get_code":{"code_sha256":"06e29fbb537270a7"}},{"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":"9af23750c4257a47","mcp_get_code":{"code_sha256":"9af23750c4257a47"}},{"arxiv_id":"2411.19451","paper":"/paper/learning-visual-abstract-reasoning-through","title":"Learning Visual Abstract Reasoning through Dual-Stream Networks","date":"2024-11-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VecchioID/DRNet","path":"src/model.py","file_url":"https://github.com/VecchioID/DRNet/blob/HEAD/src/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7759c8c62ae8eedd","mcp_get_code":{"code_sha256":"7759c8c62ae8eedd"}},{"arxiv_id":"2411.17296","paper":"/paper/grokformer-graph-fourier-kolmogorov-arnold","title":"GrokFormer: Graph Fourier Kolmogorov-Arnold Transformers","date":"2024-11-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"GGA23/GrokFormer","path":"model.py","file_url":"https://github.com/GGA23/GrokFormer/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":"1d0b74e95a6795a0","mcp_get_code":{"code_sha256":"1d0b74e95a6795a0"}},{"arxiv_id":"2411.02063","paper":"/paper/scalable-efficient-training-of-large-language","title":"Scalable Efficient Training of Large Language Models with Low-dimensional Projected Attention","date":"2024-11-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TsinghuaC3I/LPA","path":"architecture/lpa_setting1.py","file_url":"https://github.com/TsinghuaC3I/LPA/blob/HEAD/architecture/lpa_setting1.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fa104895b67665ee","mcp_get_code":{"code_sha256":"fa104895b67665ee"}},{"arxiv_id":"2410.16432","paper":"/paper/fair-bilevel-neural-network-fairbinn-on","title":"Fair Bilevel Neural Network (FairBiNN): On Balancing fairness and accuracy via Stackelberg Equilibrium","date":"2024-10-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yazdanimehdi/Distraction_Fairness","path":"model.py","file_url":"https://github.com/yazdanimehdi/Distraction_Fairness/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":"687fd6594c87ed5b","mcp_get_code":{"code_sha256":"687fd6594c87ed5b"}},{"arxiv_id":"2410.14970","paper":"/paper/taming-the-long-tail-in-human-mobility","title":"Taming the Long Tail in Human Mobility Prediction","date":"2024-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yukayo/lotnext","path":"network.py","file_url":"https://github.com/yukayo/lotnext/blob/HEAD/network.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"71ea19393168127b","mcp_get_code":{"code_sha256":"71ea19393168127b"}},{"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":"63814a6938fa994f","mcp_get_code":{"code_sha256":"63814a6938fa994f"}},{"arxiv_id":"2410.05711","paper":"/paper/diffusion-auto-regressive-transformer-for","title":"Diffusion Auto-regressive Transformer for Effective Self-supervised Time Series Forecasting","date":"2024-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mingyue-cheng/timemae","path":"model/TimeMAE.py","file_url":"https://github.com/mingyue-cheng/timemae/blob/HEAD/model/TimeMAE.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c81e84e4981f1c79","mcp_get_code":{"code_sha256":"c81e84e4981f1c79"}},{"arxiv_id":"2406.15079","paper":"/paper/goal-a-generalist-combinatorial-optimization","title":"GOAL: A Generalist Combinatorial Optimization Agent Learning","date":"2024-06-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"naver/goal-co","path":"model/goal.py","file_url":"https://github.com/naver/goal-co/blob/HEAD/model/goal.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"2bd36da6a44d602c","mcp_get_code":{"code_sha256":"2bd36da6a44d602c"}},{"arxiv_id":"2406.12454","paper":"/paper/a-neural-column-generation-approach-to-the","title":"A Neural Column Generation Approach to the Vehicle Routing Problem with Two-Dimensional Loading and Last-In-First-Out Constraints","date":"2024-06-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xyfffff/NCG-for-2L-CVRP","path":"bpp/model.py","file_url":"https://github.com/xyfffff/NCG-for-2L-CVRP/blob/HEAD/bpp/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"337e597194195937","mcp_get_code":{"code_sha256":"337e597194195937"}},{"arxiv_id":"2406.02066","paper":"/paper/preference-optimization-for-molecule","title":"Preference Optimization for Molecule Synthesis with Conditional Residual Energy-based Models","date":"2024-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"songtaoliu0823/crebm","path":"Energy_function/reward_model.py","file_url":"https://github.com/songtaoliu0823/crebm/blob/HEAD/Energy_function/reward_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"35b3f91bfff1f5ce","mcp_get_code":{"code_sha256":"35b3f91bfff1f5ce"}},{"arxiv_id":"2405.01102","paper":"/paper/less-is-more-on-the-over-globalizing-problem","title":"Less is More: on the Over-Globalizing Problem in Graph Transformers","date":"2024-05-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"null-xyj/CoBFormer","path":"Model/CoBFormer.py","file_url":"https://github.com/null-xyj/CoBFormer/blob/HEAD/Model/CoBFormer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bd341cc57b38b439","mcp_get_code":{"code_sha256":"bd341cc57b38b439"}},{"arxiv_id":"2404.11677","paper":"/paper/cross-problem-learning-for-solving-vehicle","title":"Cross-Problem Learning for Solving Vehicle Routing Problems","date":"2024-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhuoyi-lin/cross_problem_learning","path":"nets/attention_model.py","file_url":"https://github.com/zhuoyi-lin/cross_problem_learning/blob/HEAD/nets/attention_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"95828c36546886bb","mcp_get_code":{"code_sha256":"95828c36546886bb"}},{"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":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"674faf0dd21654ff","mcp_get_code":{"code_sha256":"674faf0dd21654ff"}},{"arxiv_id":"2404.04557","paper":"/paper/learning-instance-aware-correspondences-for","title":"Learning Instance-Aware Correspondences for Robust Multi-Instance Point Cloud Registration in Cluttered Scenes","date":"2024-04-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhiyuanYU134/MIRETR","path":"release/robi/modules.py","file_url":"https://github.com/zhiyuanYU134/MIRETR/blob/HEAD/release/robi/modules.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9f1df744c0d81699","mcp_get_code":{"code_sha256":"9f1df744c0d81699"}},{"arxiv_id":"2403.16030","paper":"/paper/vcr-graphormer-a-mini-batch-graph-transformer","title":"VCR-Graphormer: A Mini-batch Graph Transformer via Virtual Connections","date":"2024-03-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dongqifu/vcr-graphormer","path":"model.py","file_url":"https://github.com/dongqifu/vcr-graphormer/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"454c624c34ba637e","mcp_get_code":{"code_sha256":"454c624c34ba637e"}},{"arxiv_id":"2403.00272","paper":"/paper/dual-pose-invariant-embeddings-learning","title":"Dual Pose-invariant Embeddings: Learning Category and Object-specific Discriminative Representations for Recognition and Retrieval","date":"2024-03-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sarkar-rohan/PiRO","path":"models/VGG_PAN_DualEmb.py","file_url":"https://github.com/sarkar-rohan/PiRO/blob/HEAD/models/VGG_PAN_DualEmb.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"09b7cfcfd7541ffa","mcp_get_code":{"code_sha256":"09b7cfcfd7541ffa"}},{"arxiv_id":"2402.15591","paper":"/paper/recwizard-a-toolkit-for-conversational","title":"RecWizard: A Toolkit for Conversational Recommendation with Modular, Portable Models and Interactive User Interface","date":"2024-02-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"McAuley-Lab/RecWizard","path":"src/recwizard/modules/kbrd/transformer_encoder_decoder.py","file_url":"https://github.com/McAuley-Lab/RecWizard/blob/HEAD/src/recwizard/modules/kbrd/transformer_encoder_decoder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0b78ef53aedd3d00","mcp_get_code":{"code_sha256":"0b78ef53aedd3d00"}},{"arxiv_id":"2401.10211","paper":"/paper/improving-ptm-site-prediction-by-coupling-of","title":"Improving PTM Site Prediction by Coupling of Multi-Granularity Structure and Multi-Scale Sequence Representation","date":"2024-01-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LZY-HZAU/PTM-CMGMS","path":"Codes/Multi-scale-Sequence/model_MS.py","file_url":"https://github.com/LZY-HZAU/PTM-CMGMS/blob/HEAD/Codes/Multi-scale-Sequence/model_MS.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4c8805e187b92022","mcp_get_code":{"code_sha256":"4c8805e187b92022"}},{"arxiv_id":"2401.08567","paper":"/paper/connect-collapse-corrupt-learning-cross-modal","title":"Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data","date":"2024-01-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuhui-zh15/c3","path":"image_captioning/src/models/transformer_mapper.py","file_url":"https://github.com/yuhui-zh15/c3/blob/HEAD/image_captioning/src/models/transformer_mapper.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d65ab89c7116c485","mcp_get_code":{"code_sha256":"d65ab89c7116c485"}},{"arxiv_id":"2401.02292","paper":"/paper/gridformer-point-grid-transformer-for-surface","title":"GridFormer: Point-Grid Transformer for Surface Reconstruction","date":"2024-01-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"list17/GridFormer","path":"src/transformer.py","file_url":"https://github.com/list17/GridFormer/blob/HEAD/src/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"45b7b846b99a837c","mcp_get_code":{"code_sha256":"45b7b846b99a837c"}},{"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":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c1c52814e8545858","mcp_get_code":{"code_sha256":"c1c52814e8545858"}},{"arxiv_id":"2307.16525","paper":"/paper/transferable-decoding-with-visual-entities","title":"Transferable Decoding with Visual Entities for Zero-Shot Image Captioning","date":"2023-07-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"feielysia/viecap","path":"ClipCap.py","file_url":"https://github.com/feielysia/viecap/blob/HEAD/ClipCap.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d8ba41633b35c84c","mcp_get_code":{"code_sha256":"d8ba41633b35c84c"}},{"arxiv_id":"2307.10543","paper":"/paper/trea-tree-structure-reasoning-schema-for","title":"TREA: Tree-Structure Reasoning Schema for Conversational Recommendation","date":"2023-07-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"WindyLee0822/TREA","path":"model.py","file_url":"https://github.com/WindyLee0822/TREA/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4e16ff3a8e66caae","mcp_get_code":{"code_sha256":"4e16ff3a8e66caae"}},{"arxiv_id":"2306.11641","paper":"/paper/salsa-verde-a-machine-learning-attack-on","title":"SALSA VERDE: a machine learning attack on Learning With Errors with sparse small secrets","date":null,"month_inferred_from_arxiv_id":"2023-06","title_source":"archive","repo":"facebookresearch/verde","path":"src/train/model/transformer.py","file_url":"https://github.com/facebookresearch/verde/blob/HEAD/src/train/model/transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"4385a5e689c16e41","mcp_get_code":{"code_sha256":"4385a5e689c16e41"}},{"arxiv_id":"2305.06588","paper":"/paper/hahe-hierarchical-attention-for-hyper","title":"HAHE: Hierarchical Attention for Hyper-Relational Knowledge Graphs in Global and Local Level","date":"2023-05-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lhrlab/hahe","path":"src/transformer.py","file_url":"https://github.com/lhrlab/hahe/blob/HEAD/src/transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"85383a26407bef78","mcp_get_code":{"code_sha256":"85383a26407bef78"}},{"arxiv_id":"2304.11855","paper":"/paper/glocal-energy-based-learning-for-few-shot","title":"Glocal Energy-based Learning for Few-Shot Open-Set Recognition","date":"2023-04-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"00why00/glocal","path":"model/models/glocal_energy.py","file_url":"https://github.com/00why00/glocal/blob/HEAD/model/models/glocal_energy.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a45b4e485260a65b","mcp_get_code":{"code_sha256":"a45b4e485260a65b"}},{"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":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c06cdab10d27718a","mcp_get_code":{"code_sha256":"c06cdab10d27718a"}},{"arxiv_id":"2304.00195","paper":"/paper/abstractors-transformer-modules-for-symbolic","title":"Abstractors and relational cross-attention: An inductive bias for explicit relational reasoning in Transformers","date":"2023-04-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"awni00/abstractor","path":"abstracters.py","file_url":"https://github.com/awni00/abstractor/blob/HEAD/abstracters.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"2159f6374bdb0366","mcp_get_code":{"code_sha256":"2159f6374bdb0366"}},{"arxiv_id":"2303.15343","paper":"/paper/sigmoid-loss-for-language-image-pre-training","title":"Sigmoid Loss for Language Image Pre-Training","date":"2023-03-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"apple/ml-mobileclip","path":"mobileclip/clip.py","file_url":"https://github.com/apple/ml-mobileclip/blob/HEAD/mobileclip/clip.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"88f8bcf4b76c2844","mcp_get_code":{"code_sha256":"88f8bcf4b76c2844"}},{"arxiv_id":"2303.13014","paper":"/paper/semantic-ray-learning-a-generalizable","title":"Semantic Ray: Learning a Generalizable Semantic Field with Cross-Reprojection Attention","date":"2023-03-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liuff19/Semantic-Ray","path":"network/cranet.py","file_url":"https://github.com/liuff19/Semantic-Ray/blob/HEAD/network/cranet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4b49c3776169984f","mcp_get_code":{"code_sha256":"4b49c3776169984f"}},{"arxiv_id":"2303.09268","paper":"/paper/stylerdalle-language-guided-style-transfer","title":"StylerDALLE: Language-Guided Style Transfer Using a Vector-Quantized Tokenizer of a Large-Scale Generative Model","date":"2023-03-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zipengxuc/StylerDALLE","path":"module.py","file_url":"https://github.com/zipengxuc/StylerDALLE/blob/HEAD/module.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2dc27bff063bb4e6","mcp_get_code":{"code_sha256":"2dc27bff063bb4e6"}},{"arxiv_id":"2303.07180","paper":"/paper/incomplete-multi-view-multi-label-learning","title":"Incomplete Multi-View Multi-Label Learning via Label-Guided Masked View- and Category-Aware Transformers","date":"2023-03-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"justsmart/LMVCAT","path":"model.py","file_url":"https://github.com/justsmart/LMVCAT/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"58b02854368e8532","mcp_get_code":{"code_sha256":"58b02854368e8532"}},{"arxiv_id":"2303.06833","paper":"/paper/transformer-based-planning-for-symbolic-1","title":"Transformer-based Planning for Symbolic Regression","date":"2023-03-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"deep-symbolic-mathematics/TPSR","path":"symbolicregression/model/transformer.py","file_url":"https://github.com/deep-symbolic-mathematics/TPSR/blob/HEAD/symbolicregression/model/transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f9946efd274ff9ea","mcp_get_code":{"code_sha256":"f9946efd274ff9ea"}},{"arxiv_id":"2303.05095","paper":"/paper/trajectory-aware-body-interaction-transformer","title":"Trajectory-Aware Body Interaction Transformer for Multi-Person Pose Forecasting","date":"2023-03-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xiaogangpeng/tbiformer","path":"models/net.py","file_url":"https://github.com/xiaogangpeng/tbiformer/blob/HEAD/models/net.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b6adf32d225922b6","mcp_get_code":{"code_sha256":"b6adf32d225922b6"}},{"arxiv_id":"2302.11814","paper":"/paper/ftm-a-frame-level-timeline-modeling-method","title":"FTM: A Frame-level Timeline Modeling Method for Temporal Graph Representation Learning","date":"2023-02-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yeeeqichen/FTM","path":"modules/timeline.py","file_url":"https://github.com/yeeeqichen/FTM/blob/HEAD/modules/timeline.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"550ffe32f6af1edb","mcp_get_code":{"code_sha256":"550ffe32f6af1edb"}},{"arxiv_id":"2302.06881","paper":"/paper/simplekt-a-simple-but-tough-to-beat-baseline","title":"simpleKT: A Simple But Tough-to-Beat Baseline for Knowledge Tracing","date":"2023-02-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pykt-team/pykt-toolkit","path":"pykt/models/simplekt.py","file_url":"https://github.com/pykt-team/pykt-toolkit/blob/HEAD/pykt/models/simplekt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a9a73e8f8da578a5","mcp_get_code":{"code_sha256":"a9a73e8f8da578a5"}},{"arxiv_id":"2301.03160","paper":"/paper/towards-real-time-panoptic-narrative","title":"Towards Real-Time Panoptic Narrative Grounding by an End-to-End Grounding Network","date":"2023-01-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Mr-Neko/EPNG","path":"models/EPNG/MainModule.py","file_url":"https://github.com/Mr-Neko/EPNG/blob/HEAD/models/EPNG/MainModule.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e078fed1456dc142","mcp_get_code":{"code_sha256":"e078fed1456dc142"}},{"arxiv_id":"2210.03930","paper":"/paper/hierarchical-graph-transformer-with-adaptive","title":"Hierarchical Graph Transformer with Adaptive Node Sampling","date":"2022-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zaixizhang/ans-gt","path":"model.py","file_url":"https://github.com/zaixizhang/ans-gt/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":"ef6e8c582a751d85","mcp_get_code":{"code_sha256":"ef6e8c582a751d85"}},{"arxiv_id":"2210.01753","paper":"/paper/hypro-a-hybridly-normalized-probabilistic","title":"HYPRO: A Hybridly Normalized Probabilistic Model for Long-Horizon Prediction of Event Sequences","date":"2022-10-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ant-research/hypro_tpp","path":"hypro_tpp/models/xfmr_nhp_fast.py","file_url":"https://github.com/ant-research/hypro_tpp/blob/HEAD/hypro_tpp/models/xfmr_nhp_fast.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":"8f782f28d3d8e855","mcp_get_code":{"code_sha256":"8f782f28d3d8e855"}},{"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":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7ebfdb4decdd2967","mcp_get_code":{"code_sha256":"7ebfdb4decdd2967"}},{"arxiv_id":"2209.15200","paper":"/paper/an-efficient-encoder-decoder-architecture","title":"An efficient encoder-decoder architecture with top-down attention for speech separation","date":"2022-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JusperLee/TDANet","path":"look2hear/models/TDANet.py","file_url":"https://github.com/JusperLee/TDANet/blob/HEAD/look2hear/models/TDANet.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":"62e9ea75f34de78d","mcp_get_code":{"code_sha256":"62e9ea75f34de78d"}},{"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":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c1f7ea6657c382e1","mcp_get_code":{"code_sha256":"c1f7ea6657c382e1"}},{"arxiv_id":"2207.08625","paper":"/paper/unifying-event-detection-and-captioning-as","title":"Unifying Event Detection and Captioning as Sequence Generation via Pre-Training","date":"2022-07-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"QiQAng/UEDVC","path":"modules/transformer.py","file_url":"https://github.com/QiQAng/UEDVC/blob/HEAD/modules/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e2fd5904ba4c6794","mcp_get_code":{"code_sha256":"e2fd5904ba4c6794"}},{"arxiv_id":"2207.06652","paper":"/paper/every-preference-changes-differently-neural","title":"Everyone's Preference Changes Differently: Weighted Multi-Interest Retrieval Model","date":"2022-07-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shihui2010/mip","path":"modules/named_models.py","file_url":"https://github.com/shihui2010/mip/blob/HEAD/modules/named_models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"208c6661bc2229c7","mcp_get_code":{"code_sha256":"208c6661bc2229c7"}},{"arxiv_id":"2207.02206","paper":"/paper/segmenting-moving-objects-via-an-object","title":"Segmenting Moving Objects via an Object-Centric Layered Representation","date":"2022-07-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Jyxarthur/OCLR_model","path":"models/oclr.py","file_url":"https://github.com/Jyxarthur/OCLR_model/blob/HEAD/models/oclr.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a447981fffd42b39","mcp_get_code":{"code_sha256":"a447981fffd42b39"}},{"arxiv_id":"2206.00888","paper":"/paper/squeezeformer-an-efficient-transformer-for","title":"Squeezeformer: An Efficient Transformer for Automatic Speech Recognition","date":"2022-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kssteven418/squeezeformer","path":"src/models/conformer_encoder.py","file_url":"https://github.com/kssteven418/squeezeformer/blob/HEAD/src/models/conformer_encoder.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":"7d7f63e024f22b4b","mcp_get_code":{"code_sha256":"7d7f63e024f22b4b"}},{"arxiv_id":"2205.13225","paper":"/paper/collaborative-distillation-meta-learning-for","title":"DevFormer: A Symmetric Transformer for Context-Aware Device Placement","date":"2022-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kaist-silab/dppbench","path":"src/models/devformer.py","file_url":"https://github.com/kaist-silab/dppbench/blob/HEAD/src/models/devformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b1e65318aee81d61","mcp_get_code":{"code_sha256":"b1e65318aee81d61"}},{"arxiv_id":"2204.04179","paper":"/paper/gram-fast-fine-tuning-of-pre-trained-language","title":"GRAM: Fast Fine-tuning of Pre-trained Language Models for Content-based Collaborative Filtering","date":"2022-04-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yoonseok312/GRAM","path":"gram/news_recommendation/model_bert.py","file_url":"https://github.com/yoonseok312/GRAM/blob/HEAD/gram/news_recommendation/model_bert.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a8fe4d06671859f3","mcp_get_code":{"code_sha256":"a8fe4d06671859f3"}},{"arxiv_id":"2204.01696","paper":"/paper/joint-hand-motion-and-interaction-hotspots","title":"Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos","date":"2022-04-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"stevenlsw/hoi-forecast","path":"networks/transformer.py","file_url":"https://github.com/stevenlsw/hoi-forecast/blob/HEAD/networks/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a9bbf45f116e8c1a","mcp_get_code":{"code_sha256":"a9bbf45f116e8c1a"}},{"arxiv_id":"2203.15350","paper":"/paper/end-to-end-transformer-based-model-for-image","title":"End-to-End Transformer Based Model for Image Captioning","date":"2022-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jchenghu/expansionnet_v2","path":"models/End_ExpansionNet_v2.py","file_url":"https://github.com/jchenghu/expansionnet_v2/blob/HEAD/models/End_ExpansionNet_v2.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ac6767df3a332ab9","mcp_get_code":{"code_sha256":"ac6767df3a332ab9"}},{"arxiv_id":"2203.11335","paper":"/paper/global-matching-with-overlapping-attention","title":"Global Matching with Overlapping Attention for Optical Flow Estimation","date":"2022-03-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xiaofeng94/gmflownet","path":"core/gmflownet_model.py","file_url":"https://github.com/xiaofeng94/gmflownet/blob/HEAD/core/gmflownet_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ca7156b5b0317a60","mcp_get_code":{"code_sha256":"ca7156b5b0317a60"}},{"arxiv_id":"2202.13110","paper":"/paper/optimal-er-auctions-through-attention","title":"Optimal-er Auctions through Attention","date":"2022-02-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dimonenka/optimaler","path":"core/nets/additive_net_attention.py","file_url":"https://github.com/dimonenka/optimaler/blob/HEAD/core/nets/additive_net_attention.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2a4cfe231bde233c","mcp_get_code":{"code_sha256":"2a4cfe231bde233c"}},{"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":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"60349842ffb248e7","mcp_get_code":{"code_sha256":"60349842ffb248e7"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2bef0240af575848","mcp_get_code":{"code_sha256":"2bef0240af575848"}},{"arxiv_id":"2201.04676","paper":"/paper/uniformer-unified-transformer-for-efficient-1","title":"UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning","date":"2022-01-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"towhee-io/towhee","path":"towhee/models/uniformer/uniformer.py","file_url":"https://github.com/towhee-io/towhee/blob/HEAD/towhee/models/uniformer/uniformer.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":"e00c355740a3cab6","mcp_get_code":{"code_sha256":"e00c355740a3cab6"}},{"arxiv_id":"2110.13987","paper":"/paper/learning-collaborative-policies-to-solve-np","title":"Learning Collaborative Policies to Solve NP-hard Routing Problems","date":"2021-10-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alstn12088/lcp","path":"nets/attention_model.py","file_url":"https://github.com/alstn12088/lcp/blob/HEAD/nets/attention_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c5d3fd20d5155301","mcp_get_code":{"code_sha256":"c5d3fd20d5155301"}},{"arxiv_id":"2110.02544","paper":"/paper/learning-to-iteratively-solve-routing","title":"Learning to Iteratively Solve Routing Problems with Dual-Aspect Collaborative Transformer","date":"2021-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yining043/VRP-DACT","path":"nets/actor_network.py","file_url":"https://github.com/yining043/VRP-DACT/blob/HEAD/nets/actor_network.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fa54d99ecac04864","mcp_get_code":{"code_sha256":"fa54d99ecac04864"}},{"arxiv_id":"2110.02544","paper":"/paper/learning-to-iteratively-solve-routing","title":"Learning to Iteratively Solve Routing Problems with Dual-Aspect Collaborative Transformer","date":"2021-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yining043/TSP-improve","path":"nets/attention_model.py","file_url":"https://github.com/yining043/TSP-improve/blob/HEAD/nets/attention_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3e9c7f43e77628ea","mcp_get_code":{"code_sha256":"3e9c7f43e77628ea"}},{"arxiv_id":"2109.05446","paper":"/paper/efficient-fedrec-efficient-federated-learning","title":"Efficient-FedRec: Efficient Federated Learning Framework for Privacy-Preserving News Recommendation","date":"2021-09-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yjw1029/Efficient-FedRec","path":"src/model.py","file_url":"https://github.com/yjw1029/Efficient-FedRec/blob/HEAD/src/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dcee9ec72e705723","mcp_get_code":{"code_sha256":"dcee9ec72e705723"}},{"arxiv_id":"2108.07386","paper":"/paper/bobcat-bilevel-optimization-based","title":"BOBCAT: Bilevel Optimization-Based Computerized Adaptive Testing","date":"2021-08-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"arghosh/NeurIPSEducation2020","path":"model_task_1_2.py","file_url":"https://github.com/arghosh/NeurIPSEducation2020/blob/HEAD/model_task_1_2.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e28f6e6239277b44","mcp_get_code":{"code_sha256":"e28f6e6239277b44"}},{"arxiv_id":"2108.05997","paper":"/paper/musiq-multi-scale-image-quality-transformer","title":"MUSIQ: Multi-scale Image Quality Transformer","date":"2021-08-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"anse3832/MUSIQ","path":"model/model_main.py","file_url":"https://github.com/anse3832/MUSIQ/blob/HEAD/model/model_main.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"40eb87901e9f32af","mcp_get_code":{"code_sha256":"40eb87901e9f32af"}},{"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":"85192f7dbff6e0f1","mcp_get_code":{"code_sha256":"85192f7dbff6e0f1"}},{"arxiv_id":"2107.08918","paper":"/paper/self-promoted-prototype-refinement-for-few-1","title":"Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning","date":"2021-07-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhukaii/SPPR","path":"utils/model/my_model.py","file_url":"https://github.com/zhukaii/SPPR/blob/HEAD/utils/model/my_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0520c721df2cd5a6","mcp_get_code":{"code_sha256":"0520c721df2cd5a6"}},{"arxiv_id":"2107.07933","paper":"/paper/panoptic-segmentation-of-satellite-image-time","title":"Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networks","date":"2021-07-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VSainteuf/utae-paps","path":"src/backbones/utae.py","file_url":"https://github.com/VSainteuf/utae-paps/blob/HEAD/src/backbones/utae.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"05217b7e7b5d3120","mcp_get_code":{"code_sha256":"05217b7e7b5d3120"}},{"arxiv_id":"2106.13008","paper":"/paper/autoformer-decomposition-transformers-with","title":"Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting","date":"2021-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"WenjieDu/PyPOTS","path":"pypots/nn/modules/autoformer/layers.py","file_url":"https://github.com/WenjieDu/PyPOTS/blob/HEAD/pypots/nn/modules/autoformer/layers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"f42a7fe1ccedb9dd","mcp_get_code":{"code_sha256":"f42a7fe1ccedb9dd"}},{"arxiv_id":"2106.09685","paper":"/paper/lora-low-rank-adaptation-of-large-language","title":"LoRA: Low-Rank Adaptation of Large Language Models","date":"2021-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"labmlai/annotated_deep_learning_paper_implementations","path":"labml_nn/lora/gpt2.py","file_url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/HEAD/labml_nn/lora/gpt2.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7a1353c5e5ac87b5","mcp_get_code":{"code_sha256":"7a1353c5e5ac87b5"}},{"arxiv_id":"2106.08185","paper":"/paper/kernel-identification-through-transformers","title":"Kernel Identification Through Transformers","date":"2021-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"frgsimpson/kitt","path":"kitt/networks/transformer/set_transformer_blocks.py","file_url":"https://github.com/frgsimpson/kitt/blob/HEAD/kitt/networks/transformer/set_transformer_blocks.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"ae35f134435c3169","mcp_get_code":{"code_sha256":"ae35f134435c3169"}},{"arxiv_id":"2106.06103","paper":"/paper/conditional-variational-autoencoder-with","title":"Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech","date":null,"month_inferred_from_arxiv_id":"2021-06","title_source":"archive","repo":"isletennos/mmvc_trainer","path":"models.py","file_url":"https://github.com/isletennos/mmvc_trainer/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":"1565e9cf603643df","mcp_get_code":{"code_sha256":"1565e9cf603643df"}},{"arxiv_id":"2106.02097","paper":"/paper/a-consciousness-inspired-planning-agent-for","title":"A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning","date":"2021-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PwnerHarry/CP","path":"components_CP.py","file_url":"https://github.com/PwnerHarry/CP/blob/HEAD/components_CP.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"16c1cdf7d8a36c9a","mcp_get_code":{"code_sha256":"16c1cdf7d8a36c9a"}},{"arxiv_id":"2106.01562","paper":"/paper/discriminative-reasoning-for-document-level","title":"Discriminative Reasoning for Document-level Relation Extraction","date":"2021-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xwjim/DRN","path":"code/models/DRN.py","file_url":"https://github.com/xwjim/DRN/blob/HEAD/code/models/DRN.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b3cbaba8366c9a10","mcp_get_code":{"code_sha256":"b3cbaba8366c9a10"}},{"arxiv_id":"2106.01540","paper":"/paper/luna-linear-unified-nested-attention","title":"Luna: Linear Unified Nested Attention","date":"2021-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sooftware/luna-transformer","path":"luna_transformer/attention.py","file_url":"https://github.com/sooftware/luna-transformer/blob/HEAD/luna_transformer/attention.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9b0ec916edfd0481","mcp_get_code":{"code_sha256":"9b0ec916edfd0481"}},{"arxiv_id":"2103.15595","paper":"/paper/mvsnerf-fast-generalizable-radiance-field","title":"MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo","date":"2021-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"apchenstu/mvsnerf","path":"models.py","file_url":"https://github.com/apchenstu/mvsnerf/blob/HEAD/models.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"26e5586432af7496","mcp_get_code":{"code_sha256":"26e5586432af7496"}},{"arxiv_id":"2103.10211","paper":"/paper/space-time-crop-attend-improving-cross-modal","title":"Space-Time Crop & Attend: Improving Cross-modal Video Representation Learning","date":"2021-03-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/GDT","path":"model.py","file_url":"https://github.com/facebookresearch/GDT/blob/HEAD/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":"025f425a305c99a1","mcp_get_code":{"code_sha256":"025f425a305c99a1"}},{"arxiv_id":"2103.04256","paper":"/paper/robust-point-cloud-registration-framework","title":"Robust Point Cloud Registration Framework Based on Deep Graph Matching","date":"2021-03-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhileichen99/utopic","path":"models/architecture.py","file_url":"https://github.com/zhileichen99/utopic/blob/HEAD/models/architecture.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"11617e778bcd8123","mcp_get_code":{"code_sha256":"11617e778bcd8123"}},{"arxiv_id":"2103.03206","paper":"/paper/perceiver-general-perception-with-iterative","title":"Perceiver: General Perception with Iterative Attention","date":"2021-03-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"towhee-io/towhee","path":"towhee/models/perceiver/cross_attention.py","file_url":"https://github.com/towhee-io/towhee/blob/HEAD/towhee/models/perceiver/cross_attention.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":"055997cbf4c57dd0","mcp_get_code":{"code_sha256":"055997cbf4c57dd0"}},{"arxiv_id":"2103.03027","paper":"/paper/modeling-multi-label-action-dependencies-for","title":"Modeling Multi-Label Action Dependencies for Temporal Action Localization","date":"2021-03-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ptirupat/MLAD","path":"src/models/v1.py","file_url":"https://github.com/ptirupat/MLAD/blob/HEAD/src/models/v1.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"57aa62d54d64e9a0","mcp_get_code":{"code_sha256":"57aa62d54d64e9a0"}},{"arxiv_id":"2103.01537","paper":"/paper/few-shot-open-set-recognition-by","title":"Few-shot Open-set Recognition by Transformation Consistency","date":"2021-03-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MinkiJ/SnaTCHer","path":"model/models/SnaTCHerF.py","file_url":"https://github.com/MinkiJ/SnaTCHer/blob/HEAD/model/models/SnaTCHerF.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"85ecf5763f8f6ec3","mcp_get_code":{"code_sha256":"85ecf5763f8f6ec3"}},{"arxiv_id":"2102.13090","paper":"/paper/ibrnet-learning-multi-view-image-based","title":"IBRNet: Learning Multi-View Image-Based Rendering","date":"2021-02-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"googleinterns/ibrnet","path":"ibrnet/mlp_network.py","file_url":"https://github.com/googleinterns/ibrnet/blob/HEAD/ibrnet/mlp_network.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":"e415eac8d6b1e84c","mcp_get_code":{"code_sha256":"e415eac8d6b1e84c"}},{"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":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ef066f2fb629b698","mcp_get_code":{"code_sha256":"ef066f2fb629b698"}},{"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":"mdmhriday/vision-transformers","path":"models/vit.py","file_url":"https://github.com/mdmhriday/vision-transformers/blob/HEAD/models/vit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"32bc51f5c0550254","mcp_get_code":{"code_sha256":"32bc51f5c0550254"}},{"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":"sangHa0411/VIT","path":"model.py","file_url":"https://github.com/sangHa0411/VIT/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":"816585d560db3f1d","mcp_get_code":{"code_sha256":"816585d560db3f1d"}},{"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":"drumpt/ViT","path":"model.py","file_url":"https://github.com/drumpt/ViT/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"285f0cc9150c1c47","mcp_get_code":{"code_sha256":"285f0cc9150c1c47"}},{"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":"UdbhavPrasad072300/Transformer-Implementation-and-Language-Translation","path":"transformer_package/models/transformer.py","file_url":"https://github.com/UdbhavPrasad072300/Transformer-Implementation-and-Language-Translation/blob/HEAD/transformer_package/models/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"61787a7f1ca16779","mcp_get_code":{"code_sha256":"61787a7f1ca16779"}},{"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":"KiUngSong/Vision","path":"ViT/ViT_pytorch.py","file_url":"https://github.com/KiUngSong/Vision/blob/HEAD/ViT/ViT_pytorch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a78ee14b916decd1","mcp_get_code":{"code_sha256":"a78ee14b916decd1"}},{"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":"timH6502/VisionTransformer-PyTorch","path":"src/ViT.py","file_url":"https://github.com/timH6502/VisionTransformer-PyTorch/blob/HEAD/src/ViT.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6bad9911ea340c54","mcp_get_code":{"code_sha256":"6bad9911ea340c54"}},{"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":"bshantam97/Attention_Based_Networks","path":"vision_transformer.py","file_url":"https://github.com/bshantam97/Attention_Based_Networks/blob/HEAD/vision_transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6082f915e0ac604c","mcp_get_code":{"code_sha256":"6082f915e0ac604c"}},{"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":"Ugenteraan/Masked-AutoEncoder-PyTorch","path":"models/mae.py","file_url":"https://github.com/Ugenteraan/Masked-AutoEncoder-PyTorch/blob/HEAD/models/mae.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"f6a1ed2d7f5be2dc","mcp_get_code":{"code_sha256":"f6a1ed2d7f5be2dc"}},{"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":"tintn/vision-transformer-from-scratch","path":"vit.py","file_url":"https://github.com/tintn/vision-transformer-from-scratch/blob/HEAD/vit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"53dab365fc08769e","mcp_get_code":{"code_sha256":"53dab365fc08769e"}},{"arxiv_id":"2008.02953","paper":"/paper/neural-complexity-measures","title":"Neural Complexity Measures","date":"2020-08-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yoonholee/neural-complexity","path":"1d_regression/model/neural_complexity.py","file_url":"https://github.com/yoonholee/neural-complexity/blob/HEAD/1d_regression/model/neural_complexity.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"123f46daaea1a87d","mcp_get_code":{"code_sha256":"123f46daaea1a87d"}},{"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":"tartunlp/transformertts","path":"src/transformer_tts/model/forward_model.py","file_url":"https://github.com/tartunlp/transformertts/blob/HEAD/src/transformer_tts/model/forward_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"0d6a9c2615231e6a","mcp_get_code":{"code_sha256":"0d6a9c2615231e6a"}},{"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":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"633b426a0ece94c3","mcp_get_code":{"code_sha256":"633b426a0ece94c3"}},{"arxiv_id":"2005.12872","paper":"/paper/end-to-end-object-detection-with-transformers","title":"End-to-End Object Detection with Transformers","date":"2020-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Leonardo-Blanger/detr_tensorflow","path":"detr_tensorflow/models/detr.py","file_url":"https://github.com/Leonardo-Blanger/detr_tensorflow/blob/HEAD/detr_tensorflow/models/detr.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d81ff048a53b3958","mcp_get_code":{"code_sha256":"d81ff048a53b3958"}},{"arxiv_id":"2005.12872","paper":"/paper/end-to-end-object-detection-with-transformers","title":"End-to-End Object Detection with Transformers","date":"2020-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Visual-Behavior/detr-tensorflow","path":"detr_tf/networks/detr.py","file_url":"https://github.com/Visual-Behavior/detr-tensorflow/blob/HEAD/detr_tf/networks/detr.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"595c977770d20ea9","mcp_get_code":{"code_sha256":"595c977770d20ea9"}},{"arxiv_id":"2005.00697","paper":"/paper/deformer-decomposing-pre-trained-transformers","title":"DeFormer: Decomposing Pre-trained Transformers for Faster Question Answering","date":"2020-05-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"StonyBrookNLP/deformer","path":"models/layers/transformer.py","file_url":"https://github.com/StonyBrookNLP/deformer/blob/HEAD/models/layers/transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"17837c6365878a53","mcp_get_code":{"code_sha256":"17837c6365878a53"}},{"arxiv_id":"2004.08249","paper":"/paper/understanding-the-difficulty-of-training","title":"Understanding the Difficulty of Training Transformers","date":"2020-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"c00k1ez/plain-transformers","path":"src/plain_transformers/layers/pre_ln_encoder.py","file_url":"https://github.com/c00k1ez/plain-transformers/blob/HEAD/src/plain_transformers/layers/pre_ln_encoder.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":"d3e534b847d15575","mcp_get_code":{"code_sha256":"d3e534b847d15575"}},{"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":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b9a5bb409e08cbc8","mcp_get_code":{"code_sha256":"b9a5bb409e08cbc8"}},{"arxiv_id":"1911.02116","paper":"/paper/unsupervised-cross-lingual-representation-1","title":"Unsupervised Cross-lingual Representation Learning at Scale","date":"2019-11-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Tikquuss/meta_XLM","path":"XLM/src/model/transformer.py","file_url":"https://github.com/Tikquuss/meta_XLM/blob/HEAD/XLM/src/model/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"59c6324aa51d05e7","mcp_get_code":{"code_sha256":"59c6324aa51d05e7"}},{"arxiv_id":"1911.02116","paper":"/paper/unsupervised-cross-lingual-representation-1","title":"Unsupervised Cross-lingual Representation Learning at Scale","date":"2019-11-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"1-punchMan/CLTS","path":"src/model/transformer.py","file_url":"https://github.com/1-punchMan/CLTS/blob/HEAD/src/model/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"87278bd6d018466e","mcp_get_code":{"code_sha256":"87278bd6d018466e"}},{"arxiv_id":"1911.02116","paper":"/paper/unsupervised-cross-lingual-representation-1","title":"Unsupervised Cross-lingual Representation Learning at Scale","date":"2019-11-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"deterministic-algorithms-lab/Large-XLM","path":"src/model/transformer.py","file_url":"https://github.com/deterministic-algorithms-lab/Large-XLM/blob/HEAD/src/model/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"8ed44ce7206b1f24","mcp_get_code":{"code_sha256":"8ed44ce7206b1f24"}},{"arxiv_id":"1909.10893","paper":"/paper/recurrent-independent-mechanisms","title":"Recurrent Independent Mechanisms","date":"2019-09-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"anirudh9119/RIMs","path":"blocks_atari/a2c_ppo_acktr/blocks_core.py","file_url":"https://github.com/anirudh9119/RIMs/blob/HEAD/blocks_atari/a2c_ppo_acktr/blocks_core.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2aaad11d08c7dcef","mcp_get_code":{"code_sha256":"2aaad11d08c7dcef"}},{"arxiv_id":"1909.05858","paper":"/paper/ctrl-a-conditional-transformer-language-model-1","title":"CTRL: A Conditional Transformer Language Model for Controllable Generation","date":"2019-09-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"UKPLab/controlled-argument-generation","path":"transformer.py","file_url":"https://github.com/UKPLab/controlled-argument-generation/blob/HEAD/transformer.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":"28afe17f8e7f671f","mcp_get_code":{"code_sha256":"28afe17f8e7f671f"}},{"arxiv_id":"1909.05858","paper":"/paper/ctrl-a-conditional-transformer-language-model-1","title":"CTRL: A Conditional Transformer Language Model for Controllable Generation","date":"2019-09-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salesforce/ctrl","path":"pytorch_transformer.py","file_url":"https://github.com/salesforce/ctrl/blob/HEAD/pytorch_transformer.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":"6a0d83e892c993b0","mcp_get_code":{"code_sha256":"6a0d83e892c993b0"}},{"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":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f96d7fde8876634b","mcp_get_code":{"code_sha256":"f96d7fde8876634b"}},{"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":"rajlm10/Chandler","path":"utils.py","file_url":"https://github.com/rajlm10/Chandler/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d0f7a90c6c7d9e89","mcp_get_code":{"code_sha256":"d0f7a90c6c7d9e89"}},{"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":"eagle705/bert","path":"model/bert.py","file_url":"https://github.com/eagle705/bert/blob/HEAD/model/bert.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3c706b7d1522d9c1","mcp_get_code":{"code_sha256":"3c706b7d1522d9c1"}},{"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":"graykode/nlp-tutorial","path":"5-2.BERT/BERT.py","file_url":"https://github.com/graykode/nlp-tutorial/blob/HEAD/5-2.BERT/BERT.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"aa4eb5c5bf00a8e5","mcp_get_code":{"code_sha256":"aa4eb5c5bf00a8e5"}},{"arxiv_id":"1803.02155","paper":"/paper/self-attention-with-relative-position","title":"Self-Attention with Relative Position Representations","date":"2018-03-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OpenNMT/OpenNMT-tf","path":"opennmt/layers/transformer.py","file_url":"https://github.com/OpenNMT/OpenNMT-tf/blob/HEAD/opennmt/layers/transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5fd90f133d0b4da5","mcp_get_code":{"code_sha256":"5fd90f133d0b4da5"}},{"arxiv_id":"1803.02155","paper":"/paper/self-attention-with-relative-position","title":"Self-Attention with Relative Position Representations","date":"2018-03-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thumt/THUMT","path":"thumt/modules/attention.py","file_url":"https://github.com/thumt/THUMT/blob/HEAD/thumt/modules/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"5697fe35ac9c0449","mcp_get_code":{"code_sha256":"5697fe35ac9c0449"}},{"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":"reppy4620/Dialog","path":"nn/model/attention.py","file_url":"https://github.com/reppy4620/Dialog/blob/HEAD/nn/model/attention.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6857820904112c9e","mcp_get_code":{"code_sha256":"6857820904112c9e"}},{"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":"brainsqueeze/text2vec","path":"text2vec/models/transformer.py","file_url":"https://github.com/brainsqueeze/text2vec/blob/HEAD/text2vec/models/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"code_sha256_prefix":"5c0102ed6c55b463","mcp_get_code":{"code_sha256":"5c0102ed6c55b463"}},{"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":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"efc0e4a2db5cbe22","mcp_get_code":{"code_sha256":"efc0e4a2db5cbe22"}},{"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":"2048579a5e46af35","mcp_get_code":{"code_sha256":"2048579a5e46af35"}},{"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":"lif31up/extended-BERT-for-low-rank-adaption","path":"model/Transformer.py","file_url":"https://github.com/lif31up/extended-BERT-for-low-rank-adaption/blob/HEAD/model/Transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"64fb08c62472e6cc","mcp_get_code":{"code_sha256":"64fb08c62472e6cc"}},{"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":"shao-chi/ImageCaption","path":"core/TRANSFORMER/model.py","file_url":"https://github.com/shao-chi/ImageCaption/blob/HEAD/core/TRANSFORMER/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6812bf04c87c4c73","mcp_get_code":{"code_sha256":"6812bf04c87c4c73"}},{"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":"d98a6767ef157124","mcp_get_code":{"code_sha256":"d98a6767ef157124"}},{"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":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9206d829f8385ea9","mcp_get_code":{"code_sha256":"9206d829f8385ea9"}},{"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":"text-machine-lab/transformerpy","path":"transformer/Models.py","file_url":"https://github.com/text-machine-lab/transformerpy/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":"08012c7ee8bdaa56","mcp_get_code":{"code_sha256":"08012c7ee8bdaa56"}},{"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":"e3f5c59f43d9745e","mcp_get_code":{"code_sha256":"e3f5c59f43d9745e"}},{"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":"anhtu293/transformer_from_scratch","path":"model/transformer.py","file_url":"https://github.com/anhtu293/transformer_from_scratch/blob/HEAD/model/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4e3c3ae5deac37f3","mcp_get_code":{"code_sha256":"4e3c3ae5deac37f3"}},{"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":"antoinecollas/transformer_neural_machine_translation","path":"transformer/transformer.py","file_url":"https://github.com/antoinecollas/transformer_neural_machine_translation/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":"d8e7e151a392bb14","mcp_get_code":{"code_sha256":"d8e7e151a392bb14"}},{"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":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"404391a1cf5281cb","mcp_get_code":{"code_sha256":"404391a1cf5281cb"}},{"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":"AndreiMoraru123/Neural-Machine-Translation","path":"model.py","file_url":"https://github.com/AndreiMoraru123/Neural-Machine-Translation/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":"178bd40b337c3024","mcp_get_code":{"code_sha256":"178bd40b337c3024"}},{"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":"xcmyz/FastSpeech","path":"transformer/SubLayers.py","file_url":"https://github.com/xcmyz/FastSpeech/blob/HEAD/transformer/SubLayers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"eac9950af8865b06","mcp_get_code":{"code_sha256":"eac9950af8865b06"}},{"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":"HanhaiNotHai/transformer","path":"transformer.py","file_url":"https://github.com/HanhaiNotHai/transformer/blob/HEAD/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"WTFPL","inline_ok":false,"code_sha256_prefix":"5381d8093ee62f5a","mcp_get_code":{"code_sha256":"5381d8093ee62f5a"}},{"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":"Skumarr53/Attention-is-All-you-Need-PyTorch","path":"transformer/model.py","file_url":"https://github.com/Skumarr53/Attention-is-All-you-Need-PyTorch/blob/HEAD/transformer/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"53c73dcc3ea86ce6","mcp_get_code":{"code_sha256":"53c73dcc3ea86ce6"}},{"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":"tanjeffreyz/attention-is-all-you-need","path":"modules/transformer.py","file_url":"https://github.com/tanjeffreyz/attention-is-all-you-need/blob/HEAD/modules/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"42237bfabab4e24a","mcp_get_code":{"code_sha256":"42237bfabab4e24a"}},{"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":"bkoch4142/attention-is-all-you-need-paper","path":"src/architectures/transformer_encoder_decoder.py","file_url":"https://github.com/bkoch4142/attention-is-all-you-need-paper/blob/HEAD/src/architectures/transformer_encoder_decoder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ffd6037fbc02bfb3","mcp_get_code":{"code_sha256":"ffd6037fbc02bfb3"}},{"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":"ming024/FastSpeech2","path":"transformer/SubLayers.py","file_url":"https://github.com/ming024/FastSpeech2/blob/HEAD/transformer/SubLayers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c3c28309c3ab1b58","mcp_get_code":{"code_sha256":"c3c28309c3ab1b58"}},{"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":"dhiraa/tener","path":"src/tener/models/vanialla_transformer.py","file_url":"https://github.com/dhiraa/tener/blob/HEAD/src/tener/models/vanialla_transformer.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":"d0c0a3c1c94158ea","mcp_get_code":{"code_sha256":"d0c0a3c1c94158ea"}},{"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":"re-search/DocProduct","path":"keras_bert/keras_transformer/transformer.py","file_url":"https://github.com/re-search/DocProduct/blob/HEAD/keras_bert/keras_transformer/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e9f3610540a87c71","mcp_get_code":{"code_sha256":"e9f3610540a87c71"}},{"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":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4ab59e6644c5d75f","mcp_get_code":{"code_sha256":"4ab59e6644c5d75f"}},{"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":"uzi0espil/research-papers-implementation","path":"Attention Is All You Need/model.py","file_url":"https://github.com/uzi0espil/research-papers-implementation/blob/HEAD/Attention%20Is%20All%20You%20Need/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c9e09f90fbd51648","mcp_get_code":{"code_sha256":"c9e09f90fbd51648"}},{"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":"CVxTz/music_genre_classification","path":"code/models.py","file_url":"https://github.com/CVxTz/music_genre_classification/blob/HEAD/code/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"970bd863e6e11513","mcp_get_code":{"code_sha256":"970bd863e6e11513"}},{"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":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4bcb6aa031ba3144","mcp_get_code":{"code_sha256":"4bcb6aa031ba3144"}},{"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":"7a011e73053869be","mcp_get_code":{"code_sha256":"7a011e73053869be"}},{"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":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0cae76f0a7d6ae2a","mcp_get_code":{"code_sha256":"0cae76f0a7d6ae2a"}},{"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":"bangoc123/transformer","path":"transformer/model.py","file_url":"https://github.com/bangoc123/transformer/blob/HEAD/transformer/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0ceb02ea5effb26b","mcp_get_code":{"code_sha256":"0ceb02ea5effb26b"}},{"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":"PrideLee/sentiment-analysis","path":"transformer/model.py","file_url":"https://github.com/PrideLee/sentiment-analysis/blob/HEAD/transformer/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8de81c6bdbe41b3d","mcp_get_code":{"code_sha256":"8de81c6bdbe41b3d"}},{"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":"tree-park/transformer_lm","path":"lib/model/transformer.py","file_url":"https://github.com/tree-park/transformer_lm/blob/HEAD/lib/model/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0376198cb0764ff6","mcp_get_code":{"code_sha256":"0376198cb0764ff6"}},{"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":"cosmoquester/seq2seq","path":"seq2seq/model.py","file_url":"https://github.com/cosmoquester/seq2seq/blob/HEAD/seq2seq/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"60e8d0a3134c69ee","mcp_get_code":{"code_sha256":"60e8d0a3134c69ee"}},{"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":"WenjieDu/PyPOTS","path":"pypots/nn/modules/transformer/autoencoder.py","file_url":"https://github.com/WenjieDu/PyPOTS/blob/HEAD/pypots/nn/modules/transformer/autoencoder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"6626c0cd03b4e028","mcp_get_code":{"code_sha256":"6626c0cd03b4e028"}},{"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":"Aveek-Saha/Transformer","path":"model.py","file_url":"https://github.com/Aveek-Saha/Transformer/blob/HEAD/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":"565cce9a1d38dda5","mcp_get_code":{"code_sha256":"565cce9a1d38dda5"}},{"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":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e945bfbe1ad7c1df","mcp_get_code":{"code_sha256":"e945bfbe1ad7c1df"}},{"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":"simonjisu/annotated-transformer-kr","path":"transformer/models.py","file_url":"https://github.com/simonjisu/annotated-transformer-kr/blob/HEAD/transformer/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"730826e0274a94a9","mcp_get_code":{"code_sha256":"730826e0274a94a9"}},{"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":"BrianPulfer/PapersReimplementations","path":"src/nlp/layers/encoder.py","file_url":"https://github.com/BrianPulfer/PapersReimplementations/blob/HEAD/src/nlp/layers/encoder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9c478f15d1800b2a","mcp_get_code":{"code_sha256":"9c478f15d1800b2a"}},{"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":"enhuiz/torchnmt","path":"torchnmt/networks/transformer.py","file_url":"https://github.com/enhuiz/torchnmt/blob/HEAD/torchnmt/networks/transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"08626e97dad1c3fe","mcp_get_code":{"code_sha256":"08626e97dad1c3fe"}},{"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":"feizc/Machine-Translation-Pytorch","path":"code/model.py","file_url":"https://github.com/feizc/Machine-Translation-Pytorch/blob/HEAD/code/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"54719174caf0f679","mcp_get_code":{"code_sha256":"54719174caf0f679"}},{"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":"vpj/jax_transformer","path":"transformer.py","file_url":"https://github.com/vpj/jax_transformer/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":"61ae9552f7ea09a7","mcp_get_code":{"code_sha256":"61ae9552f7ea09a7"}},{"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":"graykode/nlp-tutorial","path":"5-1.Transformer/Transformer.py","file_url":"https://github.com/graykode/nlp-tutorial/blob/HEAD/5-1.Transformer/Transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7dd8d0189f54c083","mcp_get_code":{"code_sha256":"7dd8d0189f54c083"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2b49fc6c1609a33c","mcp_get_code":{"code_sha256":"2b49fc6c1609a33c"}},{"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":"seunghwan1228/Transfomer-MachineTranslation","path":"models/transformer.py","file_url":"https://github.com/seunghwan1228/Transfomer-MachineTranslation/blob/HEAD/models/transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ac0bfecb3908b7ad","mcp_get_code":{"code_sha256":"ac0bfecb3908b7ad"}},{"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":"sooftware/Attention-Implementation","path":"attentions.py","file_url":"https://github.com/sooftware/Attention-Implementation/blob/HEAD/attentions.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"32934f51684fa226","mcp_get_code":{"code_sha256":"32934f51684fa226"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d0c4191f4c3ec85c","mcp_get_code":{"code_sha256":"d0c4191f4c3ec85c"}},{"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":"abhaskumarsinha/MinimalGPT","path":"GPT.py","file_url":"https://github.com/abhaskumarsinha/MinimalGPT/blob/HEAD/GPT.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f40352b00f32961d","mcp_get_code":{"code_sha256":"f40352b00f32961d"}},{"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":"gooppe/transformer-summarization","path":"nn/modules/transformer.py","file_url":"https://github.com/gooppe/transformer-summarization/blob/HEAD/nn/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":"8d076c9044814790","mcp_get_code":{"code_sha256":"8d076c9044814790"}},{"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":"hrbigelow/transformer-aiayn","path":"aiayn/model.py","file_url":"https://github.com/hrbigelow/transformer-aiayn/blob/HEAD/aiayn/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fdb9df4eedce8d63","mcp_get_code":{"code_sha256":"fdb9df4eedce8d63"}},{"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":"DevSinghSachan/multilingual_nmt","path":"models/transformer.py","file_url":"https://github.com/DevSinghSachan/multilingual_nmt/blob/HEAD/models/transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"47562fc57d4ed0d7","mcp_get_code":{"code_sha256":"47562fc57d4ed0d7"}},{"arxiv_id":"1704.04368","paper":"/paper/get-to-the-point-summarization-with-pointer","title":"Get To The Point: Summarization with Pointer-Generator Networks","date":"2017-04-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"steph1793/Pointer_Transformer_Generator","path":"transformer.py","file_url":"https://github.com/steph1793/Pointer_Transformer_Generator/blob/HEAD/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"aca7c4bd13608aaf","mcp_get_code":{"code_sha256":"aca7c4bd13608aaf"}},{"arxiv_id":"1704.04368","paper":"/paper/get-to-the-point-summarization-with-pointer","title":"Get To The Point: Summarization with Pointer-Generator Networks","date":"2017-04-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NirmalenduPrakash/DocumentSummarizer","path":"summarizer_transformer.py","file_url":"https://github.com/NirmalenduPrakash/DocumentSummarizer/blob/HEAD/summarizer_transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"db4e1c41512bdaac","mcp_get_code":{"code_sha256":"db4e1c41512bdaac"}}]}