{"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/shift","entry":"shift","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":22,"n_papers_ran":7,"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":21,"n_samples_ran":7,"n_samples_fingerprinted":6,"n_places":22,"n_places_pointer_only":5,"by_status":{"ran_honours":1,"ran_violates":1,"ran_draft_wrong":1,"ran_fixture":3,"ran":1,"unverified":14},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2603.22225","paper":"/paper/arxiv-2603-22225","title":"Adapting Self-Supervised Speech Representations for Cross-lingual Dysarthria Detection in Parkinson's Disease","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"abnerLing/language-shift-dysarthria","path":"src/language_shift/pipeline.py","file_url":"https://github.com/abnerLing/language-shift-dysarthria/blob/HEAD/src/language_shift/pipeline.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"65975a99774a580e","mcp_get_code":{"code_sha256":"65975a99774a580e"}},{"arxiv_id":"2511.11090","paper":"/paper/arxiv-2511-11090","title":"A Space-Time Transformer for Precipitation Nowcasting","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":"leharris3/satformer","path":"src/model/SaTformer/SaTformer.py","file_url":"https://github.com/leharris3/satformer/blob/HEAD/src/model/SaTformer/SaTformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6ba08bb22d683e66","mcp_get_code":{"code_sha256":"6ba08bb22d683e66"}},{"arxiv_id":"2503.07580","paper":"/paper/neural-combinatorial-optimization-via","title":"Neural Combinatorial Optimization via Preference Optimization","date":"2025-03-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"L-Z-7/BOPO","path":"JSP/utils.py","file_url":"https://github.com/L-Z-7/BOPO/blob/HEAD/JSP/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b010e092280877d0","mcp_get_code":{"code_sha256":"b010e092280877d0"}},{"arxiv_id":"2312.07987","paper":"/paper/switchhead-accelerating-transformers-with","title":"SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention","date":"2023-12-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"robertcsordas/moe_attention","path":"layers/transformer/multi_head_relative_pos_attention.py","file_url":"https://github.com/robertcsordas/moe_attention/blob/HEAD/layers/transformer/multi_head_relative_pos_attention.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8142975547708e1a","mcp_get_code":{"code_sha256":"8142975547708e1a"}},{"arxiv_id":"2307.08051","paper":"/paper/transnuseg-a-lightweight-multi-task","title":"TransNuSeg: A Lightweight Multi-Task Transformer for Nuclei Segmentation","date":"2023-07-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhenqi-he/transnuseg","path":"models/transnuseg.py","file_url":"https://github.com/zhenqi-he/transnuseg/blob/HEAD/models/transnuseg.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"000b07edf24001b4","mcp_get_code":{"code_sha256":"000b07edf24001b4"}},{"arxiv_id":"2210.07920","paper":"/paper/move-unsupervised-movable-object-segmentation","title":"MOVE: Unsupervised Movable Object Segmentation and Detection","date":"2022-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"adambielski/move-seg","path":"segmenter.py","file_url":"https://github.com/adambielski/move-seg/blob/HEAD/segmenter.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a29acc562d4682ac","mcp_get_code":{"code_sha256":"a29acc562d4682ac"}},{"arxiv_id":"2203.13815","paper":"/paper/versatile-multi-modal-pre-training-for-human","title":"Versatile Multi-Modal Pre-Training for Human-Centric Perception","date":"2022-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hongfz16/hcmoco","path":"A2J/anchor.py","file_url":"https://github.com/hongfz16/hcmoco/blob/HEAD/A2J/anchor.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8308f24a0a9426f4","mcp_get_code":{"code_sha256":"8308f24a0a9426f4"}},{"arxiv_id":"2203.04967","paper":"/paper/unext-mlp-based-rapid-medical-image","title":"UNeXt: MLP-based Rapid Medical Image Segmentation Network","date":"2022-03-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jeya-maria-jose/unext-pytorch","path":"archs.py","file_url":"https://github.com/jeya-maria-jose/unext-pytorch/blob/HEAD/archs.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"000b07edf24001b4","mcp_get_code":{"code_sha256":"000b07edf24001b4"}},{"arxiv_id":"2112.13492","paper":"/paper/vision-transformer-for-small-size-datasets","title":"Vision Transformer for Small-Size Datasets","date":"2021-12-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"conceptofmind/ViT-Small-Datasets-flax","path":"vit_small_datasets.py","file_url":"https://github.com/conceptofmind/ViT-Small-Datasets-flax/blob/HEAD/vit_small_datasets.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a8ea5cb0bcde2a2b","mcp_get_code":{"code_sha256":"a8ea5cb0bcde2a2b"}},{"arxiv_id":"2110.07732","paper":"/paper/the-neural-data-router-adaptive-control-flow","title":"The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization","date":"2021-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"robertcsordas/ndr","path":"layers/transformer/ndr.py","file_url":"https://github.com/robertcsordas/ndr/blob/HEAD/layers/transformer/ndr.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fd07c4fcaa87fe04","mcp_get_code":{"code_sha256":"fd07c4fcaa87fe04"}},{"arxiv_id":"2107.11906","paper":"/paper/h-transformer-1d-fast-one-dimensional","title":"H-Transformer-1D: Fast One-Dimensional Hierarchical Attention for Sequences","date":"2021-07-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/h-transformer-1d","path":"h_transformer_1d/h_transformer_1d.py","file_url":"https://github.com/lucidrains/h-transformer-1d/blob/HEAD/h_transformer_1d/h_transformer_1d.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f73845c2459404f2","mcp_get_code":{"code_sha256":"f73845c2459404f2"}},{"arxiv_id":"2106.02343","paper":"/paper/f-drop-match-gans-with-a-dead-zone-in-the","title":"F-Drop&Match: GANs with a Dead Zone in the High-Frequency Domain","date":"2021-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cyq373/SSD-GAN","path":"get_fft_feature.py","file_url":"https://github.com/cyq373/SSD-GAN/blob/HEAD/get_fft_feature.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fea21db3bb422133","mcp_get_code":{"code_sha256":"fea21db3bb422133"}},{"arxiv_id":"2105.13677","paper":"/paper/rest-an-efficient-transformer-for-visual","title":"ResT: An Efficient Transformer for Visual Recognition","date":"2021-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wofmanaf/ResT","path":"fourier_analysis.py","file_url":"https://github.com/wofmanaf/ResT/blob/HEAD/fourier_analysis.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"4250eda6a35c9d8c","mcp_get_code":{"code_sha256":"4250eda6a35c9d8c"}},{"arxiv_id":"2105.08050","paper":"/paper/pay-attention-to-mlps","title":"Pay Attention to MLPs","date":"2021-05-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/g-mlp-pytorch","path":"g_mlp_pytorch/g_mlp_pytorch.py","file_url":"https://github.com/lucidrains/g-mlp-pytorch/blob/HEAD/g_mlp_pytorch/g_mlp_pytorch.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2fdf59e29c6d95cc","mcp_get_code":{"code_sha256":"2fdf59e29c6d95cc"}},{"arxiv_id":"2104.00563","paper":"/paper/latent-variable-nested-set-transformers","title":"Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Prediction","date":"2021-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"roggirg/AutoBots","path":"datasets/trajnetpp/create_data_npys.py","file_url":"https://github.com/roggirg/AutoBots/blob/HEAD/datasets/trajnetpp/create_data_npys.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":"1761d9ef84caa582","mcp_get_code":{"code_sha256":"1761d9ef84caa582"}},{"arxiv_id":"2102.05095","paper":"/paper/is-space-time-attention-all-you-need-for","title":"Is Space-Time Attention All You Need for Video Understanding?","date":"2021-02-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/TimeSformer-pytorch","path":"timesformer_pytorch/timesformer_pytorch.py","file_url":"https://github.com/lucidrains/TimeSformer-pytorch/blob/HEAD/timesformer_pytorch/timesformer_pytorch.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f6e07e75149898e3","mcp_get_code":{"code_sha256":"f6e07e75149898e3"}},{"arxiv_id":"2002.02798","paper":"/paper/how-to-train-your-neural-ode","title":"How to train your neural ODE: the world of Jacobian and kinetic regularization","date":"2020-02-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"D-hash-code/ffjord-rnode-finalweek-mnist","path":"trainCNFGAN.py","file_url":"https://github.com/D-hash-code/ffjord-rnode-finalweek-mnist/blob/HEAD/trainCNFGAN.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"eff72070f790a5fe","mcp_get_code":{"code_sha256":"eff72070f790a5fe"}},{"arxiv_id":"1911.09070","paper":"/paper/efficientdet-scalable-and-efficient-object","title":"EfficientDet: Scalable and Efficient Object Detection","date":"2019-11-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"signatrix/efficientdet","path":"src/utils.py","file_url":"https://github.com/signatrix/efficientdet/blob/HEAD/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7abc112d283442c7","mcp_get_code":{"code_sha256":"7abc112d283442c7"}},{"arxiv_id":"1908.09999","paper":"/paper/a2j-anchor-to-joint-regression-network-for-3d","title":"A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image","date":"2019-08-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bo-zhang-cs/CACNet-Pytorch","path":"CACNet.py","file_url":"https://github.com/bo-zhang-cs/CACNet-Pytorch/blob/HEAD/CACNet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5c866a97bb0ce1d9","mcp_get_code":{"code_sha256":"5c866a97bb0ce1d9"}},{"arxiv_id":"1906.02283","paper":"/paper/improving-retinanet-for-ct-lesion-detection","title":"Improving RetinaNet for CT Lesion Detection with Dense Masks from Weak RECIST Labels","date":"2019-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fizyr/keras-retinanet","path":"keras_retinanet/backend/backend.py","file_url":"https://github.com/fizyr/keras-retinanet/blob/HEAD/keras_retinanet/backend/backend.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":"95689b7dfe9f464e","mcp_get_code":{"code_sha256":"95689b7dfe9f464e"}},{"arxiv_id":"1901.08753","paper":"/paper/towards-a-deeper-understanding-of-adversarial","title":"On Output Activation Functions for Adversarial Losses: A Theoretical Analysis via Variational Divergence Minimization and An Empirical Study on MNIST Classification","date":"2019-01-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salu133445/dan","path":"src/process_data.py","file_url":"https://github.com/salu133445/dan/blob/HEAD/src/process_data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"54aa94d3da1df967","mcp_get_code":{"code_sha256":"54aa94d3da1df967"}},{"arxiv_id":"1511.02580","paper":"/paper/how-far-can-we-go-without-convolution","title":"How far can we go without convolution: Improving fully-connected networks","date":"2015-11-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AvocadoAlpha/boltz_bo","path":"boltzmann_machines/utils/augmentation.py","file_url":"https://github.com/AvocadoAlpha/boltz_bo/blob/HEAD/boltzmann_machines/utils/augmentation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2d6cfc56420ba55a","mcp_get_code":{"code_sha256":"2d6cfc56420ba55a"}}]}