{"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/cnn","entry":"CNN","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":23,"n_papers_ran":15,"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":25,"n_samples_ran":15,"n_samples_fingerprinted":1,"n_places":25,"n_places_pointer_only":14,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":14,"unverified":10},"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":"2602.02763","paper":"/paper/arxiv-2602-02763","title":"Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"Bohan7/TSEF","path":"experiments/evaluation/tsef_attack.py","file_url":"https://github.com/Bohan7/TSEF/blob/HEAD/experiments/evaluation/tsef_attack.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d6cccad4740ee81e","mcp_get_code":{"code_sha256":"d6cccad4740ee81e"}},{"arxiv_id":"2510.07664","paper":"/paper/arxiv-2510-07664","title":"FedQS: Optimizing Gradient and Model Aggregation for Semi-Asynchronous Federated Learning","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"bkjod/FedQS_","path":"utils/afl_avg_our.py","file_url":"https://github.com/bkjod/FedQS_/blob/HEAD/utils/afl_avg_our.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"36f183711192ad56","mcp_get_code":{"code_sha256":"36f183711192ad56"}},{"arxiv_id":"2406.17251","paper":"/paper/topogcl-topological-graph-contrastive","title":"TopoGCL: Topological Graph Contrastive Learning","date":"2024-06-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"topogclaaai24/TopoGCL","path":"topogin.py","file_url":"https://github.com/topogclaaai24/TopoGCL/blob/HEAD/topogin.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b1d976a60d91f352","mcp_get_code":{"code_sha256":"b1d976a60d91f352"}},{"arxiv_id":"2310.05858","paper":"/paper/dsac-t-distributional-soft-actor-critic-with","title":"Distributional Soft Actor-Critic with Three Refinements","date":"2023-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jingliang-duan/dsac-t","path":"networks/cnn.py","file_url":"https://github.com/jingliang-duan/dsac-t/blob/HEAD/networks/cnn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c182f96b7f88ba70","mcp_get_code":{"code_sha256":"c182f96b7f88ba70"}},{"arxiv_id":"2306.02109","paper":null,"title":"arXiv:2306.02109","date":null,"month_inferred_from_arxiv_id":"2023-06","title_source":null,"repo":"mims-harvard/TimeX","path":"txai/models/bc_model.py","file_url":"https://github.com/mims-harvard/TimeX/blob/HEAD/txai/models/bc_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"00fc6035b5f44c6b","mcp_get_code":{"code_sha256":"00fc6035b5f44c6b"}},{"arxiv_id":"2303.07109","paper":"/paper/transformer-based-world-models-are-happy-with","title":"Transformer-based World Models Are Happy With 100k Interactions","date":"2023-03-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jrobine/twm","path":"twm/world_model.py","file_url":"https://github.com/jrobine/twm/blob/HEAD/twm/world_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"173854afd0798188","mcp_get_code":{"code_sha256":"173854afd0798188"}},{"arxiv_id":"2205.00146","paper":"/paper/look-closer-to-supervise-better-one-shot-font","title":"Look Closer to Supervise Better: One-Shot Font Generation via Component-Based Discriminator","date":"2022-04-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kyxscut/CG-GAN","path":"models/networks.py","file_url":"https://github.com/kyxscut/CG-GAN/blob/HEAD/models/networks.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"06d32a82871f6c23","mcp_get_code":{"code_sha256":"06d32a82871f6c23"}},{"arxiv_id":"2203.01517","paper":"/paper/correct-n-contrast-a-contrastive-approach-for-1","title":"Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations","date":"2022-03-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HazyResearch/correct-n-contrast","path":"contrastive_network.py","file_url":"https://github.com/HazyResearch/correct-n-contrast/blob/HEAD/contrastive_network.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":"2b35ce7f87cc3db1","mcp_get_code":{"code_sha256":"2b35ce7f87cc3db1"}},{"arxiv_id":"2111.04263","paper":"/paper/federated-learning-based-on-dynamic-1","title":"Federated Learning Based on Dynamic Regularization","date":"2021-11-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thejungwon/gc-fed","path":"algorithms/gcfed.py","file_url":"https://github.com/thejungwon/gc-fed/blob/HEAD/algorithms/gcfed.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cff80b8ecb8c8c99","mcp_get_code":{"code_sha256":"cff80b8ecb8c8c99"}},{"arxiv_id":"2108.09274","paper":"/paper/mg-gan-a-multi-generator-model-preventing-out","title":"MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Prediction","date":"2021-08-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"selflein/MG-GAN","path":"mggan/model/modules/discriminators.py","file_url":"https://github.com/selflein/MG-GAN/blob/HEAD/mggan/model/modules/discriminators.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8a8a07750d95c720","mcp_get_code":{"code_sha256":"8a8a07750d95c720"}},{"arxiv_id":"2106.10891","paper":"/paper/open-set-label-noise-can-improve-robustness","title":"Open-set Label Noise Can Improve Robustness Against Inherent Label Noise","date":"2021-06-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hongxin001/JoCoR","path":"algorithm/jocor.py","file_url":"https://github.com/hongxin001/JoCoR/blob/HEAD/algorithm/jocor.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c15655fa5cf01c52","mcp_get_code":{"code_sha256":"c15655fa5cf01c52"}},{"arxiv_id":"2105.12628","paper":"/paper/predict-then-interpolate-a-simple-algorithm","title":"Predict then Interpolate: A Simple Algorithm to Learn Stable Classifiers","date":"2021-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YujiaBao/Predict-then-Interpolate","path":"src/training/ours.py","file_url":"https://github.com/YujiaBao/Predict-then-Interpolate/blob/HEAD/src/training/ours.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ca25c33b3ca5cfdf","mcp_get_code":{"code_sha256":"ca25c33b3ca5cfdf"}},{"arxiv_id":"2105.04100","paper":"/paper/z-gcnets-time-zigzags-at-graph-convolutional","title":"Z-GCNETs: Time Zigzags at Graph Convolutional Networks for Time Series Forecasting","date":"2021-05-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Z-GCNETs/Z-GCNETs","path":"model/ZGCNETs.py","file_url":"https://github.com/Z-GCNETs/Z-GCNETs/blob/HEAD/model/ZGCNETs.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ace626efd2e7365c","mcp_get_code":{"code_sha256":"ace626efd2e7365c"}},{"arxiv_id":"2002.05780","paper":"/paper/reinforcement-learning-based-portfolio","title":"Reinforcement-Learning based Portfolio Management with Augmented Asset Movement Prediction States","date":"2020-02-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"andreaslillevangbech/PortfolioManager-pytorch","path":"src/agent.py","file_url":"https://github.com/andreaslillevangbech/PortfolioManager-pytorch/blob/HEAD/src/agent.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e8f4b1f1ba324a4b","mcp_get_code":{"code_sha256":"e8f4b1f1ba324a4b"}},{"arxiv_id":"1802.03268","paper":"/paper/efficient-neural-architecture-search-via-1","title":"Efficient Neural Architecture Search via Parameter Sharing","date":"2018-02-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MengTianjian/enas-pytorch","path":"micro_child.py","file_url":"https://github.com/MengTianjian/enas-pytorch/blob/HEAD/micro_child.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":"eab22bd84e3559c2","mcp_get_code":{"code_sha256":"eab22bd84e3559c2"}},{"arxiv_id":"1704.00028","paper":"/paper/improved-training-of-wasserstein-gans","title":"Improved Training of Wasserstein GANs","date":"2017-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dylanell/wasserstein-gan","path":"model/wasserstein_gan.py","file_url":"https://github.com/dylanell/wasserstein-gan/blob/HEAD/model/wasserstein_gan.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0ec8f070b436bb82","mcp_get_code":{"code_sha256":"0ec8f070b436bb82"}},{"arxiv_id":"1702.05373","paper":"/paper/emnist-an-extension-of-mnist-to-handwritten","title":"EMNIST: an extension of MNIST to handwritten letters","date":"2017-02-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Lornatang/TensorFlow-MNIST","path":"v0_2/models.py","file_url":"https://github.com/Lornatang/TensorFlow-MNIST/blob/HEAD/v0_2/models.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":"640fbef861b1331b","mcp_get_code":{"code_sha256":"640fbef861b1331b"}},{"arxiv_id":"1612.03897","paper":"/paper/inverse-compositional-spatial-transformer","title":"Inverse Compositional Spatial Transformer Networks","date":"2016-12-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chenhsuanlin/inverse-compositional-STN","path":"MNIST-tensorflow/graph.py","file_url":"https://github.com/chenhsuanlin/inverse-compositional-STN/blob/HEAD/MNIST-tensorflow/graph.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"18200a028bb94600","mcp_get_code":{"code_sha256":"18200a028bb94600"}},{"arxiv_id":"1612.03897","paper":"/paper/inverse-compositional-spatial-transformer","title":"Inverse Compositional Spatial Transformer Networks","date":"2016-12-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chenhsuanlin/inverse-compositional-STN","path":"traffic-sign-tensorflow/graph.py","file_url":"https://github.com/chenhsuanlin/inverse-compositional-STN/blob/HEAD/traffic-sign-tensorflow/graph.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"927d2eba9569f165","mcp_get_code":{"code_sha256":"927d2eba9569f165"}},{"arxiv_id":"1608.06993","paper":"/paper/densely-connected-convolutional-networks","title":"Densely Connected Convolutional Networks","date":"2016-08-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lionelmessi6410/ntga","path":"models/cnn.py","file_url":"https://github.com/lionelmessi6410/ntga/blob/HEAD/models/cnn.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":"58b75b74e06f3539","mcp_get_code":{"code_sha256":"58b75b74e06f3539"}},{"arxiv_id":"1605.07146","paper":"/paper/wide-residual-networks","title":"Wide Residual Networks","date":"2016-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YeongHyeon/WideResNet_WRN-TF2","path":"source/neuralnet.py","file_url":"https://github.com/YeongHyeon/WideResNet_WRN-TF2/blob/HEAD/source/neuralnet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"91bc66bcedbb1076","mcp_get_code":{"code_sha256":"91bc66bcedbb1076"}},{"arxiv_id":"1512.03385","paper":"/paper/deep-residual-learning-for-image-recognition","title":"Deep Residual Learning for Image Recognition","date":"2015-12-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ls-da3m0ns/Short-ResNet","path":"model/network.py","file_url":"https://github.com/ls-da3m0ns/Short-ResNet/blob/HEAD/model/network.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"8c75ed360f4ed07d","mcp_get_code":{"code_sha256":"8c75ed360f4ed07d"}},{"arxiv_id":"1509.06461","paper":"/paper/deep-reinforcement-learning-with-double-q","title":"Deep Reinforcement Learning with Double Q-learning","date":"2015-09-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ifestus/rl","path":"dqn/dqn.py","file_url":"https://github.com/ifestus/rl/blob/HEAD/dqn/dqn.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"39984e4ec10e928e","mcp_get_code":{"code_sha256":"39984e4ec10e928e"}},{"arxiv_id":"1312.5602","paper":"/paper/playing-atari-with-deep-reinforcement","title":"Playing Atari with Deep Reinforcement Learning","date":"2013-12-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"FauzaanQureshi/deep-Q-learning","path":"CNN.py","file_url":"https://github.com/FauzaanQureshi/deep-Q-learning/blob/HEAD/CNN.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ed92e17b3aae8048","mcp_get_code":{"code_sha256":"ed92e17b3aae8048"}},{"arxiv_id":"1312.5602","paper":"/paper/playing-atari-with-deep-reinforcement","title":"Playing Atari with Deep Reinforcement Learning","date":"2013-12-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"parilo/rl-server","path":"tf_rl/conv_model.py","file_url":"https://github.com/parilo/rl-server/blob/HEAD/tf_rl/conv_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"986b511bd19889fc","mcp_get_code":{"code_sha256":"986b511bd19889fc"}}]}