{"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/preactresnet18","entry":"PreActResNet18","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":38,"n_papers_ran":19,"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":26,"n_samples_ran":12,"n_samples_fingerprinted":0,"n_places":40,"n_places_pointer_only":14,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":0,"ran":9,"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":"2606.00738","paper":"/paper/arxiv-2606-00738","title":"SORA: Free Second-Order Attacks in Fast Adversarial Training","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"HuangZhiChao95/ATAS","path":"models/preact_resnet.py","file_url":"https://github.com/HuangZhiChao95/ATAS/blob/HEAD/models/preact_resnet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"40db4256aab2ed92","mcp_get_code":{"code_sha256":"40db4256aab2ed92"}},{"arxiv_id":"2606.00738","paper":"/paper/arxiv-2606-00738","title":"SORA: Free Second-Order Attacks in Fast Adversarial Training","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"tmllab/2023_NeurIPS_AAER","path":"CIFAR10/preact_resnet.py","file_url":"https://github.com/tmllab/2023_NeurIPS_AAER/blob/HEAD/CIFAR10/preact_resnet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0234f49f9592dec8","mcp_get_code":{"code_sha256":"0234f49f9592dec8"}},{"arxiv_id":"2601.03805","paper":"/paper/arxiv-2601-03805","title":"Detecting Semantic Backdoors in a Mystery Shopping Scenario","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"szegedai/SemanticBackdoorDetection","path":"models/preact_resnet.py","file_url":"https://github.com/szegedai/SemanticBackdoorDetection/blob/HEAD/models/preact_resnet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a55348359ff9d8f1","mcp_get_code":{"code_sha256":"a55348359ff9d8f1"}},{"arxiv_id":"2406.01494","paper":"/paper/robust-classification-by-coupling-data","title":"Robust Classification by Coupling Data Mollification with Label Smoothing","date":"2024-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"markusheinonen/supervised-mollification","path":"src/networks/presnet.py","file_url":"https://github.com/markusheinonen/supervised-mollification/blob/HEAD/src/networks/presnet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"397de955665b5839","mcp_get_code":{"code_sha256":"397de955665b5839"}},{"arxiv_id":"2406.01130","paper":null,"title":"arXiv:2406.01130","date":null,"month_inferred_from_arxiv_id":"2024-06","title_source":null,"repo":"skezle/sava","path":"models/preact_resnet.py","file_url":"https://github.com/skezle/sava/blob/HEAD/models/preact_resnet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"84bbb44718624598","mcp_get_code":{"code_sha256":"84bbb44718624598"}},{"arxiv_id":"2406.00816","paper":"/paper/invisible-backdoor-attacks-on-diffusion","title":"Invisible Backdoor Attacks on Diffusion Models","date":"2024-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"linweiii/backdoordm","path":"classifier_models/preact_resnet.py","file_url":"https://github.com/linweiii/backdoordm/blob/HEAD/classifier_models/preact_resnet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4427a19ae0928cb2","mcp_get_code":{"code_sha256":"4427a19ae0928cb2"}},{"arxiv_id":"2405.17613","paper":"/paper/a-framework-for-multi-modal-learning-jointly","title":"Jointly Modeling Inter- & Intra-Modality Dependencies for Multi-modal Learning","date":"2024-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"divyam3897/i2m2","path":"fastMRI/models/preactresnet_knee.py","file_url":"https://github.com/divyam3897/i2m2/blob/HEAD/fastMRI/models/preactresnet_knee.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"96037b0c5b8c3511","mcp_get_code":{"code_sha256":"96037b0c5b8c3511"}},{"arxiv_id":"2405.16262","paper":"/paper/layer-aware-analysis-of-catastrophic","title":"Layer-Aware Analysis of Catastrophic Overfitting: Revealing the Pseudo-Robust Shortcut Dependency","date":"2024-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tmllab/2024_ICML_LAP","path":"CIFAR10/preact_resnet.py","file_url":"https://github.com/tmllab/2024_ICML_LAP/blob/HEAD/CIFAR10/preact_resnet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0234f49f9592dec8","mcp_get_code":{"code_sha256":"0234f49f9592dec8"}},{"arxiv_id":"2405.16262","paper":"/paper/layer-aware-analysis-of-catastrophic","title":"Layer-Aware Analysis of Catastrophic Overfitting: Revealing the Pseudo-Robust Shortcut Dependency","date":"2024-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tmllab/2024_ICML_LAP","path":"Tiny-imagenet/preact_resnet.py","file_url":"https://github.com/tmllab/2024_ICML_LAP/blob/HEAD/Tiny-imagenet/preact_resnet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"12838ecee21bc861","mcp_get_code":{"code_sha256":"12838ecee21bc861"}},{"arxiv_id":"2405.01817","paper":"/paper/uniformly-stable-algorithms-for-adversarial","title":"Uniformly Stable Algorithms for Adversarial Training and Beyond","date":"2024-05-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jiancongxiao/moreau-envelope-sgd","path":"adversarial_robustness_overfitting/preactresnet.py","file_url":"https://github.com/jiancongxiao/moreau-envelope-sgd/blob/HEAD/adversarial_robustness_overfitting/preactresnet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1153837ba4a94242","mcp_get_code":{"code_sha256":"1153837ba4a94242"}},{"arxiv_id":"2404.11265","paper":"/paper/the-victim-and-the-beneficiary-exploiting-a-1","title":"The Victim and The Beneficiary: Exploiting a Poisoned Model to Train a Clean Model on Poisoned Data","date":"2024-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zixuan-zhu/vab","path":"models/preact_resnet.py","file_url":"https://github.com/zixuan-zhu/vab/blob/HEAD/models/preact_resnet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a55348359ff9d8f1","mcp_get_code":{"code_sha256":"a55348359ff9d8f1"}},{"arxiv_id":"2404.08154","paper":"/paper/eliminating-catastrophic-overfitting-via-1","title":"Eliminating Catastrophic Overfitting Via Abnormal Adversarial Examples Regularization","date":"2024-04-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tmllab/2023_neurips_aaer","path":"CIFAR10/preact_resnet.py","file_url":"https://github.com/tmllab/2023_neurips_aaer/blob/HEAD/CIFAR10/preact_resnet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0234f49f9592dec8","mcp_get_code":{"code_sha256":"0234f49f9592dec8"}},{"arxiv_id":"2402.01879","paper":"/paper/s-zero-gradient-based-optimization-of-ell-0","title":"$σ$-zero: Gradient-based Optimization of $\\ell_0$-norm Adversarial Examples","date":"2024-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cinofix/sigma-zero-adversarial-attack","path":"models/cifar10/preact_resnet.py","file_url":"https://github.com/cinofix/sigma-zero-adversarial-attack/blob/HEAD/models/cifar10/preact_resnet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"88e37f205195a51a","mcp_get_code":{"code_sha256":"88e37f205195a51a"}},{"arxiv_id":"2401.12532","paper":"/paper/dafa-distance-aware-fair-adversarial-training","title":"DAFA: Distance-Aware Fair Adversarial Training","date":"2024-01-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rucy74/DAFA","path":"models/preact_resnet.py","file_url":"https://github.com/rucy74/DAFA/blob/HEAD/models/preact_resnet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1153837ba4a94242","mcp_get_code":{"code_sha256":"1153837ba4a94242"}},{"arxiv_id":"2311.07444","paper":"/paper/on-the-robustness-of-neural-collapse-and-the","title":"On the Robustness of Neural Collapse and the Neural Collapse of Robustness","date":"2023-11-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jingtongsu/robust_neural_collapse","path":"preactresnet.py","file_url":"https://github.com/jingtongsu/robust_neural_collapse/blob/HEAD/preactresnet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ab48c8c3bd0271a7","mcp_get_code":{"code_sha256":"ab48c8c3bd0271a7"}},{"arxiv_id":"2310.08847","paper":"/paper/on-the-over-memorization-during-natural","title":"On the Over-Memorization During Natural, Robust and Catastrophic Overfitting","date":"2023-10-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tmllab/2024_ICLR_DOM","path":"preactresnet.py","file_url":"https://github.com/tmllab/2024_ICLR_DOM/blob/HEAD/preactresnet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1153837ba4a94242","mcp_get_code":{"code_sha256":"1153837ba4a94242"}},{"arxiv_id":"2308.12857","paper":"/paper/fast-adversarial-training-with-smooth","title":"Fast Adversarial Training with Smooth Convergence","date":"2023-08-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"FAT-CS/ConvergeSmooth","path":"models/preact_resnet.py","file_url":"https://github.com/FAT-CS/ConvergeSmooth/blob/HEAD/models/preact_resnet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"10a42e5434d0fdcd","mcp_get_code":{"code_sha256":"10a42e5434d0fdcd"}},{"arxiv_id":"2308.06703","paper":"/paper/understanding-the-robustness-difference","title":"Understanding the robustness difference between stochastic gradient descent and adaptive gradient methods","date":"2023-08-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"averyma/opt-robust","path":"models/preact_resnet.py","file_url":"https://github.com/averyma/opt-robust/blob/HEAD/models/preact_resnet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6bc11692e189a289","mcp_get_code":{"code_sha256":"6bc11692e189a289"}},{"arxiv_id":"2307.11565","paper":"/paper/fmt-removing-backdoor-feature-maps-via","title":"Adversarial Feature Map Pruning for Backdoor","date":"2023-07-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"retsuh-bqw/FMP","path":"models/preact_resnet.py","file_url":"https://github.com/retsuh-bqw/FMP/blob/HEAD/models/preact_resnet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a55348359ff9d8f1","mcp_get_code":{"code_sha256":"a55348359ff9d8f1"}},{"arxiv_id":"2307.10562","paper":"/paper/shared-adversarial-unlearning-backdoor","title":"Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples","date":"2023-07-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shawkui/Shared_Adversarial_Unlearning","path":"models/preact_resnet.py","file_url":"https://github.com/shawkui/Shared_Adversarial_Unlearning/blob/HEAD/models/preact_resnet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a55348359ff9d8f1","mcp_get_code":{"code_sha256":"a55348359ff9d8f1"}},{"arxiv_id":"2303.02251","paper":"/paper/certified-robust-neural-networks","title":"Certified Robust Neural Networks: Generalization and Corruption Resistance","date":"2023-03-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ryanlucas3/hr_neural_networks","path":"HR_Neural_Networks/Paper_experiments/Section_6.2/preactresnet.py","file_url":"https://github.com/ryanlucas3/hr_neural_networks/blob/HEAD/HR_Neural_Networks/Paper_experiments/Section_6.2/preactresnet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1153837ba4a94242","mcp_get_code":{"code_sha256":"1153837ba4a94242"}},{"arxiv_id":"2302.11408","paper":"/paper/asset-robust-backdoor-data-detection-across-a","title":"ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning Paradigms","date":"2023-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ruoxi-jia-group/asset","path":"models/preact_resnet.py","file_url":"https://github.com/ruoxi-jia-group/asset/blob/HEAD/models/preact_resnet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b6e5f24824f19914","mcp_get_code":{"code_sha256":"b6e5f24824f19914"}},{"arxiv_id":"2302.08872","paper":"/paper/revisiting-adversarial-training-for-the-worst","title":"Revisiting adversarial training for the worst-performing class","date":"2023-02-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lions-epfl/class-focused-online-learning-code","path":"cfol/preactresnet.py","file_url":"https://github.com/lions-epfl/class-focused-online-learning-code/blob/HEAD/cfol/preactresnet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1153837ba4a94242","mcp_get_code":{"code_sha256":"1153837ba4a94242"}},{"arxiv_id":"2210.15127","paper":"/paper/rethinking-the-reverse-engineering-of-trojan","title":"Rethinking the Reverse-engineering of Trojan Triggers","date":"2022-10-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ru-system-software-and-security/featurere","path":"models/preact_resnet.py","file_url":"https://github.com/ru-system-software-and-security/featurere/blob/HEAD/models/preact_resnet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8c9f324e2ca8f8ff","mcp_get_code":{"code_sha256":"8c9f324e2ca8f8ff"}},{"arxiv_id":"2210.09852","paper":"/paper/scaling-adversarial-training-to-large","title":"Scaling Adversarial Training to Large Perturbation Bounds","date":"2022-10-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"val-iisc/OAAT","path":"models/preactresnet.py","file_url":"https://github.com/val-iisc/OAAT/blob/HEAD/models/preactresnet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6720f86e06ca335e","mcp_get_code":{"code_sha256":"6720f86e06ca335e"}},{"arxiv_id":"2210.03543","paper":"/paper/a2-efficient-automated-attacker-for-boosting","title":"A2: Efficient Automated Attacker for Boosting Adversarial Training","date":"2022-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alipay/A2-efficient-automated-attacker-for-boosting-adversarial-training","path":"preactresnet.py","file_url":"https://github.com/alipay/A2-efficient-automated-attacker-for-boosting-adversarial-training/blob/HEAD/preactresnet.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":"1153837ba4a94242","mcp_get_code":{"code_sha256":"1153837ba4a94242"}},{"arxiv_id":"2205.13383","paper":"/paper/bppattack-stealthy-and-efficient-trojan","title":"BppAttack: Stealthy and Efficient Trojan Attacks against Deep Neural Networks via Image Quantization and Contrastive Adversarial Learning","date":"2022-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ru-system-software-and-security/bppattack","path":"classifier_models/preact_resnet.py","file_url":"https://github.com/ru-system-software-and-security/bppattack/blob/HEAD/classifier_models/preact_resnet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"009ef5196808279a","mcp_get_code":{"code_sha256":"009ef5196808279a"}},{"arxiv_id":"2204.03714","paper":"/paper/using-multiple-self-supervised-tasks-improves","title":"Using Multiple Self-Supervised Tasks Improves Model Robustness","date":"2022-04-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mattlawhon/SelfSupDefense","path":"learning/preactresnet.py","file_url":"https://github.com/mattlawhon/SelfSupDefense/blob/HEAD/learning/preactresnet.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":"1153837ba4a94242","mcp_get_code":{"code_sha256":"1153837ba4a94242"}},{"arxiv_id":"2202.14026","paper":"/paper/robust-training-under-label-noise-by-over","title":"Robust Training under Label Noise by Over-parameterization","date":"2022-02-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shengliu66/sop","path":"model/PreResNet.py","file_url":"https://github.com/shengliu66/sop/blob/HEAD/model/PreResNet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bf41d63bb259c163","mcp_get_code":{"code_sha256":"bf41d63bb259c163"}},{"arxiv_id":"2103.17268","paper":"/paper/fast-certified-robust-training-via-better","title":"Fast Certified Robust Training with Short Warmup","date":"2021-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shizhouxing/Fast-Certified-Robust-Training","path":"models/resnet.py","file_url":"https://github.com/shizhouxing/Fast-Certified-Robust-Training/blob/HEAD/models/resnet.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":"abc02d2c96c29b28","mcp_get_code":{"code_sha256":"abc02d2c96c29b28"}},{"arxiv_id":"2103.14222","paper":"/paper/adversarial-attacks-are-reversible-with","title":"Adversarial Attacks are Reversible with Natural Supervision","date":"2021-03-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cvlab-columbia/SelfSupDefense","path":"learning/preactresnet.py","file_url":"https://github.com/cvlab-columbia/SelfSupDefense/blob/HEAD/learning/preactresnet.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":"1153837ba4a94242","mcp_get_code":{"code_sha256":"1153837ba4a94242"}},{"arxiv_id":"2009.08325","paper":"/paper/noisy-concurrent-training-for-efficient","title":"Noisy Concurrent Training for Efficient Learning under Label Noise","date":"2020-09-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NeurAI-Lab/NCT","path":"models/preact_resnet.py","file_url":"https://github.com/NeurAI-Lab/NCT/blob/HEAD/models/preact_resnet.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"08458e1871e2fd5f","mcp_get_code":{"code_sha256":"08458e1871e2fd5f"}},{"arxiv_id":"2003.04887","paper":"/paper/rezero-is-all-you-need-fast-convergence-at","title":"ReZero is All You Need: Fast Convergence at Large Depth","date":"2020-03-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"statsu1990/ReZero-Cifar100","path":"src/model/rezero_preact_resnet.py","file_url":"https://github.com/statsu1990/ReZero-Cifar100/blob/HEAD/src/model/rezero_preact_resnet.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"09aa6bbcdc551903","mcp_get_code":{"code_sha256":"09aa6bbcdc551903"}},{"arxiv_id":"2001.03994","paper":"/paper/fast-is-better-than-free-revisiting-1","title":"Fast is better than free: Revisiting adversarial training","date":"2020-01-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tml-epfl/understanding-fast-adv-training","path":"models.py","file_url":"https://github.com/tml-epfl/understanding-fast-adv-training/blob/HEAD/models.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fa636f649fc7a458","mcp_get_code":{"code_sha256":"fa636f649fc7a458"}},{"arxiv_id":"1907.04371","paper":"/paper/a-stochastic-first-order-method-for-ordered","title":"Ordered SGD: A New Stochastic Optimization Framework for Empirical Risk Minimization","date":"2019-07-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kenjikawaguchi/qSGD","path":"models/preact_resnet.py","file_url":"https://github.com/kenjikawaguchi/qSGD/blob/HEAD/models/preact_resnet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"61182bd4fcf9cc8d","mcp_get_code":{"code_sha256":"61182bd4fcf9cc8d"}},{"arxiv_id":"1905.11926","paper":"/paper/190511926","title":"Network Deconvolution","date":"2019-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"deconvolutionpaper/deconvolution","path":"models/preact_resnet.py","file_url":"https://github.com/deconvolutionpaper/deconvolution/blob/HEAD/models/preact_resnet.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":"8b6f2206042fed23","mcp_get_code":{"code_sha256":"8b6f2206042fed23"}},{"arxiv_id":"1710.09412","paper":"/paper/mixup-beyond-empirical-risk-minimization","title":"mixup: Beyond Empirical Risk Minimization","date":"2017-10-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leehomyc/mixup_pytorch","path":"models/preact_resnet.py","file_url":"https://github.com/leehomyc/mixup_pytorch/blob/HEAD/models/preact_resnet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b6e5f24824f19914","mcp_get_code":{"code_sha256":"b6e5f24824f19914"}},{"arxiv_id":"aaai_29250","paper":null,"title":"arXiv:aaai_29250","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Feng-peng-Li/Regroup-Loss-Median-to-Combat-Label-Noise","path":"networks/ResNet.py","file_url":"https://github.com/Feng-peng-Li/Regroup-Loss-Median-to-Combat-Label-Noise/blob/HEAD/networks/ResNet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9d76ba3eb64583df","mcp_get_code":{"code_sha256":"9d76ba3eb64583df"}},{"arxiv_id":"aaai_28019","paper":null,"title":"arXiv:aaai_28019","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"VinAIResearch/COMBAT","path":"classifier_models/preact_resnet.py","file_url":"https://github.com/VinAIResearch/COMBAT/blob/HEAD/classifier_models/preact_resnet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1dfacc8b74dc8780","mcp_get_code":{"code_sha256":"1dfacc8b74dc8780"}},{"arxiv_id":"Pang_Backdoor_Cleansing_With_Unlabeled_Data_CVPR_2023_paper","paper":null,"title":"arXiv:Pang_Backdoor_Cleansing_With_Unlabeled_Data_CVPR_2023_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"luluppang/BCU","path":"models/preact_resnet.py","file_url":"https://github.com/luluppang/BCU/blob/HEAD/models/preact_resnet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a55348359ff9d8f1","mcp_get_code":{"code_sha256":"a55348359ff9d8f1"}}]}