{"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/clamp","entry":"clamp","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":78,"n_papers_ran":34,"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":33,"n_samples_ran":20,"n_samples_fingerprinted":14,"n_places":79,"n_places_pointer_only":28,"by_status":{"ran_honours":4,"ran_violates":1,"ran_draft_wrong":4,"ran_fixture":2,"ran":9,"unverified":13},"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":"2606.30966","paper":"/paper/arxiv-2606-30966","title":"HYPOLE: Hyperproperty-Guided Multi-Agent Reinforcement Learning under Partial Observation","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"oxwhirl/smac","path":"smac/env/starcraft2/render.py","file_url":"https://github.com/oxwhirl/smac/blob/HEAD/smac/env/starcraft2/render.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"768c86dee853b804","mcp_get_code":{"code_sha256":"768c86dee853b804"}},{"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":"LIONS-EPFL/ELLE","path":"eval_pgd50-10.py","file_url":"https://github.com/LIONS-EPFL/ELLE/blob/HEAD/eval_pgd50-10.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0beec913c324c82a","mcp_get_code":{"code_sha256":"0beec913c324c82a"}},{"arxiv_id":"2605.17453","paper":"/paper/arxiv-2605-17453","title":"Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"idwts/TRUST-BENCH","path":"code/risk_utils.py","file_url":"https://github.com/idwts/TRUST-BENCH/blob/HEAD/code/risk_utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f8527531e86cc660","mcp_get_code":{"code_sha256":"f8527531e86cc660"}},{"arxiv_id":"2605.12960","paper":"/paper/arxiv-2605-12960","title":"DiM 3 : Bridging Multilingual and Multimodal Models via Direction-and Magnitude-Aware Merging","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"wzj1718/DiM3","path":"merge/merging_methods/pcb_merging.py","file_url":"https://github.com/wzj1718/DiM3/blob/HEAD/merge/merging_methods/pcb_merging.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"76418510bf7df06d","mcp_get_code":{"code_sha256":"76418510bf7df06d"}},{"arxiv_id":"2603.15020","paper":"/paper/arxiv-2603-15020","title":"MER-Bench: A Comprehensive Benchmark for Multimodal Meme Reappraisal","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"one-seven17/MER-Bench","path":"results/figure_5_a-n.py","file_url":"https://github.com/one-seven17/MER-Bench/blob/HEAD/results/figure_5_a-n.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3ea4fe9a8337eb9e","mcp_get_code":{"code_sha256":"3ea4fe9a8337eb9e"}},{"arxiv_id":"2602.10230","paper":"/paper/arxiv-2602-10230","title":"Encode Once, Decode Never: Reusing Audio LM Internals for Efficient Temporal Localization","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"inkitori/taudio","path":"tasks/timestamp_all.py","file_url":"https://github.com/inkitori/taudio/blob/HEAD/tasks/timestamp_all.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"768c86dee853b804","mcp_get_code":{"code_sha256":"768c86dee853b804"}},{"arxiv_id":"2512.12997","paper":"/paper/arxiv-2512-12997","title":"Calibrating Uncertainty for Zero-Shot Adversarial CLIP","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"VivienLu/UCAT","path":"attacks.py","file_url":"https://github.com/VivienLu/UCAT/blob/HEAD/attacks.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8a93e041134b597a","mcp_get_code":{"code_sha256":"8a93e041134b597a"}},{"arxiv_id":"2512.10275","paper":"/paper/arxiv-2512-10275","title":"Sample-wise Adaptive Weighting for Transfer Consistency in Adversarial Distillation","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"HongsinLee/saad","path":"attacks.py","file_url":"https://github.com/HongsinLee/saad/blob/HEAD/attacks.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e4e96565ba2bec7a","mcp_get_code":{"code_sha256":"e4e96565ba2bec7a"}},{"arxiv_id":"2510.10000","paper":"/paper/arxiv-2510-10000","title":"Tight Robustness Certificates and Wasserstein Distributional Attacks for Deep Neural Networks","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"OLab-Repo/WDA","path":"wda.py","file_url":"https://github.com/OLab-Repo/WDA/blob/HEAD/wda.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c09cbca10020bb47","mcp_get_code":{"code_sha256":"c09cbca10020bb47"}},{"arxiv_id":"2503.03613","paper":"/paper/clip-is-strong-enough-to-fight-back-test-time","title":"CLIP is Strong Enough to Fight Back: Test-time Counterattacks towards Zero-shot Adversarial Robustness of CLIP","date":"2025-03-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"8a93e041134b597a","mcp_get_code":{"code_sha256":"8a93e041134b597a"}},{"arxiv_id":"2502.17159","paper":"/paper/parameter-efficient-merging-for-multimodal","title":"Parameter Efficient Merging for Multimodal Large Language Models with Complementary Parameter Adaptation","date":"2025-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"683ad0be49559242","mcp_get_code":{"code_sha256":"683ad0be49559242"}},{"arxiv_id":"2410.21802","paper":"/paper/text-guided-attention-is-all-you-need-for","title":"Text-Guided Attention is All You Need for Zero-Shot Robustness in Vision-Language Models","date":"2024-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhyblue424/TGA-ZSR","path":"attacks.py","file_url":"https://github.com/zhyblue424/TGA-ZSR/blob/HEAD/attacks.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8a93e041134b597a","mcp_get_code":{"code_sha256":"8a93e041134b597a"}},{"arxiv_id":"2410.02396","paper":"/paper/parameter-competition-balancing-for-model","title":"Parameter Competition Balancing for Model Merging","date":"2024-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"duguodong7/pcb-merging","path":"pcb-merging.py","file_url":"https://github.com/duguodong7/pcb-merging/blob/HEAD/pcb-merging.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"683ad0be49559242","mcp_get_code":{"code_sha256":"683ad0be49559242"}},{"arxiv_id":"2407.10918","paper":"/paper/partimagenet-dataset-scaling-up-part-based","title":"PartImageNet++ Dataset: Scaling up Part-based Models for Robust Recognition","date":"2024-07-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LixiaoTHU/PartImageNetPP","path":"adv_utils.py","file_url":"https://github.com/LixiaoTHU/PartImageNetPP/blob/HEAD/adv_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8a93e041134b597a","mcp_get_code":{"code_sha256":"8a93e041134b597a"}},{"arxiv_id":"2406.12814","paper":"/paper/adversarial-attacks-on-multimodal-agents","title":"Dissecting Adversarial Robustness of Multimodal LM Agents","date":"2024-06-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chenwu98/agent-attack","path":"agent_attack/attacks/clip_attack.py","file_url":"https://github.com/chenwu98/agent-attack/blob/HEAD/agent_attack/attacks/clip_attack.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6007bd5812bfaa0f","mcp_get_code":{"code_sha256":"6007bd5812bfaa0f"}},{"arxiv_id":"2405.17656","paper":"/paper/alignment-is-key-for-applying-diffusion","title":"Equivariant Denoisers Cannot Copy Graphs: Align Your Graph Diffusion Models","date":"2024-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Aalto-QuML/DiffAlign","path":"diffalign/neuralnet/ema_pytorch.py","file_url":"https://github.com/Aalto-QuML/DiffAlign/blob/HEAD/diffalign/neuralnet/ema_pytorch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e907f76525778206","mcp_get_code":{"code_sha256":"e907f76525778206"}},{"arxiv_id":"2405.17556","paper":"/paper/probabilistic-verification-of-neural-networks-1","title":"Probabilistic Verification of Neural Networks using Branch and Bound","date":"2024-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sen-uni-kn/probspecs","path":"probspecs/operations/clamp.py","file_url":"https://github.com/sen-uni-kn/probspecs/blob/HEAD/probspecs/operations/clamp.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"24efb96a2400ff7e","mcp_get_code":{"code_sha256":"24efb96a2400ff7e"}},{"arxiv_id":"2405.17476","paper":"/paper/how-to-leverage-diverse-demonstrations-in","title":"How to Leverage Diverse Demonstrations in Offline Imitation Learning","date":"2024-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liziniu/ISWBC","path":"atari/experiments/agents/iswbc_agent.py","file_url":"https://github.com/liziniu/ISWBC/blob/HEAD/atari/experiments/agents/iswbc_agent.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3336fdca39b09846","mcp_get_code":{"code_sha256":"3336fdca39b09846"}},{"arxiv_id":"2405.09981","paper":"/paper/adversarial-robustness-for-visual-grounding","title":"Adversarial Robustness for Visual Grounding of Multimodal Large Language Models","date":"2024-05-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"KuofengGao/MLLM-Grounding-Robustness","path":"eval_scripts/target_to_all.py","file_url":"https://github.com/KuofengGao/MLLM-Grounding-Robustness/blob/HEAD/eval_scripts/target_to_all.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"52eb6c41f97993a4","mcp_get_code":{"code_sha256":"52eb6c41f97993a4"}},{"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/mea_train_cifar.py","file_url":"https://github.com/jiancongxiao/moreau-envelope-sgd/blob/HEAD/adversarial_robustness_overfitting/mea_train_cifar.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8a93e041134b597a","mcp_get_code":{"code_sha256":"8a93e041134b597a"}},{"arxiv_id":"2404.19287","paper":"/paper/revisiting-the-adversarial-robustness-of","title":"Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspective","date":"2024-04-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ellezwq/mmcoa","path":"attacks.py","file_url":"https://github.com/ellezwq/mmcoa/blob/HEAD/attacks.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8a93e041134b597a","mcp_get_code":{"code_sha256":"8a93e041134b597a"}},{"arxiv_id":"2403.17343","paper":"/paper/language-models-are-free-boosters-for","title":"Residual-based Language Models are Free Boosters for Biomedical Imaging","date":"2024-03-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhixinlai/llmboostmedical","path":"2D_classification/engine.py","file_url":"https://github.com/zhixinlai/llmboostmedical/blob/HEAD/2D_classification/engine.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8a93e041134b597a","mcp_get_code":{"code_sha256":"8a93e041134b597a"}},{"arxiv_id":"2403.14774","paper":"/paper/few-shot-adversarial-prompt-learning-on","title":"Few-Shot Adversarial Prompt Learning on Vision-Language Models","date":"2024-03-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lionel-w2/FAP","path":"attack/pgd.py","file_url":"https://github.com/lionel-w2/FAP/blob/HEAD/attack/pgd.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8a93e041134b597a","mcp_get_code":{"code_sha256":"8a93e041134b597a"}},{"arxiv_id":"2402.17144","paper":"/paper/metasql-a-generate-then-rank-framework-for","title":"Metasql: A Generate-then-Rank Framework for Natural Language to SQL Translation","date":"2024-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Kaimary/MetaSQL","path":"allenmodels/dataset_readers/enc_preproc.py","file_url":"https://github.com/Kaimary/MetaSQL/blob/HEAD/allenmodels/dataset_readers/enc_preproc.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":"6bef2da47f1a8400","mcp_get_code":{"code_sha256":"6bef2da47f1a8400"}},{"arxiv_id":"2402.08567","paper":"/paper/agent-smith-a-single-image-can-jailbreak-one","title":"Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast","date":"2024-02-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sail-sg/Agent-Smith","path":"attack/optimize.py","file_url":"https://github.com/sail-sg/Agent-Smith/blob/HEAD/attack/optimize.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3936f167deef1650","mcp_get_code":{"code_sha256":"3936f167deef1650"}},{"arxiv_id":"2402.02316","paper":"/paper/your-diffusion-model-is-secretly-a","title":"Diffusion Models are Certifiably Robust Classifiers","date":"2024-02-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"huanranchen/NoisedDiffusionClassifiers","path":"attacks/utils.py","file_url":"https://github.com/huanranchen/NoisedDiffusionClassifiers/blob/HEAD/attacks/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6007bd5812bfaa0f","mcp_get_code":{"code_sha256":"6007bd5812bfaa0f"}},{"arxiv_id":"2401.11618","paper":"/paper/efficient-local-linearity-regularization-to","title":"Efficient local linearity regularization to overcome catastrophic overfitting","date":"2024-01-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lions-epfl/elle","path":"core/models/SLAT_hidden_module.py","file_url":"https://github.com/lions-epfl/elle/blob/HEAD/core/models/SLAT_hidden_module.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1e4ac7a9e6dd4298","mcp_get_code":{"code_sha256":"1e4ac7a9e6dd4298"}},{"arxiv_id":"2312.01473","paper":"/paper/regularity-as-intrinsic-reward-for-free-play-1","title":"Regularity as Intrinsic Reward for Free Play","date":"2023-12-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"orybkin/lexa-benchmark","path":"d4rl/carla/carla_env.py","file_url":"https://github.com/orybkin/lexa-benchmark/blob/HEAD/d4rl/carla/carla_env.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ccc25780948874cb","mcp_get_code":{"code_sha256":"ccc25780948874cb"}},{"arxiv_id":"2310.12973","paper":"/paper/frozen-transformers-in-language-models-are","title":"Frozen Transformers in Language Models Are Effective Visual Encoder Layers","date":"2023-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ziqipang/lm4visualencoding","path":"image_classification/engine.py","file_url":"https://github.com/ziqipang/lm4visualencoding/blob/HEAD/image_classification/engine.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8a93e041134b597a","mcp_get_code":{"code_sha256":"8a93e041134b597a"}},{"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":"DOM.py","file_url":"https://github.com/tmllab/2024_ICLR_DOM/blob/HEAD/DOM.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8a93e041134b597a","mcp_get_code":{"code_sha256":"8a93e041134b597a"}},{"arxiv_id":"2307.03214","paper":"/paper/preadd-prefix-adaptive-decoding-for","title":"PREADD: Prefix-Adaptive Decoding for Controlled Text Generation","date":"2023-07-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jonnypei/acl23-preadd","path":"methods/fudge/util.py","file_url":"https://github.com/jonnypei/acl23-preadd/blob/HEAD/methods/fudge/util.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2f04763df90287b6","mcp_get_code":{"code_sha256":"2f04763df90287b6"}},{"arxiv_id":"2306.07743","paper":"/paper/v-lol-a-diagnostic-dataset-for-visual-logical","title":"V-LoL: A Diagnostic Dataset for Visual Logical Learning","date":"2023-06-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ml-research/vlol-dataset-gen","path":"blender_image_generator/get_b_box.py","file_url":"https://github.com/ml-research/vlol-dataset-gen/blob/HEAD/blender_image_generator/get_b_box.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"97b29bd21738c149","mcp_get_code":{"code_sha256":"97b29bd21738c149"}},{"arxiv_id":"2306.06446","paper":"/paper/shiftaddvit-mixture-of-multiplication-1","title":"ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer","date":"2023-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gatech-eic/shiftaddvit","path":"pvt/deepshift/modules.py","file_url":"https://github.com/gatech-eic/shiftaddvit/blob/HEAD/pvt/deepshift/modules.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":"f3c76f772fb760b8","mcp_get_code":{"code_sha256":"f3c76f772fb760b8"}},{"arxiv_id":"2305.11846","paper":"/paper/any-to-any-generation-via-composable","title":"Any-to-Any Generation via Composable Diffusion","date":"2023-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/i-Code","path":"i-Code-Doc/core/common/utils.py","file_url":"https://github.com/microsoft/i-Code/blob/HEAD/i-Code-Doc/core/common/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"59eacee354fa7772","mcp_get_code":{"code_sha256":"59eacee354fa7772"}},{"arxiv_id":"2303.16570","paper":"/paper/point2vec-for-self-supervised-representation","title":"Point2Vec for Self-Supervised Representation Learning on Point Clouds","date":"2023-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kabouzeid/point2vec","path":"point2vec/modules/EMA.py","file_url":"https://github.com/kabouzeid/point2vec/blob/HEAD/point2vec/modules/EMA.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e907f76525778206","mcp_get_code":{"code_sha256":"e907f76525778206"}},{"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/Rice_HR/Rice_HR.py","file_url":"https://github.com/ryanlucas3/hr_neural_networks/blob/HEAD/HR_Neural_Networks/Paper_experiments/Section_6.2/Rice_HR/Rice_HR.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8a93e041134b597a","mcp_get_code":{"code_sha256":"8a93e041134b597a"}},{"arxiv_id":"2302.13130","paper":"/paper/point-cloud-forecasting-as-a-proxy-for-4d","title":"Point Cloud Forecasting as a Proxy for 4D Occupancy Forecasting","date":"2023-02-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tarashakhurana/4d-occ-forecasting","path":"utils/evaluation.py","file_url":"https://github.com/tarashakhurana/4d-occ-forecasting/blob/HEAD/utils/evaluation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9cb5038bb4debac9","mcp_get_code":{"code_sha256":"9cb5038bb4debac9"}},{"arxiv_id":"2302.12480","paper":"/paper/robust-weight-signatures-gaining-robustness","title":"Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights?","date":"2023-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VITA-Group/Robust_Weight_Signatures","path":"trainer/engine_pgd.py","file_url":"https://github.com/VITA-Group/Robust_Weight_Signatures/blob/HEAD/trainer/engine_pgd.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8a93e041134b597a","mcp_get_code":{"code_sha256":"8a93e041134b597a"}},{"arxiv_id":"2302.01375","paper":"/paper/on-the-robustness-of-randomized-ensembles-to","title":"On the Robustness of Randomized Ensembles to Adversarial Perturbations","date":"2023-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"8a93e041134b597a","mcp_get_code":{"code_sha256":"8a93e041134b597a"}},{"arxiv_id":"2212.03798","paper":"/paper/stochastic-rising-bandits","title":"Stochastic Rising Bandits","date":"2022-12-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"albertometelli/stochastic-rising-bandits","path":"src/reward_model.py","file_url":"https://github.com/albertometelli/stochastic-rising-bandits/blob/HEAD/src/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":"70d16b99ac1b2a81","mcp_get_code":{"code_sha256":"70d16b99ac1b2a81"}},{"arxiv_id":"2212.02623","paper":"/paper/unifying-vision-text-and-layout-for-universal","title":"Unifying Vision, Text, and Layout for Universal Document Processing","date":"2022-12-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DS4SD/MarkushGrapher","path":"markushgrapher/core/common/utils.py","file_url":"https://github.com/DS4SD/MarkushGrapher/blob/HEAD/markushgrapher/core/common/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"59eacee354fa7772","mcp_get_code":{"code_sha256":"59eacee354fa7772"}},{"arxiv_id":"2211.09817","paper":"/paper/on-the-effect-of-pre-training-for-transformer","title":"On the Effect of Pre-training for Transformer in Different Modality on Offline Reinforcement Learning","date":"2022-11-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rail-berkeley/d4rl","path":"d4rl/carla/carla_env.py","file_url":"https://github.com/rail-berkeley/d4rl/blob/HEAD/d4rl/carla/carla_env.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":"ccc25780948874cb","mcp_get_code":{"code_sha256":"ccc25780948874cb"}},{"arxiv_id":"2211.00824","paper":"/paper/adversarial-auto-augment-with-label","title":"Adversarial Auto-Augment with Label Preservation: A Representation Learning Principle Guided Approach","date":"2022-11-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"8a93e041134b597a","mcp_get_code":{"code_sha256":"8a93e041134b597a"}},{"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":"train_cifar10.py","file_url":"https://github.com/alipay/A2-efficient-automated-attacker-for-boosting-adversarial-training/blob/HEAD/train_cifar10.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":"8a93e041134b597a","mcp_get_code":{"code_sha256":"8a93e041134b597a"}},{"arxiv_id":"2210.03209","paper":"/paper/self-adaptive-driving-in-nonstationary","title":"Self-Adaptive Driving in Nonstationary Environments through Conjectural Online Lookahead Adaptation","date":null,"month_inferred_from_arxiv_id":"2022-10","title_source":"archive","repo":"panshark/cola","path":"macad_gym/multi_env.py","file_url":"https://github.com/panshark/cola/blob/HEAD/macad_gym/multi_env.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ccc25780948874cb","mcp_get_code":{"code_sha256":"ccc25780948874cb"}},{"arxiv_id":"2210.03078","paper":"/paper/rainier-reinforced-knowledge-introspector-for","title":"Rainier: Reinforced Knowledge Introspector for Commonsense Question Answering","date":"2022-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liujch1998/rainier","path":"rainier/ppo.py","file_url":"https://github.com/liujch1998/rainier/blob/HEAD/rainier/ppo.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"37a3441d06cf812e","mcp_get_code":{"code_sha256":"37a3441d06cf812e"}},{"arxiv_id":"2208.13049","paper":"/paper/trojvit-trojan-insertion-in-vision","title":"TrojViT: Trojan Insertion in Vision Transformers","date":"2022-08-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mxzheng/trojvit","path":"utils.py","file_url":"https://github.com/mxzheng/trojvit/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8a93e041134b597a","mcp_get_code":{"code_sha256":"8a93e041134b597a"}},{"arxiv_id":"2206.08675","paper":"/paper/understanding-robust-overfitting-of","title":"Understanding Robust Overfitting of Adversarial Training and Beyond","date":"2022-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"8a93e041134b597a","mcp_get_code":{"code_sha256":"8a93e041134b597a"}},{"arxiv_id":"2206.06737","paper":"/paper/adversarial-vulnerability-of-randomized","title":"Adversarial Vulnerability of Randomized Ensembles","date":"2022-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"8a93e041134b597a","mcp_get_code":{"code_sha256":"8a93e041134b597a"}},{"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":"cifar10_defense.py","file_url":"https://github.com/mattlawhon/SelfSupDefense/blob/HEAD/cifar10_defense.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":"8a93e041134b597a","mcp_get_code":{"code_sha256":"8a93e041134b597a"}},{"arxiv_id":"2203.08392","paper":"/paper/patch-fool-are-vision-transformers-always-1","title":"Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations?","date":"2022-03-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RICE-EIC/Patch-Fool","path":"utils.py","file_url":"https://github.com/RICE-EIC/Patch-Fool/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8a93e041134b597a","mcp_get_code":{"code_sha256":"8a93e041134b597a"}},{"arxiv_id":"2202.09844","paper":"/paper/sparsity-winning-twice-better-robust-1","title":"Sparsity Winning Twice: Better Robust Generalization from More Efficient Training","date":"2022-02-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vita-group/sparsity-win-robust-generalization","path":"Robust-Bird/utils/function.py","file_url":"https://github.com/vita-group/sparsity-win-robust-generalization/blob/HEAD/Robust-Bird/utils/function.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0beec913c324c82a","mcp_get_code":{"code_sha256":"0beec913c324c82a"}},{"arxiv_id":"2202.00441","paper":"/paper/few-bit-backward-quantized-gradients-of","title":"Few-Bit Backward: Quantized Gradients of Activation Functions for Memory Footprint Reduction","date":"2022-02-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SkoltechAI/fewbit","path":"fewbit/functional/linear.py","file_url":"https://github.com/SkoltechAI/fewbit/blob/HEAD/fewbit/functional/linear.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":"c8f42186142a2a86","mcp_get_code":{"code_sha256":"c8f42186142a2a86"}},{"arxiv_id":"2110.14871","paper":"/paper/generalized-depthwise-separable-convolutions","title":"Generalized Depthwise-Separable Convolutions for Adversarially Robust and Efficient Neural Networks","date":"2021-10-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"8a93e041134b597a","mcp_get_code":{"code_sha256":"8a93e041134b597a"}},{"arxiv_id":"2110.14068","paper":"/paper/drawing-robust-scratch-tickets-subnetworks","title":"Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networks","date":"2021-10-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RICE-EIC/Robust-Scratch-Ticket","path":"trainers/default.py","file_url":"https://github.com/RICE-EIC/Robust-Scratch-Ticket/blob/HEAD/trainers/default.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8a93e041134b597a","mcp_get_code":{"code_sha256":"8a93e041134b597a"}},{"arxiv_id":"2108.10394","paper":"/paper/dynamic-network-quantization-for-efficient","title":"Dynamic Network Quantization for Efficient Video Inference","date":"2021-08-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sunxm2357/VideoIQ","path":"models/twod_models/ops/twoside_pact.py","file_url":"https://github.com/sunxm2357/VideoIQ/blob/HEAD/models/twod_models/ops/twoside_pact.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"adc9dfd4579470c0","mcp_get_code":{"code_sha256":"adc9dfd4579470c0"}},{"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":"cifar10_defense.py","file_url":"https://github.com/cvlab-columbia/SelfSupDefense/blob/HEAD/cifar10_defense.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":"8a93e041134b597a","mcp_get_code":{"code_sha256":"8a93e041134b597a"}},{"arxiv_id":"2103.12531","paper":"/paper/clip-cheap-lipschitz-training-of-neural","title":"CLIP: Cheap Lipschitz Training of Neural Networks","date":"2021-03-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TimRoith/CLIP","path":"adversarial_attacks.py","file_url":"https://github.com/TimRoith/CLIP/blob/HEAD/adversarial_attacks.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"444c1bca3ed3cae9","mcp_get_code":{"code_sha256":"444c1bca3ed3cae9"}},{"arxiv_id":"2102.07861","paper":"/paper/low-curvature-activations-reduce-overfitting","title":"Low Curvature Activations Reduce Overfitting in Adversarial Training","date":"2021-02-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"8a93e041134b597a","mcp_get_code":{"code_sha256":"8a93e041134b597a"}},{"arxiv_id":"2010.00467","paper":"/paper/bag-of-tricks-for-adversarial-training","title":"Bag of Tricks for Adversarial Training","date":"2020-10-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"8a93e041134b597a","mcp_get_code":{"code_sha256":"8a93e041134b597a"}},{"arxiv_id":"2007.05123","paper":"/paper/improving-adversarial-robustness-by-enforcing","title":"Improving Adversarial Robustness by Enforcing Local and Global Compactness","date":"2020-07-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tuananhbui89/Adversarial-Divergence-Reduction","path":"ADR_pt/adr.py","file_url":"https://github.com/tuananhbui89/Adversarial-Divergence-Reduction/blob/HEAD/ADR_pt/adr.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8a93e041134b597a","mcp_get_code":{"code_sha256":"8a93e041134b597a"}},{"arxiv_id":"2004.07219","paper":"/paper/datasets-for-data-driven-reinforcement","title":"D4RL: Datasets for Deep Data-Driven Reinforcement Learning","date":"2020-04-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"anuragajay/d4rl","path":"d4rl/carla/carla_env.py","file_url":"https://github.com/anuragajay/d4rl/blob/HEAD/d4rl/carla/carla_env.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":"ccc25780948874cb","mcp_get_code":{"code_sha256":"ccc25780948874cb"}},{"arxiv_id":"2004.05884","paper":"/paper/revisiting-loss-landscape-for-adversarial","title":"Adversarial Weight Perturbation Helps Robust Generalization","date":"2020-04-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"csdongxian/AWP","path":"AT_AWP/train_cifar10.py","file_url":"https://github.com/csdongxian/AWP/blob/HEAD/AT_AWP/train_cifar10.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8a93e041134b597a","mcp_get_code":{"code_sha256":"8a93e041134b597a"}},{"arxiv_id":"2003.01690","paper":"/paper/reliable-evaluation-of-adversarial-robustness","title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks","date":"2020-03-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"locuslab/robust_overfitting","path":"train_cifar.py","file_url":"https://github.com/locuslab/robust_overfitting/blob/HEAD/train_cifar.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8a93e041134b597a","mcp_get_code":{"code_sha256":"8a93e041134b597a"}},{"arxiv_id":"2002.11569","paper":"/paper/overfitting-in-adversarially-robust-deep","title":"Overfitting in adversarially robust deep learning","date":"2020-02-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"8a93e041134b597a","mcp_get_code":{"code_sha256":"8a93e041134b597a"}},{"arxiv_id":"2002.00434","paper":"/paper/integrating-deep-reinforcement-learning-with","title":"Integrating Deep Reinforcement Learning with Model-based Path Planners for Automated Driving","date":"2020-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Ekim-Yurtsever/Hybrid-DeepRL-Automated-Driving","path":"hybrid-rl/sources/carla.py","file_url":"https://github.com/Ekim-Yurtsever/Hybrid-DeepRL-Automated-Driving/blob/HEAD/hybrid-rl/sources/carla.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ccc25780948874cb","mcp_get_code":{"code_sha256":"ccc25780948874cb"}},{"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":"locuslab/fast_adversarial","path":"MNIST/evaluate_mnist.py","file_url":"https://github.com/locuslab/fast_adversarial/blob/HEAD/MNIST/evaluate_mnist.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8a93e041134b597a","mcp_get_code":{"code_sha256":"8a93e041134b597a"}},{"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":"MetaSolver/icml2021","path":"MegaAdversarial/src/attacks/fgsm.py","file_url":"https://github.com/MetaSolver/icml2021/blob/HEAD/MegaAdversarial/src/attacks/fgsm.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":"f1f502008abfb7b0","mcp_get_code":{"code_sha256":"f1f502008abfb7b0"}},{"arxiv_id":"1911.10868","paper":"/paper/end-to-end-model-free-reinforcement-learning","title":"End-to-End Model-Free Reinforcement Learning for Urban Driving using Implicit Affordances","date":"2019-11-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"valeoai/LearningByCheating","path":"misc/dynamic_weather.py","file_url":"https://github.com/valeoai/LearningByCheating/blob/HEAD/misc/dynamic_weather.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ccc25780948874cb","mcp_get_code":{"code_sha256":"ccc25780948874cb"}},{"arxiv_id":"1911.04175","paper":"/paper/multi-agent-connected-autonomous-driving","title":"Multi-Agent Connected Autonomous Driving using Deep Reinforcement Learning","date":"2019-11-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"praveen-palanisamy/macad-gym","path":"src/macad_gym/carla/PythonAPI/dynamic_weather.py","file_url":"https://github.com/praveen-palanisamy/macad-gym/blob/HEAD/src/macad_gym/carla/PythonAPI/dynamic_weather.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ccc25780948874cb","mcp_get_code":{"code_sha256":"ccc25780948874cb"}},{"arxiv_id":"1906.07983","paper":"/paper/explanations-can-be-manipulated-and-geometry","title":"Explanations can be manipulated and geometry is to blame","date":"2019-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pankessel/explanations_can_be_manipulated","path":"src/nn/utils.py","file_url":"https://github.com/pankessel/explanations_can_be_manipulated/blob/HEAD/src/nn/utils.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":"3fc9f581b5e17469","mcp_get_code":{"code_sha256":"3fc9f581b5e17469"}},{"arxiv_id":"1810.11953","paper":"/paper/failing-loudly-an-empirical-study-of-methods","title":"Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift","date":"2018-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"steverab/failing-loudly","path":"generate_summary_tables.py","file_url":"https://github.com/steverab/failing-loudly/blob/HEAD/generate_summary_tables.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dc5beb6794ffee14","mcp_get_code":{"code_sha256":"dc5beb6794ffee14"}},{"arxiv_id":"1802.03916","paper":"/paper/detecting-and-correcting-for-label-shift-with","title":"Detecting and Correcting for Label Shift with Black Box Predictors","date":"2018-02-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bbwang1030/half-kfn","path":"halfkfn.py","file_url":"https://github.com/bbwang1030/half-kfn/blob/HEAD/halfkfn.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"dc5beb6794ffee14","mcp_get_code":{"code_sha256":"dc5beb6794ffee14"}},{"arxiv_id":"1708.04552","paper":"/paper/improved-regularization-of-convolutional","title":"Improved Regularization of Convolutional Neural Networks with Cutout","date":"2017-08-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"barisozmen/deepaugment","path":"src/deepaugment/transforms.py","file_url":"https://github.com/barisozmen/deepaugment/blob/HEAD/src/deepaugment/transforms.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"77de6eeb25f3b2cc","mcp_get_code":{"code_sha256":"77de6eeb25f3b2cc"}},{"arxiv_id":"1706.06083","paper":"/paper/towards-deep-learning-models-resistant-to","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","date":"2017-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"8a93e041134b597a","mcp_get_code":{"code_sha256":"8a93e041134b597a"}},{"arxiv_id":"1602.01783","paper":"/paper/asynchronous-methods-for-deep-reinforcement","title":"Asynchronous Methods for Deep Reinforcement Learning","date":"2016-02-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cdesilv1/sc2_ai_cdes","path":"deepmind_api_modified/pysc2/lib/renderer_human.py","file_url":"https://github.com/cdesilv1/sc2_ai_cdes/blob/HEAD/deepmind_api_modified/pysc2/lib/renderer_human.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"768c86dee853b804","mcp_get_code":{"code_sha256":"768c86dee853b804"}},{"arxiv_id":"Tanke_Social_Diffusion_Long-term_Multiple_Human_Motion_Anticipation_ICCV_2023_paper","paper":null,"title":"arXiv:Tanke_Social_Diffusion_Long-term_Multiple_Human_Motion_Anticipation_ICCV_2023_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"jutanke/social_diffusion","path":"social_diffusion/ema.py","file_url":"https://github.com/jutanke/social_diffusion/blob/HEAD/social_diffusion/ema.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e907f76525778206","mcp_get_code":{"code_sha256":"e907f76525778206"}},{"arxiv_id":"Ming_Deep_Dive_Into_Gradients_Better_Optimization_for_3D_Object_Detection_CVPR_2023_paper","paper":null,"title":"arXiv:Ming_Deep_Dive_Into_Gradients_Better_Optimization_for_3D_Object_Detection_CVPR_2023_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"ming71/GCIoU-loss","path":"pcdet/models/dense_heads/anchor_head_iou.py","file_url":"https://github.com/ming71/GCIoU-loss/blob/HEAD/pcdet/models/dense_heads/anchor_head_iou.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"01b37e5b0c9a8b57","mcp_get_code":{"code_sha256":"01b37e5b0c9a8b57"}},{"arxiv_id":"Guo_Improving_Robustness_of_Vision_Transformers_by_Reducing_Sensitivity_To_Patch_CVPR_2023_paper","paper":null,"title":"arXiv:Guo_Improving_Robustness_of_Vision_Transformers_by_Reducing_Sensitivity_To_Patch_CVPR_2023_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"guoyongcs/RSPC","path":"RSPC_RVT/engine.py","file_url":"https://github.com/guoyongcs/RSPC/blob/HEAD/RSPC_RVT/engine.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8a93e041134b597a","mcp_get_code":{"code_sha256":"8a93e041134b597a"}}]}