{"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/perturb","entry":"perturb","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":20,"n_papers_ran":9,"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":18,"n_samples_ran":8,"n_samples_fingerprinted":3,"n_places":20,"n_places_pointer_only":8,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":2,"ran":3,"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":"2601.22029","paper":"/paper/arxiv-2601-22029","title":"The Ensemble Inverse Problem: Applications and Methods","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"ZhengyanHuan/The-Ensemble-Inverse-Problem--Applications-and-Methods","path":"Sec3p2/dataset.py","file_url":"https://github.com/ZhengyanHuan/The-Ensemble-Inverse-Problem--Applications-and-Methods/blob/HEAD/Sec3p2/dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f88ebac879b99202","mcp_get_code":{"code_sha256":"f88ebac879b99202"}},{"arxiv_id":"2403.01849","paper":"/paper/one-prompt-word-is-enough-to-boost","title":"One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models","date":"2024-03-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TreeLLi/APT","path":"apt/evaluate.py","file_url":"https://github.com/TreeLLi/APT/blob/HEAD/apt/evaluate.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c2be82a99f878e8c","mcp_get_code":{"code_sha256":"c2be82a99f878e8c"}},{"arxiv_id":"2312.10988","paper":"/paper/graph-invariant-learning-with-subgraph-co","title":"Graph Invariant Learning with Subgraph Co-mixup for Out-Of-Distribution Generalization","date":"2023-12-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bupt-gamma/igm","path":"IGM_code/dataset_gen/BA3_loc.py","file_url":"https://github.com/bupt-gamma/igm/blob/HEAD/IGM_code/dataset_gen/BA3_loc.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"425d3f16a4164e4c","mcp_get_code":{"code_sha256":"425d3f16a4164e4c"}},{"arxiv_id":"2310.19668","paper":"/paper/drm-mastering-visual-reinforcement-learning","title":"DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization","date":"2023-10-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"XuGW-Kevin/DrM","path":"agents/drm.py","file_url":"https://github.com/XuGW-Kevin/DrM/blob/HEAD/agents/drm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4a4ae05c66dd350a","mcp_get_code":{"code_sha256":"4a4ae05c66dd350a"}},{"arxiv_id":"2309.15718","paper":"/paper/gpip-geometry-enhanced-pre-training-on","title":"Geometry-enhanced Pre-training on Interatomic Potentials","date":null,"month_inferred_from_arxiv_id":"2023-09","title_source":"archive","repo":"cuitaoyong/gpip","path":"pretraining.py","file_url":"https://github.com/cuitaoyong/gpip/blob/HEAD/pretraining.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f4e22a0a3a8ec839","mcp_get_code":{"code_sha256":"f4e22a0a3a8ec839"}},{"arxiv_id":"2306.07197","paper":"/paper/aroid-improving-adversarial-robustness","title":"AROID: Improving Adversarial Robustness Through Online Instance-Wise Data Augmentation","date":"2023-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"treelli/aroid","path":"src/utils/adversary.py","file_url":"https://github.com/treelli/aroid/blob/HEAD/src/utils/adversary.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2ed1c4f9595c38a6","mcp_get_code":{"code_sha256":"2ed1c4f9595c38a6"}},{"arxiv_id":"2305.07984","paper":"/paper/scene-self-labeled-counterfactuals-for","title":"SCENE: Self-Labeled Counterfactuals for Extrapolating to Negative Examples","date":"2023-05-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"deqingfu/scene","path":"perturb.py","file_url":"https://github.com/deqingfu/scene/blob/HEAD/perturb.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"82507651b361aacb","mcp_get_code":{"code_sha256":"82507651b361aacb"}},{"arxiv_id":"2301.09879","paper":"/paper/data-augmentation-alone-can-improve","title":"Data Augmentation Alone Can Improve Adversarial Training","date":"2023-01-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"treelli/da-alone-improves-at","path":"src/utils/adversary.py","file_url":"https://github.com/treelli/da-alone-improves-at/blob/HEAD/src/utils/adversary.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c4ff8c6f13f39bc5","mcp_get_code":{"code_sha256":"c4ff8c6f13f39bc5"}},{"arxiv_id":"2206.12314","paper":"/paper/learning-sparse-features-can-lead-to","title":"Learning sparse features can lead to overfitting in neural networks","date":"2022-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pcsl-epfl/regressionsphere","path":"stability.py","file_url":"https://github.com/pcsl-epfl/regressionsphere/blob/HEAD/stability.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d9794cc8e3c1bcb9","mcp_get_code":{"code_sha256":"d9794cc8e3c1bcb9"}},{"arxiv_id":"2104.10482","paper":"/paper/graphsvx-shapley-value-explanations-for-graph","title":"GraphSVX: Shapley Value Explanations for Graph Neural Networks","date":"2021-04-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AlexDuvalinho/GraphSVX","path":"src/gengraph.py","file_url":"https://github.com/AlexDuvalinho/GraphSVX/blob/HEAD/src/gengraph.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"25b882d4de9cd6bd","mcp_get_code":{"code_sha256":"25b882d4de9cd6bd"}},{"arxiv_id":"2009.08965","paper":"/paper/preparing-for-the-worst-making-networks-less","title":"Encoding Robustness to Image Style via Adversarial Feature Perturbations","date":"2020-09-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"azshue/advbn","path":"train_imagenet.py","file_url":"https://github.com/azshue/advbn/blob/HEAD/train_imagenet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9fe44f1273732195","mcp_get_code":{"code_sha256":"9fe44f1273732195"}},{"arxiv_id":"2003.02977","paper":"/paper/likelihood-regret-an-out-of-distribution","title":"Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder","date":"2020-03-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"XavierXiao/Likelihood-Regret","path":"train_pixel.py","file_url":"https://github.com/XavierXiao/Likelihood-Regret/blob/HEAD/train_pixel.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":"356aef4a4b74b441","mcp_get_code":{"code_sha256":"356aef4a4b74b441"}},{"arxiv_id":"2001.05847","paper":"/paper/end-to-end-pixel-based-deep-active-inference","title":"End-to-End Pixel-Based Deep Active Inference for Body Perception and Action","date":"2019-12-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cansu97/PixelAI","path":"Benchmark_Perceptual_Offline/run_benchmark.py","file_url":"https://github.com/cansu97/PixelAI/blob/HEAD/Benchmark_Perceptual_Offline/run_benchmark.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4449023f158b9935","mcp_get_code":{"code_sha256":"4449023f158b9935"}},{"arxiv_id":"1906.05838","paper":"/paper/goal-conditioned-imitation-learning","title":"Goal-conditioned Imitation Learning","date":"2019-06-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dingyiming0427/goalgail","path":"baselines/her/her.py","file_url":"https://github.com/dingyiming0427/goalgail/blob/HEAD/baselines/her/her.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2924888d72c2c274","mcp_get_code":{"code_sha256":"2924888d72c2c274"}},{"arxiv_id":"1903.08333","paper":"/paper/on-the-robustness-of-deep-k-nearest-neighbors","title":"On the Robustness of Deep K-Nearest Neighbors","date":"2019-03-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"79c0d47a0e121164","mcp_get_code":{"code_sha256":"79c0d47a0e121164"}},{"arxiv_id":"1903.03894","paper":"/paper/gnn-explainer-a-tool-for-post-hoc-explanation","title":"GNNExplainer: Generating Explanations for Graph Neural Networks","date":"2019-03-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RexYing/gnn-model-explainer","path":"gengraph.py","file_url":"https://github.com/RexYing/gnn-model-explainer/blob/HEAD/gengraph.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":"11e1d48886273577","mcp_get_code":{"code_sha256":"11e1d48886273577"}},{"arxiv_id":"1810.00470","paper":"/paper/procedural-noise-adversarial-examples-for","title":"Procedural Noise Adversarial Examples for Black-Box Attacks on Deep Convolutional Networks","date":"2018-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kenny-co/procedural-advml","path":"utils_attack.py","file_url":"https://github.com/kenny-co/procedural-advml/blob/HEAD/utils_attack.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"eb58662c9956c611","mcp_get_code":{"code_sha256":"eb58662c9956c611"}},{"arxiv_id":"1803.04765","paper":"/paper/deep-k-nearest-neighbors-towards-confident","title":"Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning","date":"2018-03-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fiona-lxd/AdvKnn","path":"attack.py","file_url":"https://github.com/fiona-lxd/AdvKnn/blob/HEAD/attack.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"79c0d47a0e121164","mcp_get_code":{"code_sha256":"79c0d47a0e121164"}},{"arxiv_id":"1802.08773","paper":"/paper/graphrnn-generating-realistic-graphs-with","title":"GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models","date":"2018-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"snap-stanford/GraphRNN","path":"utils.py","file_url":"https://github.com/snap-stanford/GraphRNN/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":"8f7d2c1aa425efe6","mcp_get_code":{"code_sha256":"8f7d2c1aa425efe6"}},{"arxiv_id":"aaai_29648","paper":null,"title":"arXiv:aaai_29648","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"haibin65535/ICL","path":"gengraph.py","file_url":"https://github.com/haibin65535/ICL/blob/HEAD/gengraph.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"11e1d48886273577","mcp_get_code":{"code_sha256":"11e1d48886273577"}}]}