{"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/normalise","entry":"normalise","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":26,"n_papers_ran":8,"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":20,"n_samples_ran":7,"n_samples_fingerprinted":6,"n_places":27,"n_places_pointer_only":5,"by_status":{"ran_honours":0,"ran_violates":1,"ran_draft_wrong":2,"ran_fixture":0,"ran":4,"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":"2607.19083","paper":"/paper/arxiv-2607-19083","title":"GEqTrain: A Configuration-Driven Framework for Retargeting Equivariant Graph Neural Networks Across 3D Scientific Tasks","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"limresgrp/HEroBM","path":"herobm/utils/analysis.py","file_url":"https://github.com/limresgrp/HEroBM/blob/HEAD/herobm/utils/analysis.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"81dd09f5d9856e2d","mcp_get_code":{"code_sha256":"81dd09f5d9856e2d"}},{"arxiv_id":"2607.02510","paper":"/paper/arxiv-2607-02510","title":"Online Safety Monitoring for LLMs","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"monasch/llm-monitor","path":"python_scripts/add_final_label.py","file_url":"https://github.com/monasch/llm-monitor/blob/HEAD/python_scripts/add_final_label.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b680b953c3c12edc","mcp_get_code":{"code_sha256":"b680b953c3c12edc"}},{"arxiv_id":"2603.25635","paper":"/paper/arxiv-2603-25635","title":"Anchored-Branched Steady-state WInd Flow Transformer (AB-SWIFT): a metamodel for 3D atmospheric flow in urban environments","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"cerea-daml/abswift","path":"dataset/random_buildings_dataset.py","file_url":"https://github.com/cerea-daml/abswift/blob/HEAD/dataset/random_buildings_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"80dc83d86c96f7e3","mcp_get_code":{"code_sha256":"80dc83d86c96f7e3"}},{"arxiv_id":"2602.01951","paper":"/paper/arxiv-2602-01951","title":"Enabling Progressive Whole-slide Image Analysis with Multi-scale Pyramidal Network","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"CraigMyles/SurGen-Dataset","path":"reproducibility/wsi_core/WholeSlideImage.py","file_url":"https://github.com/CraigMyles/SurGen-Dataset/blob/HEAD/reproducibility/wsi_core/WholeSlideImage.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"3a334b495845600c","mcp_get_code":{"code_sha256":"3a334b495845600c"}},{"arxiv_id":"2506.07883","paper":"/paper/diffusion-counterfactual-generation-with","title":"Diffusion Counterfactual Generation with Semantic Abduction","date":"2025-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rajatrasal/diffusion-counterfactuals","path":"model/mnist.py","file_url":"https://github.com/rajatrasal/diffusion-counterfactuals/blob/HEAD/model/mnist.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e8a4d61a5fec68dd","mcp_get_code":{"code_sha256":"e8a4d61a5fec68dd"}},{"arxiv_id":"2505.13471","paper":"/paper/the-spotlight-resonance-method-resolving-the","title":"The Spotlight Resonance Method: Resolving the Alignment of Embedded Activations","date":"2025-05-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"GeorgeBird1/Spotlight-Resonance-Method","path":"SpotlightResonanceMethod.py","file_url":"https://github.com/GeorgeBird1/Spotlight-Resonance-Method/blob/HEAD/SpotlightResonanceMethod.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":"a5fc79aaef54e9b7","mcp_get_code":{"code_sha256":"a5fc79aaef54e9b7"}},{"arxiv_id":"2503.15156","paper":"/paper/arc-anchored-representation-clouds-for-high","title":"ARC: Anchored Representation Clouds for High-Resolution INR Classification","date":"2025-03-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jluij/anchored_representation_clouds","path":"tasks/fit_inrs.py","file_url":"https://github.com/jluij/anchored_representation_clouds/blob/HEAD/tasks/fit_inrs.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"794a68324e6429c8","mcp_get_code":{"code_sha256":"794a68324e6429c8"}},{"arxiv_id":"2412.03299","paper":"/paper/gaussian-processes-for-probabilistic","title":"Gaussian Processes for Probabilistic Estimates of Earthquake Ground Shaking: A 1-D Proof-of-Concept","date":"2024-12-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sscivier/gp-prob-earthquake-shaking","path":"utils/data_gen_utils.py","file_url":"https://github.com/sscivier/gp-prob-earthquake-shaking/blob/HEAD/utils/data_gen_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":"8587df9a22c58e46","mcp_get_code":{"code_sha256":"8587df9a22c58e46"}},{"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/utils.py","file_url":"https://github.com/jiancongxiao/moreau-envelope-sgd/blob/HEAD/adversarial_robustness_overfitting/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d2a4ac781b2a9628","mcp_get_code":{"code_sha256":"d2a4ac781b2a9628"}},{"arxiv_id":"2311.08516","paper":"/paper/llms-cannot-find-reasoning-errors-but-can","title":"LLMs cannot find reasoning errors, but can correct them given the error location","date":"2023-11-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"whgtyen/big-bench-mistake","path":"annotate_dyck_languages.py","file_url":"https://github.com/whgtyen/big-bench-mistake/blob/HEAD/annotate_dyck_languages.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":"abed58b3f4aafc06","mcp_get_code":{"code_sha256":"abed58b3f4aafc06"}},{"arxiv_id":"2310.15773","paper":"/paper/bless-benchmarking-large-language-models-on","title":"BLESS: Benchmarking Large Language Models on Sentence Simplification","date":"2023-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZurichNLP/BLESS","path":"evaluation/simplification_evaluation.py","file_url":"https://github.com/ZurichNLP/BLESS/blob/HEAD/evaluation/simplification_evaluation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6fa2469a4abc4b97","mcp_get_code":{"code_sha256":"6fa2469a4abc4b97"}},{"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":"utils.py","file_url":"https://github.com/tmllab/2024_ICLR_DOM/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":"d2a4ac781b2a9628","mcp_get_code":{"code_sha256":"d2a4ac781b2a9628"}},{"arxiv_id":"2307.07093","paper":"/paper/maxcorrmgnn-a-multi-graph-neural-network","title":"MaxCorrMGNN: A Multi-Graph Neural Network Framework for Generalized Multimodal Fusion of Medical Data for Outcome Prediction","date":"2023-07-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IBM/MMMG","path":"Graph_Classification/utils/autoencoder_modules.py","file_url":"https://github.com/IBM/MMMG/blob/HEAD/Graph_Classification/utils/autoencoder_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":"703833189e8bde6c","mcp_get_code":{"code_sha256":"703833189e8bde6c"}},{"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/utils.py","file_url":"https://github.com/ryanlucas3/hr_neural_networks/blob/HEAD/HR_Neural_Networks/Paper_experiments/Section_6.2/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d2a4ac781b2a9628","mcp_get_code":{"code_sha256":"d2a4ac781b2a9628"}},{"arxiv_id":"2210.17213","paper":"/paper/deep-gaussian-process-based-multi-fidelity","title":"Deep Gaussian Process-based Multi-fidelity Bayesian Optimization for Simulated Chemical Reactors","date":"2022-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"optimal-pse-lab/pulsed-reactor-optimisation","path":"utils.py","file_url":"https://github.com/optimal-pse-lab/pulsed-reactor-optimisation/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":"0987413217de1d2f","mcp_get_code":{"code_sha256":"0987413217de1d2f"}},{"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":"utils.py","file_url":"https://github.com/alipay/A2-efficient-automated-attacker-for-boosting-adversarial-training/blob/HEAD/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":"d2a4ac781b2a9628","mcp_get_code":{"code_sha256":"d2a4ac781b2a9628"}},{"arxiv_id":"2205.08399","paper":"/paper/how-do-variational-autoencoders-learn","title":"How do Variational Autoencoders Learn? Insights from Representational Similarity","date":"2022-05-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bonheml/vae_learning_dynamics","path":"vae_ld/learning_dynamics/information_bottleneck.py","file_url":"https://github.com/bonheml/vae_learning_dynamics/blob/HEAD/vae_ld/learning_dynamics/information_bottleneck.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":"82160aff46ed416e","mcp_get_code":{"code_sha256":"82160aff46ed416e"}},{"arxiv_id":"2204.08582","paper":"/paper/massive-a-1m-example-multilingual-natural","title":"MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages","date":"2022-04-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rita-nlp/italic","path":"asr_inference.py","file_url":"https://github.com/rita-nlp/italic/blob/HEAD/asr_inference.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":"48422a4b6a62ca2f","mcp_get_code":{"code_sha256":"48422a4b6a62ca2f"}},{"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":"utils.py","file_url":"https://github.com/mattlawhon/SelfSupDefense/blob/HEAD/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":"d2a4ac781b2a9628","mcp_get_code":{"code_sha256":"d2a4ac781b2a9628"}},{"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":"utils.py","file_url":"https://github.com/cvlab-columbia/SelfSupDefense/blob/HEAD/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":"d2a4ac781b2a9628","mcp_get_code":{"code_sha256":"d2a4ac781b2a9628"}},{"arxiv_id":"2006.12135","paper":"/paper/learning-to-generate-noise-for-robustness","title":"Learning to Generate Noise for Multi-Attack Robustness","date":"2020-06-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"divyam3897/MNG_AC","path":"core.py","file_url":"https://github.com/divyam3897/MNG_AC/blob/HEAD/core.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8b28005c645a1f0d","mcp_get_code":{"code_sha256":"8b28005c645a1f0d"}},{"arxiv_id":"2003.14297","paper":"/paper/learning-from-small-data-through-sampling-an","title":"Generative Latent Implicit Conditional Optimization when Learning from Small Sample","date":"2020-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IdanAzuri/glico-learning-small-sample","path":"glico_model/cifar10.py","file_url":"https://github.com/IdanAzuri/glico-learning-small-sample/blob/HEAD/glico_model/cifar10.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e6db98c4f0c516df","mcp_get_code":{"code_sha256":"e6db98c4f0c516df"}},{"arxiv_id":"2003.14297","paper":"/paper/learning-from-small-data-through-sampling-an","title":"Generative Latent Implicit Conditional Optimization when Learning from Small Sample","date":"2020-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IdanAzuri/glico-learning-small-sample","path":"glico_model/cifar100.py","file_url":"https://github.com/IdanAzuri/glico-learning-small-sample/blob/HEAD/glico_model/cifar100.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f0a379836cfa494d","mcp_get_code":{"code_sha256":"f0a379836cfa494d"}},{"arxiv_id":"1910.00617","paper":"/paper/predicting-materials-properties-without","title":"Predicting materials properties without crystal structure: Deep representation learning from stoichiometry","date":"2019-10-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"s-a-malik/inorg-synth-graph","path":"preprocess.py","file_url":"https://github.com/s-a-malik/inorg-synth-graph/blob/HEAD/preprocess.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"71df8083f550743e","mcp_get_code":{"code_sha256":"71df8083f550743e"}},{"arxiv_id":"1905.02249","paper":"/paper/mixmatch-a-holistic-approach-to-semi","title":"MixMatch: A Holistic Approach to Semi-Supervised Learning","date":"2019-05-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kevinghst/mixmatch","path":"dataset/cifar10.py","file_url":"https://github.com/kevinghst/mixmatch/blob/HEAD/dataset/cifar10.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d2a4ac781b2a9628","mcp_get_code":{"code_sha256":"d2a4ac781b2a9628"}},{"arxiv_id":"1811.08425","paper":"/paper/fast-classification-of-small-x-ray","title":"Fast and interpretable classification of small X-ray diffraction datasets using data augmentation and deep neural networks","date":"2018-11-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ma921/XRDidentifier","path":"train_expert.py","file_url":"https://github.com/ma921/XRDidentifier/blob/HEAD/train_expert.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f1a7af06566be3ed","mcp_get_code":{"code_sha256":"f1a7af06566be3ed"}},{"arxiv_id":"2024.findings-acl.826","paper":null,"title":"arXiv:2024.findings-acl.826","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"WHGTyen/BIG-Bench-Mistake","path":"annotate_dyck_languages.py","file_url":"https://github.com/WHGTyen/BIG-Bench-Mistake/blob/HEAD/annotate_dyck_languages.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":"abed58b3f4aafc06","mcp_get_code":{"code_sha256":"abed58b3f4aafc06"}}]}