{"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/relu","entry":"relu","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":58,"n_papers_ran":27,"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":49,"n_samples_ran":19,"n_samples_fingerprinted":16,"n_places":60,"n_places_pointer_only":14,"by_status":{"ran_honours":10,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":7,"unverified":30},"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":"2608.13628","paper":"/paper/arxiv-2608-13628","title":"Robust Dual-Model Collaborative Random Vector Functional Link Network","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"1dbace35862da027","mcp_get_code":{"code_sha256":"1dbace35862da027"}},{"arxiv_id":"2607.16761","paper":"/paper/arxiv-2607-16761","title":"Dropout and Random Gradient Masking Are Asymptotically Equivalent in Large ResNets","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"xavimaass/dropout_and_ram_2026","path":"src/jax_resnet/activations.py","file_url":"https://github.com/xavimaass/dropout_and_ram_2026/blob/HEAD/src/jax_resnet/activations.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bb3e244596afa241","mcp_get_code":{"code_sha256":"bb3e244596afa241"}},{"arxiv_id":"2604.04323","paper":"/paper/arxiv-2604-04323","title":"How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"UCSB-NLP-Chang/Skill-Usage","path":"terminal-bench-2/model-extraction-relu-logits/environment/forward.py","file_url":"https://github.com/UCSB-NLP-Chang/Skill-Usage/blob/HEAD/terminal-bench-2/model-extraction-relu-logits/environment/forward.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"68ee2675b183b56f","mcp_get_code":{"code_sha256":"68ee2675b183b56f"}},{"arxiv_id":"2512.02494","paper":"/paper/arxiv-2512-02494","title":"A Fully First-Order Layer for Differentiable Optimization","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"GT-KOALA/FFOLayer","path":"baselines/AltDiff.py","file_url":"https://github.com/GT-KOALA/FFOLayer/blob/HEAD/baselines/AltDiff.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"75a806c121e013d2","mcp_get_code":{"code_sha256":"75a806c121e013d2"}},{"arxiv_id":"2409.15771","paper":"/paper/zero-shot-forecasting-of-chaotic-systems","title":"Zero-shot forecasting of chaotic systems","date":"2024-09-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"williamgilpin/dysts","path":"dysts/metrics.py","file_url":"https://github.com/williamgilpin/dysts/blob/HEAD/dysts/metrics.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":"c9d8d9901e3c6aab","mcp_get_code":{"code_sha256":"c9d8d9901e3c6aab"}},{"arxiv_id":"2407.11542","paper":"/paper/understanding-counting-in-small-transformers","title":"Counting in Small Transformers: The Delicate Interplay between Attention and Feed-Forward Layers","date":"2024-07-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SPOC-group/counting-attention","path":"manual_models.py","file_url":"https://github.com/SPOC-group/counting-attention/blob/HEAD/manual_models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"df689d0142c2d3c9","mcp_get_code":{"code_sha256":"df689d0142c2d3c9"}},{"arxiv_id":"2406.06158","paper":"/paper/get-rich-quick-exact-solutions-reveal-how","title":"Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning","date":"2024-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"allanraventos/getrichquick","path":"two-layer-relu/utils.py","file_url":"https://github.com/allanraventos/getrichquick/blob/HEAD/two-layer-relu/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c0a59302e913313d","mcp_get_code":{"code_sha256":"c0a59302e913313d"}},{"arxiv_id":"2402.02969","paper":"/paper/towards-understanding-the-word-sensitivity-of","title":"Towards Understanding the Word Sensitivity of Attention Layers: A Study via Random Features","date":"2024-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"simone-bombari/attention-sensitivity","path":"utils.py","file_url":"https://github.com/simone-bombari/attention-sensitivity/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9d27f9aa50a86a4b","mcp_get_code":{"code_sha256":"9d27f9aa50a86a4b"}},{"arxiv_id":"2401.11627","paper":"/paper/tight-verification-of-probabilistic","title":"Tight Verification of Probabilistic Robustness in Bayesian Neural Networks","date":"2024-01-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"benbatten/TightVerificationOfProbabilisticRobustnessInBNNs","path":"verifier/utils.py","file_url":"https://github.com/benbatten/TightVerificationOfProbabilisticRobustnessInBNNs/blob/HEAD/verifier/utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5af8fa537914ff3d","mcp_get_code":{"code_sha256":"5af8fa537914ff3d"}},{"arxiv_id":"2312.12657","paper":"/paper/the-convex-landscape-of-neural-networks","title":"The Convex Landscape of Neural Networks: Characterizing Global Optima and Stationary Points via Lasso Models","date":"2023-12-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pilancilab/convex_nn","path":"convex_nn.py","file_url":"https://github.com/pilancilab/convex_nn/blob/HEAD/convex_nn.py","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1dbace35862da027","mcp_get_code":{"code_sha256":"1dbace35862da027"}},{"arxiv_id":"2310.10537","paper":"/paper/microscaling-data-formats-for-deep-learning","title":"Microscaling Data Formats for Deep Learning","date":"2023-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/microxcaling","path":"mx/activations.py","file_url":"https://github.com/microsoft/microxcaling/blob/HEAD/mx/activations.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4490c20d2c5ae00e","mcp_get_code":{"code_sha256":"4490c20d2c5ae00e"}},{"arxiv_id":"2310.07015","paper":"/paper/neural-relational-inference-with-fast-modular-1","title":"Neural Relational Inference with Fast Modular Meta-learning","date":"2023-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"FerranAlet/modular-metalearning","path":"layers.py","file_url":"https://github.com/FerranAlet/modular-metalearning/blob/HEAD/layers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8dd8a8e3eac0253a","mcp_get_code":{"code_sha256":"8dd8a8e3eac0253a"}},{"arxiv_id":"2310.06179","paper":"/paper/automatic-integration-for-spatiotemporal-1","title":"Automatic Integration for Spatiotemporal Neural Point Processes","date":"2023-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rose-stl-lab/autostpp","path":"src/demo/CorrectingMLE.py","file_url":"https://github.com/rose-stl-lab/autostpp/blob/HEAD/src/demo/CorrectingMLE.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5af8fa537914ff3d","mcp_get_code":{"code_sha256":"5af8fa537914ff3d"}},{"arxiv_id":"2309.01171","paper":"/paper/deep-unfolding-convolutional-dictionary-model","title":"Deep Unfolding Convolutional Dictionary Model for Multi-Contrast MRI Super-resolution and Reconstruction","date":"2023-09-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lpcccc-cv/MC-CDic","path":"models/modules/MCCDic.py","file_url":"https://github.com/lpcccc-cv/MC-CDic/blob/HEAD/models/modules/MCCDic.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e87a5885334f0de1","mcp_get_code":{"code_sha256":"e87a5885334f0de1"}},{"arxiv_id":"2305.18512","paper":"/paper/a-rainbow-in-deep-network-black-boxes","title":"A Rainbow in Deep Network Black Boxes","date":"2023-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"florentinguth/rainbow","path":"models/Analysis.py","file_url":"https://github.com/florentinguth/rainbow/blob/HEAD/models/Analysis.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":"1a2d7d179b6fcef3","mcp_get_code":{"code_sha256":"1a2d7d179b6fcef3"}},{"arxiv_id":"2303.08010","paper":"/paper/window-based-early-exit-cascades-for","title":"Window-Based Early-Exit Cascades for Uncertainty Estimation: When Deep Ensembles are More Efficient than Single Models","date":"2023-03-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"keras-team/keras","path":"keras/src/activations/activations.py","file_url":"https://github.com/keras-team/keras/blob/HEAD/keras/src/activations/activations.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":"59c7dca60305d651","mcp_get_code":{"code_sha256":"59c7dca60305d651"}},{"arxiv_id":"2303.03320","paper":"/paper/learning-to-backdoor-federated-learning","title":"Learning to Backdoor Federated Learning","date":"2023-03-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HengerLi/RLBackdoorFL","path":"Util.py","file_url":"https://github.com/HengerLi/RLBackdoorFL/blob/HEAD/Util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"65bc749ceadcf87d","mcp_get_code":{"code_sha256":"65bc749ceadcf87d"}},{"arxiv_id":"2210.02419","paper":"/paper/explanation-uncertainty-with-decision","title":"Boundary-Aware Uncertainty for Feature Attribution Explainers","date":"2022-10-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"davinhill/gpec","path":"GPEC/utils/utils_np.py","file_url":"https://github.com/davinhill/gpec/blob/HEAD/GPEC/utils/utils_np.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5af8fa537914ff3d","mcp_get_code":{"code_sha256":"5af8fa537914ff3d"}},{"arxiv_id":"2205.13098","paper":"/paper/optimal-neural-network-approximation-of","title":"Optimal Neural Network Approximation of Wasserstein Gradient Direction via Convex Optimization","date":"2022-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"1dbace35862da027","mcp_get_code":{"code_sha256":"1dbace35862da027"}},{"arxiv_id":"2112.06868","paper":"/paper/variational-autoencoders-in-the-presence-of-1","title":"Variational autoencoders in the presence of low-dimensional data: landscape and implicit bias","date":"2021-12-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"virajmehta/vae-training","path":"utils.py","file_url":"https://github.com/virajmehta/vae-training/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":"2cc5c094d751d00a","mcp_get_code":{"code_sha256":"2cc5c094d751d00a"}},{"arxiv_id":"2111.11146","paper":"/paper/on-the-existence-of-universal-lottery-tickets-1","title":"On the Existence of Universal Lottery Tickets","date":"2021-11-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"relationalml/universallt","path":"subsetsum.py","file_url":"https://github.com/relationalml/universallt/blob/HEAD/subsetsum.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4c9a9cab68f5a375","mcp_get_code":{"code_sha256":"4c9a9cab68f5a375"}},{"arxiv_id":"2111.06719","paper":"/paper/on-transferability-of-prompt-tuning-for","title":"On Transferability of Prompt Tuning for Natural Language Processing","date":"2021-11-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thunlp/Prompt-Transferability","path":"Prompt-Transferability-1.0/activate_neuron_Roberta.py","file_url":"https://github.com/thunlp/Prompt-Transferability/blob/HEAD/Prompt-Transferability-1.0/activate_neuron_Roberta.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5a45143bbc682622","mcp_get_code":{"code_sha256":"5a45143bbc682622"}},{"arxiv_id":"2110.05283","paper":"/paper/phase-collapse-in-neural-networks-1","title":"Phase Collapse in Neural Networks","date":"2021-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"florentinguth/phasecollapse","path":"models/Analysis.py","file_url":"https://github.com/florentinguth/phasecollapse/blob/HEAD/models/Analysis.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":"1a2d7d179b6fcef3","mcp_get_code":{"code_sha256":"1a2d7d179b6fcef3"}},{"arxiv_id":"2108.03673","paper":"/paper/recall-replay-based-continual-learning-in","title":"RECALL: Replay-based Continual Learning in Semantic Segmentation","date":"2021-08-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LTTM/RECALL","path":"model_resnet.py","file_url":"https://github.com/LTTM/RECALL/blob/HEAD/model_resnet.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"37e49142da9ee0cd","mcp_get_code":{"code_sha256":"37e49142da9ee0cd"}},{"arxiv_id":"2105.12639","paper":"/paper/blurs-make-results-clearer-spatial-smoothings","title":"Blurs Behave Like Ensembles: Spatial Smoothings to Improve Accuracy, Uncertainty, and Robustness","date":"2021-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xxxnell/spatial-smoothing","path":"models/smoothing_block.py","file_url":"https://github.com/xxxnell/spatial-smoothing/blob/HEAD/models/smoothing_block.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":"d419f818792d3793","mcp_get_code":{"code_sha256":"d419f818792d3793"}},{"arxiv_id":"2104.14672","paper":"/paper/analytical-bounds-on-the-local-lipschitz-1","title":"Analytical bounds on the local Lipschitz constants of ReLU networks","date":"2021-04-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uwaa-ndcl/local_lipschitz","path":"network_bound.py","file_url":"https://github.com/uwaa-ndcl/local_lipschitz/blob/HEAD/network_bound.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7bc22741366e8140","mcp_get_code":{"code_sha256":"7bc22741366e8140"}},{"arxiv_id":"2102.13037","paper":"/paper/spinn-sparse-physics-based-and-interpretable","title":"SPINN: Sparse, Physics-based, and partially Interpretable Neural Networks for PDEs","date":"2021-02-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nn4pde/SPINN","path":"automate.py","file_url":"https://github.com/nn4pde/SPINN/blob/HEAD/automate.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"93a27674bbe152a1","mcp_get_code":{"code_sha256":"93a27674bbe152a1"}},{"arxiv_id":"2102.10058","paper":"/paper/principled-simplicial-neural-networks-for","title":"Principled Simplicial Neural Networks for Trajectory Prediction","date":"2021-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nglaze00/scone_gcn","path":"trajectory_analysis/trajectory_experiments.py","file_url":"https://github.com/nglaze00/scone_gcn/blob/HEAD/trajectory_analysis/trajectory_experiments.py","status":"unverified","verification_level":0,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4e5209e332ac17d2","mcp_get_code":{"code_sha256":"4e5209e332ac17d2"}},{"arxiv_id":"2012.10424","paper":"/paper/separation-and-concentration-in-deep-networks","title":"Separation and Concentration in Deep Networks","date":"2020-12-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"j-zarka/separation_concentration_deepnets","path":"models/Analysis.py","file_url":"https://github.com/j-zarka/separation_concentration_deepnets/blob/HEAD/models/Analysis.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"d5d46e42d48015f4","mcp_get_code":{"code_sha256":"d5d46e42d48015f4"}},{"arxiv_id":"2006.04647","paper":"/paper/neural-architecture-search-without-training","title":"Neural Architecture Search without Training","date":"2020-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nlinc1905/evolutionary-reinforcement-learner","path":"models/mlp.py","file_url":"https://github.com/nlinc1905/evolutionary-reinforcement-learner/blob/HEAD/models/mlp.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0bd581e0afb4c04a","mcp_get_code":{"code_sha256":"0bd581e0afb4c04a"}},{"arxiv_id":"2006.04508","paper":"/paper/black-box-mixed-variable-optimisation-using-a","title":"Black-box Mixed-Variable Optimisation using a Surrogate Model that Satisfies Integer Constraints","date":"2020-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lbliek/MVRSM","path":"MVRSM.py","file_url":"https://github.com/lbliek/MVRSM/blob/HEAD/MVRSM.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5778be44d14bcb09","mcp_get_code":{"code_sha256":"5778be44d14bcb09"}},{"arxiv_id":"2004.13912","paper":"/paper/neural-additive-models-interpretable-machine","title":"Neural Additive Models: Interpretable Machine Learning with Neural Nets","date":"2020-04-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Habush/nam_jax","path":"models.py","file_url":"https://github.com/Habush/nam_jax/blob/HEAD/models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"454cfa9b8b9aed47","mcp_get_code":{"code_sha256":"454cfa9b8b9aed47"}},{"arxiv_id":"2004.13912","paper":"/paper/neural-additive-models-interpretable-machine","title":"Neural Additive Models: Interpretable Machine Learning with Neural Nets","date":"2020-04-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nickfrosst/neural_additive_models","path":"models.py","file_url":"https://github.com/nickfrosst/neural_additive_models/blob/HEAD/models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"207a3a66ecdc0f2f","mcp_get_code":{"code_sha256":"207a3a66ecdc0f2f"}},{"arxiv_id":"2003.04884","paper":"/paper/cryptanalytic-extraction-of-neural-network","title":"Cryptanalytic Extraction of Neural Network Models","date":"2020-03-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-research/cryptanalytic-model-extraction","path":"check_solution_svd.py","file_url":"https://github.com/google-research/cryptanalytic-model-extraction/blob/HEAD/check_solution_svd.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":"5af8fa537914ff3d","mcp_get_code":{"code_sha256":"5af8fa537914ff3d"}},{"arxiv_id":"2001.01568","paper":"/paper/learned-image-compression-with-discretized","title":"Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules","date":"2020-01-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LiuLei95/PyTorch-Learned-Image-Compression-with-GMM-and-Attention","path":"models/basics.py","file_url":"https://github.com/LiuLei95/PyTorch-Learned-Image-Compression-with-GMM-and-Attention/blob/HEAD/models/basics.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":"ba24f201a717509b","mcp_get_code":{"code_sha256":"ba24f201a717509b"}},{"arxiv_id":"1911.08287","paper":"/paper/distance-iou-loss-faster-and-better-learning","title":"Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression","date":"2019-11-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"grifon-239/diploma","path":"common/backbones/mobilenet_v3.py","file_url":"https://github.com/grifon-239/diploma/blob/HEAD/common/backbones/mobilenet_v3.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d304c126a9501818","mcp_get_code":{"code_sha256":"d304c126a9501818"}},{"arxiv_id":"1910.03561","paper":"/paper/deep-network-classification-by-scattering-and","title":"Deep Network Classification by Scattering and Homotopy Dictionary Learning","date":"2019-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"j-zarka/SparseScatNet","path":"models/ISTC.py","file_url":"https://github.com/j-zarka/SparseScatNet/blob/HEAD/models/ISTC.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"d5d46e42d48015f4","mcp_get_code":{"code_sha256":"d5d46e42d48015f4"}},{"arxiv_id":"1907.10599","paper":"/paper/a-fine-grained-spectral-perspective-on-neural","title":"A Fine-Grained Spectral Perspective on Neural Networks","date":"2019-07-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thegregyang/NNspectra","path":"theory.py","file_url":"https://github.com/thegregyang/NNspectra/blob/HEAD/theory.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5af8fa537914ff3d","mcp_get_code":{"code_sha256":"5af8fa537914ff3d"}},{"arxiv_id":"1905.11946","paper":"/paper/efficientnet-rethinking-model-scaling-for","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","date":"2019-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rohitgr7/tvmodels","path":"tvmodels/models/blocks/effnet_blocks.py","file_url":"https://github.com/rohitgr7/tvmodels/blob/HEAD/tvmodels/models/blocks/effnet_blocks.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9461188086a155ec","mcp_get_code":{"code_sha256":"9461188086a155ec"}},{"arxiv_id":"1905.06331","paper":"/paper/lgm-net-learning-to-generate-matching","title":"LGM-Net: Learning to Generate Matching Networks for Few-Shot Learning","date":"2019-05-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"likesiwell/LGM-Net","path":"meta_matching_network.py","file_url":"https://github.com/likesiwell/LGM-Net/blob/HEAD/meta_matching_network.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ba415e733a64978f","mcp_get_code":{"code_sha256":"ba415e733a64978f"}},{"arxiv_id":"1905.04405","paper":"/paper/language-conditioned-graph-networks-for","title":"Language-Conditioned Graph Networks for Relational Reasoning","date":"2019-05-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ronghanghu/lcgn","path":"models_clevr/ops.py","file_url":"https://github.com/ronghanghu/lcgn/blob/HEAD/models_clevr/ops.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"code_sha256_prefix":"2de8a558c3e97e3d","mcp_get_code":{"code_sha256":"2de8a558c3e97e3d"}},{"arxiv_id":"1905.00641","paper":"/paper/190500641","title":"RetinaFace: Single-stage Dense Face Localisation in the Wild","date":"2019-05-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"StanislasBertrand/RetinaFace-tf2","path":"src/retinafacetf2/networks/network_utils.py","file_url":"https://github.com/StanislasBertrand/RetinaFace-tf2/blob/HEAD/src/retinafacetf2/networks/network_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c24c719cc4022d0b","mcp_get_code":{"code_sha256":"c24c719cc4022d0b"}},{"arxiv_id":"1811.00145","paper":"/paper/scalable-end-to-end-autonomous-vehicle","title":"Scalable End-to-End Autonomous Vehicle Testing via Rare-event Simulation","date":"2018-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amansinha/neural-bridge","path":"envs/car_racing/WorldModel/dream_model.py","file_url":"https://github.com/amansinha/neural-bridge/blob/HEAD/envs/car_racing/WorldModel/dream_model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b4ffc7174f63b5d9","mcp_get_code":{"code_sha256":"b4ffc7174f63b5d9"}},{"arxiv_id":"1802.09419","paper":"/paper/stochastic-hyperparameter-optimization","title":"Stochastic Hyperparameter Optimization through Hypernetworks","date":"2018-02-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lorraine2/hypernet-hypertraining","path":"code/neural_network.py","file_url":"https://github.com/lorraine2/hypernet-hypertraining/blob/HEAD/code/neural_network.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"57d85d9dbc47f39e","mcp_get_code":{"code_sha256":"57d85d9dbc47f39e"}},{"arxiv_id":"1802.09232","paper":"/paper/2d3d-pose-estimation-and-action-recognition","title":"2D/3D Pose Estimation and Action Recognition using Multitask Deep Learning","date":"2018-02-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dluvizon/deephar","path":"deephar/layers.py","file_url":"https://github.com/dluvizon/deephar/blob/HEAD/deephar/layers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"401ff7831c3db2d1","mcp_get_code":{"code_sha256":"401ff7831c3db2d1"}},{"arxiv_id":"1710.03463","paper":"/paper/learning-to-generalize-meta-learning-for","title":"Learning to Generalize: Meta-Learning for Domain Generalization","date":"2017-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HAHA-DL/MLDG","path":"ops.py","file_url":"https://github.com/HAHA-DL/MLDG/blob/HEAD/ops.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"982640b2b87ab733","mcp_get_code":{"code_sha256":"982640b2b87ab733"}},{"arxiv_id":"1710.03463","paper":"/paper/learning-to-generalize-meta-learning-for","title":"Learning to Generalize: Meta-Learning for Domain Generalization","date":"2017-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Pulkit-Khandelwal/mldg","path":"ops.py","file_url":"https://github.com/Pulkit-Khandelwal/mldg/blob/HEAD/ops.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":"ffc6304fe71748bf","mcp_get_code":{"code_sha256":"ffc6304fe71748bf"}},{"arxiv_id":"1703.03717","paper":"/paper/right-for-the-right-reasons-training","title":"Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations","date":"2017-03-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dtak/rrr","path":"rrr/multilayer_perceptron.py","file_url":"https://github.com/dtak/rrr/blob/HEAD/rrr/multilayer_perceptron.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fd6644bff4456444","mcp_get_code":{"code_sha256":"fd6644bff4456444"}},{"arxiv_id":"1703.03400","paper":"/paper/model-agnostic-meta-learning-for-fast","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","date":"2017-03-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"katerakelly/pytorch-maml","path":"src/layers.py","file_url":"https://github.com/katerakelly/pytorch-maml/blob/HEAD/src/layers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8dd8a8e3eac0253a","mcp_get_code":{"code_sha256":"8dd8a8e3eac0253a"}},{"arxiv_id":"1702.00748","paper":"/paper/qcd-aware-recursive-neural-networks-for-jet","title":"QCD-Aware Recursive Neural Networks for Jet Physics","date":"2017-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"glouppe/recnn","path":"recnn/recnn.py","file_url":"https://github.com/glouppe/recnn/blob/HEAD/recnn/recnn.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":"ef94bdd1ea899a09","mcp_get_code":{"code_sha256":"ef94bdd1ea899a09"}},{"arxiv_id":"1611.09326","paper":"/paper/the-one-hundred-layers-tiramisu-fully","title":"The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation","date":"2016-11-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ankit-vaghela30/Cilia-Segmentation","path":"hastings/tiramisu_model.py","file_url":"https://github.com/ankit-vaghela30/Cilia-Segmentation/blob/HEAD/hastings/tiramisu_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a5b43c4ed0ec9709","mcp_get_code":{"code_sha256":"a5b43c4ed0ec9709"}},{"arxiv_id":"1611.07725","paper":"/paper/icarl-incremental-classifier-and","title":"iCaRL: Incremental Classifier and Representation Learning","date":"2016-11-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"srebuffi/iCaRL","path":"iCaRL-Tensorflow/utils_resnet.py","file_url":"https://github.com/srebuffi/iCaRL/blob/HEAD/iCaRL-Tensorflow/utils_resnet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4c8201151d6e4d18","mcp_get_code":{"code_sha256":"4c8201151d6e4d18"}},{"arxiv_id":"1611.01704","paper":"/paper/end-to-end-optimized-image-compression","title":"End-to-end Optimized Image Compression","date":"2016-11-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liujiaheng/iclr_17_compression","path":"models/basics.py","file_url":"https://github.com/liujiaheng/iclr_17_compression/blob/HEAD/models/basics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ba24f201a717509b","mcp_get_code":{"code_sha256":"ba24f201a717509b"}},{"arxiv_id":"1610.02391","paper":"/paper/grad-cam-visual-explanations-from-deep","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","date":"2016-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ryoasu/grad-cam","path":"keras_pkg/grad_cam.py","file_url":"https://github.com/ryoasu/grad-cam/blob/HEAD/keras_pkg/grad_cam.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b4ffc7174f63b5d9","mcp_get_code":{"code_sha256":"b4ffc7174f63b5d9"}},{"arxiv_id":"1603.05959","paper":"/paper/efficient-multi-scale-3d-cnn-with-fully","title":"Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation","date":"2016-03-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Kamnitsask/deepmedic","path":"deepmedic/neuralnet/ops.py","file_url":"https://github.com/Kamnitsask/deepmedic/blob/HEAD/deepmedic/neuralnet/ops.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":"5d605f64da7a03e1","mcp_get_code":{"code_sha256":"5d605f64da7a03e1"}},{"arxiv_id":"1509.09292","paper":"/paper/convolutional-networks-on-graphs-for-learning","title":"Convolutional Networks on Graphs for Learning Molecular Fingerprints","date":"2015-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HIPS/neural-fingerprint","path":"neuralfingerprint/build_vanilla_net.py","file_url":"https://github.com/HIPS/neural-fingerprint/blob/HEAD/neuralfingerprint/build_vanilla_net.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cba23591b86550d5","mcp_get_code":{"code_sha256":"cba23591b86550d5"}},{"arxiv_id":"1505.04597","paper":"/paper/u-net-convolutional-networks-for-biomedical","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","date":"2015-05-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ChengBinJin/U-Net-TensorFlow","path":"src/model.py","file_url":"https://github.com/ChengBinJin/U-Net-TensorFlow/blob/HEAD/src/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2746cf1ccebe4079","mcp_get_code":{"code_sha256":"2746cf1ccebe4079"}},{"arxiv_id":"1502.01852","paper":"/paper/delving-deep-into-rectifiers-surpassing-human","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","date":"2015-02-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hamiddimyati/dd2424-deep-learning","path":"assignment-2/assignment2-bonus.py","file_url":"https://github.com/hamiddimyati/dd2424-deep-learning/blob/HEAD/assignment-2/assignment2-bonus.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"94d5729d92a97933","mcp_get_code":{"code_sha256":"94d5729d92a97933"}},{"arxiv_id":"aaai_5987","paper":null,"title":"arXiv:aaai_5987","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"RingBDStack/MA-GCNNs","path":"M-GCNNs/layers.py","file_url":"https://github.com/RingBDStack/MA-GCNNs/blob/HEAD/M-GCNNs/layers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"df2e36697d20ae04","mcp_get_code":{"code_sha256":"df2e36697d20ae04"}},{"arxiv_id":"aaai_17756","paper":null,"title":"arXiv:aaai_17756","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"kia-kia/IC-MLNet","path":"model/ops.py","file_url":"https://github.com/kia-kia/IC-MLNet/blob/HEAD/model/ops.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8ec69db6155c57f6","mcp_get_code":{"code_sha256":"8ec69db6155c57f6"}}]}