{"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/kl-divergence","entry":"kl_divergence","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":86,"n_papers_ran":41,"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":82,"n_samples_ran":38,"n_samples_fingerprinted":24,"n_places":90,"n_places_pointer_only":30,"by_status":{"ran_honours":6,"ran_violates":6,"ran_draft_wrong":7,"ran_fixture":3,"ran":16,"unverified":44},"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":"2607.10825","paper":"/paper/arxiv-2607-10825","title":"Large Language Models for Token-Efficient and Semantic-Preserving Opinion Summarization","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"SCAlabUnical/semantic-preserving-summarization","path":"stratifiers/StratifierKullbackLeibler.py","file_url":"https://github.com/SCAlabUnical/semantic-preserving-summarization/blob/HEAD/stratifiers/StratifierKullbackLeibler.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8c91bd640a67c01c","mcp_get_code":{"code_sha256":"8c91bd640a67c01c"}},{"arxiv_id":"2607.09893","paper":"/paper/arxiv-2607-09893","title":"An End-to-End Hybrid Quantum-Classical Sampling Workflow for Discrete Markov Random Fields: A Reproducible Case Study","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"arulrhikm/QuantumDGM","path":"src/metrics.py","file_url":"https://github.com/arulrhikm/QuantumDGM/blob/HEAD/src/metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b0cf13770f3cffcd","mcp_get_code":{"code_sha256":"b0cf13770f3cffcd"}},{"arxiv_id":"2606.18209","paper":"/paper/arxiv-2606-18209","title":"Rethinking Dataset Distillation for Classification: Do Distilled Sets Outperform Coresets?","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"AyushRoy2001/ManifoldGD","path":"kl.py","file_url":"https://github.com/AyushRoy2001/ManifoldGD/blob/HEAD/kl.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6a59f07f0b669e9e","mcp_get_code":{"code_sha256":"6a59f07f0b669e9e"}},{"arxiv_id":"2606.01340","paper":"/paper/arxiv-2606-01340","title":"Sample Complexity and Decision-Theoretic Guarantees for Bayesian Model Averaging over Decision Trees with Catalan-Exponential Priors","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"vitsch/jbdt","path":"src/bma_oracle.py","file_url":"https://github.com/vitsch/jbdt/blob/HEAD/src/bma_oracle.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3c3e6a0f9dde08a3","mcp_get_code":{"code_sha256":"3c3e6a0f9dde08a3"}},{"arxiv_id":"2603.01771","paper":"/paper/arxiv-2603-01771","title":"Hyperparameter Trajectory Inference with Conditional Lagrangian Optimal Transport","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"DLR-RM/stable-baselines3","path":"stable_baselines3/common/distributions.py","file_url":"https://github.com/DLR-RM/stable-baselines3/blob/HEAD/stable_baselines3/common/distributions.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b0d527dcd96cd8de","mcp_get_code":{"code_sha256":"b0d527dcd96cd8de"}},{"arxiv_id":"2601.11926","paper":"/paper/arxiv-2601-11926","title":"H𝑎𝑟𝑚𝑜𝑛𝑖𝑐𝑎: A Self-Adaptation Exemplar for Sustainable MLOps","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"sa4s-serc/HarmonE-tool","path":"tool/managed_system_cv/mape_logic/monitor.py","file_url":"https://github.com/sa4s-serc/HarmonE-tool/blob/HEAD/tool/managed_system_cv/mape_logic/monitor.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fcef7b2cb358d326","mcp_get_code":{"code_sha256":"fcef7b2cb358d326"}},{"arxiv_id":"2510.10116","paper":"/paper/arxiv-2510-10116","title":"Preference-driven Knowledge Distillation for Few-shot Node Classification","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"GEEX-Weixing/PKD","path":"arxiv_1.py","file_url":"https://github.com/GEEX-Weixing/PKD/blob/HEAD/arxiv_1.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cd53b01d81e7d384","mcp_get_code":{"code_sha256":"cd53b01d81e7d384"}},{"arxiv_id":"2509.20911","paper":"/paper/arxiv-2509-20911","title":"Mesh Interpolation Graph Network for Dynamic and Spatially Irregular Global Weather Forecasting","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"Graph-Machine-Learning-Group/taming-local-effects-stgnns","path":"lib/nn/losses.py","file_url":"https://github.com/Graph-Machine-Learning-Group/taming-local-effects-stgnns/blob/HEAD/lib/nn/losses.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7d883dfd1ef8ba72","mcp_get_code":{"code_sha256":"7d883dfd1ef8ba72"}},{"arxiv_id":"2507.19141","paper":null,"title":"arXiv:2507.19141","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"chenj02/DASH","path":"utils/loss_utils.py","file_url":"https://github.com/chenj02/DASH/blob/HEAD/utils/loss_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f3848cee9c6f43e3","mcp_get_code":{"code_sha256":"f3848cee9c6f43e3"}},{"arxiv_id":"2506.07298","paper":null,"title":"arXiv:2506.07298","date":null,"month_inferred_from_arxiv_id":"2025-06","title_source":null,"repo":"DaiYijia02/icl-hmm","path":"synthetic/evaluate.py","file_url":"https://github.com/DaiYijia02/icl-hmm/blob/HEAD/synthetic/evaluate.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":"7af8742ca199fe2e","mcp_get_code":{"code_sha256":"7af8742ca199fe2e"}},{"arxiv_id":"2505.18399","paper":"/paper/taming-diffusion-for-dataset-distillation","title":"Taming Diffusion for Dataset Distillation with High Representativeness","date":"2025-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lin-zhao-resolve/d3hr","path":"generation/group_sampling.py","file_url":"https://github.com/lin-zhao-resolve/d3hr/blob/HEAD/generation/group_sampling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"652cccb37631b811","mcp_get_code":{"code_sha256":"652cccb37631b811"}},{"arxiv_id":"2505.17003","paper":"/paper/sufficient-conditions-for-offline-1","title":"Sufficient conditions for offline reactivation in recurrent neural networks","date":"2025-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nandahkrishna/RNNReactivation","path":"utils.py","file_url":"https://github.com/nandahkrishna/RNNReactivation/blob/HEAD/utils.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":"93d7219bda1beca7","mcp_get_code":{"code_sha256":"93d7219bda1beca7"}},{"arxiv_id":"2505.13380","paper":"/paper/competesmoe-statistically-guaranteed-mixture","title":"CompeteSMoE -- Statistically Guaranteed Mixture of Experts Training via Competition","date":"2025-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"giangdip2410/competesmoe","path":"custom_layers_opt.py","file_url":"https://github.com/giangdip2410/competesmoe/blob/HEAD/custom_layers_opt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b334bcc524847095","mcp_get_code":{"code_sha256":"b334bcc524847095"}},{"arxiv_id":"2502.11196","paper":"/paper/how-do-llms-acquire-new-knowledge-a-knowledge","title":"How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training","date":"2025-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zjunlp/knowledgecircuits","path":"acdc/acdc_utils.py","file_url":"https://github.com/zjunlp/knowledgecircuits/blob/HEAD/acdc/acdc_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"de093820db99eddf","mcp_get_code":{"code_sha256":"de093820db99eddf"}},{"arxiv_id":"2501.14048","paper":"/paper/sidda-sinkhorn-dynamic-domain-adaptation-for","title":"SIDDA: SInkhorn Dynamic Domain Adaptation for Image Classification with Equivariant Neural Networks","date":"2025-01-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"deepskies/sidda","path":"src/scripts/train_SIDDA.py","file_url":"https://github.com/deepskies/sidda/blob/HEAD/src/scripts/train_SIDDA.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"fc8000b231339fd0","mcp_get_code":{"code_sha256":"fc8000b231339fd0"}},{"arxiv_id":"2412.08160","paper":"/paper/dg-mamba-robust-and-efficient-dynamic-graph","title":"DG-Mamba: Robust and Efficient Dynamic Graph Structure Learning with Selective State Space Models","date":"2024-12-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RingBDStack/DG-Mamba","path":"REDGSL.py","file_url":"https://github.com/RingBDStack/DG-Mamba/blob/HEAD/REDGSL.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fd7d71e5939fb04a","mcp_get_code":{"code_sha256":"fd7d71e5939fb04a"}},{"arxiv_id":"2412.07186","paper":"/paper/monte-carlo-tree-search-based-space-transfer","title":"Monte Carlo Tree Search based Space Transfer for Black-box Optimization","date":"2024-12-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lamda-bbo/mcts-transfer","path":"mcts/MCTS.py","file_url":"https://github.com/lamda-bbo/mcts-transfer/blob/HEAD/mcts/MCTS.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"583e40f60b83cc8b","mcp_get_code":{"code_sha256":"583e40f60b83cc8b"}},{"arxiv_id":"2411.02902","paper":"/paper/membership-inference-attacks-against-large","title":"Membership Inference Attacks against Large Vision-Language Models","date":"2024-11-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LIONS-EPFL/VL-MIA","path":"metric_util.py","file_url":"https://github.com/LIONS-EPFL/VL-MIA/blob/HEAD/metric_util.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":"af3c773aaee1147e","mcp_get_code":{"code_sha256":"af3c773aaee1147e"}},{"arxiv_id":"2410.23996","paper":"/paper/an-information-criterion-for-controlled","title":"An Information Criterion for Controlled Disentanglement of Multimodal Data","date":"2024-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uhlerlab/DisentangledSSL","path":"synthetic_task/losses.py","file_url":"https://github.com/uhlerlab/DisentangledSSL/blob/HEAD/synthetic_task/losses.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"28bcb2a124a000e4","mcp_get_code":{"code_sha256":"28bcb2a124a000e4"}},{"arxiv_id":"2410.14574","paper":"/paper/momentumsmoe-integrating-momentum-into-sparse","title":"MomentumSMoE: Integrating Momentum into Sparse Mixture of Experts","date":"2024-10-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rachtsy/MomentumSMoE","path":"custom_layers_opt.py","file_url":"https://github.com/rachtsy/MomentumSMoE/blob/HEAD/custom_layers_opt.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":"b334bcc524847095","mcp_get_code":{"code_sha256":"b334bcc524847095"}},{"arxiv_id":"2410.13708","paper":"/paper/on-the-role-of-attention-heads-in-large","title":"On the Role of Attention Heads in Large Language Model Safety","date":"2024-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ydyjya/safetyheadattribution","path":"lib/SHIPS/get_ships.py","file_url":"https://github.com/ydyjya/safetyheadattribution/blob/HEAD/lib/SHIPS/get_ships.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":"2c199cf061f618c1","mcp_get_code":{"code_sha256":"2c199cf061f618c1"}},{"arxiv_id":"2409.17840","paper":"/paper/detecting-and-measuring-confounding-using","title":"Detecting and Measuring Confounding Using Causal Mechanism Shifts","date":"2024-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gautam0707/cd_cnf","path":"setting1/ErdosRenyi/confounding_measure.py","file_url":"https://github.com/gautam0707/cd_cnf/blob/HEAD/setting1/ErdosRenyi/confounding_measure.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"379cd203182267e3","mcp_get_code":{"code_sha256":"379cd203182267e3"}},{"arxiv_id":"2407.14364","paper":"/paper/towards-assessing-data-replication-in-music","title":"Towards Assessing Data Replication in Music Generation with Music Similarity Metrics on Raw Audio","date":"2024-07-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"roserbatlleroca/mira","path":"src/mira_sim/metrics/kldiv/kld_metric.py","file_url":"https://github.com/roserbatlleroca/mira/blob/HEAD/src/mira_sim/metrics/kldiv/kld_metric.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"AGPL-3.0","inline_ok":false,"code_sha256_prefix":"ee53047b4a3470aa","mcp_get_code":{"code_sha256":"ee53047b4a3470aa"}},{"arxiv_id":"2406.19298","paper":"/paper/compositional-image-decomposition-with","title":"Compositional Image Decomposition with Diffusion Models","date":"2024-06-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"1Konny/Beta-VAE","path":"solver.py","file_url":"https://github.com/1Konny/Beta-VAE/blob/HEAD/solver.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"39b467466c64b8ed","mcp_get_code":{"code_sha256":"39b467466c64b8ed"}},{"arxiv_id":"2406.08938","paper":"/paper/mirror-and-preconditioned-gradient-descent-in","title":"Mirror and Preconditioned Gradient Descent in Wasserstein Space","date":"2024-06-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"clbonet/Mirror_and_Preconditioned_Gradient_Descent_in_Wasserstein_Space","path":"xps_Gaussians/xp_gaussian.py","file_url":"https://github.com/clbonet/Mirror_and_Preconditioned_Gradient_Descent_in_Wasserstein_Space/blob/HEAD/xps_Gaussians/xp_gaussian.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"969166020ca100c0","mcp_get_code":{"code_sha256":"969166020ca100c0"}},{"arxiv_id":"2406.08332","paper":"/paper/udon-universal-dynamic-online-distillation","title":"UDON: Universal Dynamic Online distillatioN for generic image representations","date":"2024-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nikosips/UDON","path":"universal_embedding/loss_utils.py","file_url":"https://github.com/nikosips/UDON/blob/HEAD/universal_embedding/loss_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fbe85c54819c6bdf","mcp_get_code":{"code_sha256":"fbe85c54819c6bdf"}},{"arxiv_id":"2406.07826","paper":"/paper/the-max-min-formulation-of-multi-objective","title":"The Max-Min Formulation of Multi-Objective Reinforcement Learning: From Theory to a Model-Free Algorithm","date":"2024-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"giseung-park/maxmin-morl","path":"supplementary_ICML24/stable_baselines3/common/distributions.py","file_url":"https://github.com/giseung-park/maxmin-morl/blob/HEAD/supplementary_ICML24/stable_baselines3/common/distributions.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f10351f5bf047910","mcp_get_code":{"code_sha256":"f10351f5bf047910"}},{"arxiv_id":"2405.14276","paper":"/paper/d-miso-editing-dynamic-3d-scenes-using-multi","title":"D-MiSo: Editing Dynamic 3D Scenes using Multi-Gaussians Soup","date":"2024-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"waczjoan/D-MiSo","path":"utils/loss_utils.py","file_url":"https://github.com/waczjoan/D-MiSo/blob/HEAD/utils/loss_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f3848cee9c6f43e3","mcp_get_code":{"code_sha256":"f3848cee9c6f43e3"}},{"arxiv_id":"2405.14226","paper":"/paper/variational-delayed-policy-optimization","title":"Variational Delayed Policy Optimization","date":"2024-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qingyuanwunothing/vdpo","path":"VDPO.py","file_url":"https://github.com/qingyuanwunothing/vdpo/blob/HEAD/VDPO.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":"9af8fadcf673cf17","mcp_get_code":{"code_sha256":"9af8fadcf673cf17"}},{"arxiv_id":"2405.11605","paper":"/paper/switched-flow-matching-eliminating","title":"Switched Flow Matching: Eliminating Singularities via Switching ODEs","date":"2024-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tensorflow/gan","path":"tensorflow_gan/python/eval/classifier_metrics.py","file_url":"https://github.com/tensorflow/gan/blob/HEAD/tensorflow_gan/python/eval/classifier_metrics.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":"a3e29c3eb31126b7","mcp_get_code":{"code_sha256":"a3e29c3eb31126b7"}},{"arxiv_id":"2405.04405","paper":"/paper/weakly-supervised-residual-evidential","title":"Weakly-Supervised Residual Evidential Learning for Multi-Instance Uncertainty Estimation","date":"2024-05-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liupei101/MIREL","path":"loss/loss_edl.py","file_url":"https://github.com/liupei101/MIREL/blob/HEAD/loss/loss_edl.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b810113372d69a75","mcp_get_code":{"code_sha256":"b810113372d69a75"}},{"arxiv_id":"2404.14367","paper":"/paper/preference-fine-tuning-of-llms-should","title":"Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data","date":"2024-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Asap7772/understanding-rlhf","path":"bandit_experiment/metrics.py","file_url":"https://github.com/Asap7772/understanding-rlhf/blob/HEAD/bandit_experiment/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ed7aa020fea3c190","mcp_get_code":{"code_sha256":"ed7aa020fea3c190"}},{"arxiv_id":"2404.14313","paper":"/paper/self-supervised-alignment-with-mutual","title":"Self-Supervised Alignment with Mutual Information: Learning to Follow Principles without Preference Labels","date":"2024-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"janphilippfranken/sami","path":"src/sami/trainers/sami_trainer.py","file_url":"https://github.com/janphilippfranken/sami/blob/HEAD/src/sami/trainers/sami_trainer.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"84501014a71e038e","mcp_get_code":{"code_sha256":"84501014a71e038e"}},{"arxiv_id":"2404.10980","paper":"/paper/hyper-evidential-deep-learning-to-quantify","title":"Hyper Evidential Deep Learning to Quantify Composite Classification Uncertainty","date":"2024-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hugo101/hyperevidentialnn","path":"loss.py","file_url":"https://github.com/hugo101/hyperevidentialnn/blob/HEAD/loss.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"567ef00dd199f3ca","mcp_get_code":{"code_sha256":"567ef00dd199f3ca"}},{"arxiv_id":"2402.16897","paper":"/paper/reliable-conflictive-multi-view-learning","title":"Reliable Conflictive Multi-View Learning","date":"2024-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jiajunsi/RCML","path":"loss_function.py","file_url":"https://github.com/jiajunsi/RCML/blob/HEAD/loss_function.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c68ca74a791416fa","mcp_get_code":{"code_sha256":"c68ca74a791416fa"}},{"arxiv_id":"2402.11917","paper":"/paper/a-mechanistic-analysis-of-a-transformer","title":"A Mechanistic Analysis of a Transformer Trained on a Symbolic Multi-Step Reasoning Task","date":"2024-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"abhay-sheshadri/backward-chaining-circuits","path":"src/attention_knockout.py","file_url":"https://github.com/abhay-sheshadri/backward-chaining-circuits/blob/HEAD/src/attention_knockout.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0b3394b38c5b85c6","mcp_get_code":{"code_sha256":"0b3394b38c5b85c6"}},{"arxiv_id":"2402.11137","paper":"/paper/tunetables-context-optimization-for-scalable","title":"TuneTables: Context Optimization for Scalable Prior-Data Fitted Networks","date":"2024-02-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"penfever/TuneTables","path":"tunetables/losses.py","file_url":"https://github.com/penfever/TuneTables/blob/HEAD/tunetables/losses.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":"98d35d058dcc75c7","mcp_get_code":{"code_sha256":"98d35d058dcc75c7"}},{"arxiv_id":"2402.09345","paper":"/paper/mitigating-reward-hacking-via-information","title":"InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling","date":"2024-02-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"miaoyuchun/inform","path":"openrlhf/models/model_inform.py","file_url":"https://github.com/miaoyuchun/inform/blob/HEAD/openrlhf/models/model_inform.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":"04d7f678f5b3f532","mcp_get_code":{"code_sha256":"04d7f678f5b3f532"}},{"arxiv_id":"2312.02567","paper":"/paper/think-twice-before-selection-federated","title":"Think Twice Before Selection: Federated Evidential Active Learning for Medical Image Analysis with Domain Shifts","date":"2023-12-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jiayichen815/feal","path":"utils/loss_func.py","file_url":"https://github.com/jiayichen815/feal/blob/HEAD/utils/loss_func.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a98b330060c19a96","mcp_get_code":{"code_sha256":"a98b330060c19a96"}},{"arxiv_id":"2311.15838","paper":"/paper/utilizing-explainability-techniques-for","title":"Utilizing Explainability Techniques for Reinforcement Learning Model Assurance","date":"2023-11-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mitre/arlin","path":"arlin/adversarial/metrics.py","file_url":"https://github.com/mitre/arlin/blob/HEAD/arlin/adversarial/metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"f0ceb8a7b51b4ad1","mcp_get_code":{"code_sha256":"f0ceb8a7b51b4ad1"}},{"arxiv_id":"2311.00430","paper":"/paper/distil-whisper-robust-knowledge-distillation","title":"Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling","date":"2023-11-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"innerNULL/simpler-distil-whisper","path":"run_distillation.py","file_url":"https://github.com/innerNULL/simpler-distil-whisper/blob/HEAD/run_distillation.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4d942c3663846d26","mcp_get_code":{"code_sha256":"4d942c3663846d26"}},{"arxiv_id":"2309.16515","paper":"/paper/latent-noise-segmentation-how-neural-noise","title":"Latent Noise Segmentation: How Neural Noise Leads to the Emergence of Segmentation and Grouping","date":"2023-09-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZhengqingUUU/LatentNoiseSegmentation","path":"solver.py","file_url":"https://github.com/ZhengqingUUU/LatentNoiseSegmentation/blob/HEAD/solver.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"8e97dcc43326b0c1","mcp_get_code":{"code_sha256":"8e97dcc43326b0c1"}},{"arxiv_id":"2309.13101","paper":"/paper/deformable-3d-gaussians-for-high-fidelity","title":"Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction","date":"2023-09-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ingra14m/deformable-3d-gaussians","path":"utils/loss_utils.py","file_url":"https://github.com/ingra14m/deformable-3d-gaussians/blob/HEAD/utils/loss_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f3848cee9c6f43e3","mcp_get_code":{"code_sha256":"f3848cee9c6f43e3"}},{"arxiv_id":"2309.02995","paper":"/paper/continual-evidential-deep-learning-for-out-of","title":"Continual Evidential Deep Learning for Out-of-Distribution Detection","date":"2023-09-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eaaguilart/cedl","path":"losses.py","file_url":"https://github.com/eaaguilart/cedl/blob/HEAD/losses.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1b5e3e91270b3492","mcp_get_code":{"code_sha256":"1b5e3e91270b3492"}},{"arxiv_id":"2307.16210","paper":"/paper/rethinking-uncertainly-missing-and-ambiguous","title":"Rethinking Uncertainly Missing and Ambiguous Visual Modality in Multi-Modal Entity Alignment","date":"2023-07-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zjukg/umaea","path":"UMAEA/model/Tool_model.py","file_url":"https://github.com/zjukg/umaea/blob/HEAD/UMAEA/model/Tool_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"69962e3b2cc8db6d","mcp_get_code":{"code_sha256":"69962e3b2cc8db6d"}},{"arxiv_id":"2307.02245","paper":"/paper/set-learning-for-accurate-and-calibrated","title":"Set Learning for Accurate and Calibrated Models","date":"2023-07-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lukasmut/oko","path":"training/loss_funs.py","file_url":"https://github.com/lukasmut/oko/blob/HEAD/training/loss_funs.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"84c83fbd0d15c014","mcp_get_code":{"code_sha256":"84c83fbd0d15c014"}},{"arxiv_id":"2306.02018","paper":"/paper/videocomposer-compositional-video-synthesis","title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","date":"2023-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"damo-vilab/videocomposer","path":"artist/ops/losses.py","file_url":"https://github.com/damo-vilab/videocomposer/blob/HEAD/artist/ops/losses.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"24f8868cf6825433","mcp_get_code":{"code_sha256":"24f8868cf6825433"}},{"arxiv_id":"2306.01574","paper":"/paper/probabilistic-concept-bottleneck-models","title":"Probabilistic Concept Bottleneck Models","date":"2023-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"samuelebortolotti/bears","path":"XOR_MNIST/models/mnistpcbmdpl.py","file_url":"https://github.com/samuelebortolotti/bears/blob/HEAD/XOR_MNIST/models/mnistpcbmdpl.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7f0ddf1b30b1a8ac","mcp_get_code":{"code_sha256":"7f0ddf1b30b1a8ac"}},{"arxiv_id":"2305.19158","paper":"/paper/competing-for-shareable-arms-in-multi-player","title":"Competing for Shareable Arms in Multi-Player Multi-Armed Bandits","date":"2023-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"windxrz/smaa","path":"model/method.py","file_url":"https://github.com/windxrz/smaa/blob/HEAD/model/method.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d326593f87383098","mcp_get_code":{"code_sha256":"d326593f87383098"}},{"arxiv_id":"2305.13788","paper":"/paper/can-large-language-models-infer-and-disagree","title":"Can Large Language Models Capture Dissenting Human Voices?","date":"2023-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xfactlab/emnlp2023-LLM-Disagreement","path":"utils/metrics.py","file_url":"https://github.com/xfactlab/emnlp2023-LLM-Disagreement/blob/HEAD/utils/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cfd7ee739cccf02d","mcp_get_code":{"code_sha256":"cfd7ee739cccf02d"}},{"arxiv_id":"2304.14997","paper":"/paper/towards-automated-circuit-discovery-for-1","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","date":"2023-04-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ArthurConmy/Automatic-Circuit-Discovery","path":"acdc/acdc_utils.py","file_url":"https://github.com/ArthurConmy/Automatic-Circuit-Discovery/blob/HEAD/acdc/acdc_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"de093820db99eddf","mcp_get_code":{"code_sha256":"de093820db99eddf"}},{"arxiv_id":"2304.04307","paper":"/paper/priorcvae-scalable-mcmc-parameter-inference","title":"PriorCVAE: scalable MCMC parameter inference with Bayesian deep generative modelling","date":"2023-04-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"elizavetasemenova/priorCVAE_jax","path":"priorCVAE/losses/loss_units.py","file_url":"https://github.com/elizavetasemenova/priorCVAE_jax/blob/HEAD/priorCVAE/losses/loss_units.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"edc317cb9a6c1d03","mcp_get_code":{"code_sha256":"edc317cb9a6c1d03"}},{"arxiv_id":"2302.11215","paper":"/paper/energy-based-test-sample-adaptation-for","title":"Energy-Based Test Sample Adaptation for Domain Generalization","date":"2023-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zzzx1224/ebtsa-iclr2023","path":"ebmdg_main.py","file_url":"https://github.com/zzzx1224/ebtsa-iclr2023/blob/HEAD/ebmdg_main.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":"cb955692fef4dc97","mcp_get_code":{"code_sha256":"cb955692fef4dc97"}},{"arxiv_id":"2302.01242","paper":"/paper/neuro-symbolic-continual-learning-knowledge","title":"Neuro-Symbolic Continual Learning: Knowledge, Reasoning Shortcuts and Concept Rehearsal","date":"2023-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ema-marconato/nesy-cl","path":"models/cool.py","file_url":"https://github.com/ema-marconato/nesy-cl/blob/HEAD/models/cool.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"79ad7949ae4becd4","mcp_get_code":{"code_sha256":"79ad7949ae4becd4"}},{"arxiv_id":"2301.07573","paper":"/paper/synthcity-facilitating-innovative-use-cases","title":"Synthcity: facilitating innovative use cases of synthetic data in different data modalities","date":"2023-01-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vanderschaarlab/datagnosis","path":"src/datagnosis/plugins/utils.py","file_url":"https://github.com/vanderschaarlab/datagnosis/blob/HEAD/src/datagnosis/plugins/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":"4c9ed631fb637b8b","mcp_get_code":{"code_sha256":"4c9ed631fb637b8b"}},{"arxiv_id":"2208.14226","paper":"/paper/unsupervised-representation-learning-in-deep","title":"Unsupervised Representation Learning in Deep Reinforcement Learning: A Review","date":"2022-08-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nicob15/state_representation_learning_methods","path":"losses.py","file_url":"https://github.com/nicob15/state_representation_learning_methods/blob/HEAD/losses.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1fb148e6ddfc2822","mcp_get_code":{"code_sha256":"1fb148e6ddfc2822"}},{"arxiv_id":"2206.07259","paper":"/paper/self-supervised-learning-of-image-scale-and","title":"Self-Supervised Learning of Image Scale and Orientation","date":"2022-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bluedream1121/self-sca-ori","path":"model/loss.py","file_url":"https://github.com/bluedream1121/self-sca-ori/blob/HEAD/model/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"faec82d84dd41fae","mcp_get_code":{"code_sha256":"faec82d84dd41fae"}},{"arxiv_id":"2206.05825","paper":"/paper/a-unified-approach-to-reinforcement-learning","title":"A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games","date":"2022-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ryan-dorazio/mmd-dilated","path":"mmd_dilated/mmd_dilated.py","file_url":"https://github.com/ryan-dorazio/mmd-dilated/blob/HEAD/mmd_dilated/mmd_dilated.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5b9b7639a0244fd3","mcp_get_code":{"code_sha256":"5b9b7639a0244fd3"}},{"arxiv_id":"2205.07649","paper":"/paper/generalizing-to-evolving-domains-with-latent","title":"Generalizing to Evolving Domains with Latent Structure-Aware Sequential Autoencoder","date":"2022-05-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wonderseven/lssae","path":"network/loss_func.py","file_url":"https://github.com/wonderseven/lssae/blob/HEAD/network/loss_func.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0a3e4f7eb14d940c","mcp_get_code":{"code_sha256":"0a3e4f7eb14d940c"}},{"arxiv_id":"2203.14542","paper":"/paper/unicon-combating-label-noise-through-uniform","title":"UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learning","date":"2022-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nazmul-karim170/unicon-noisy-label","path":"Train_TinyImageNet.py","file_url":"https://github.com/nazmul-karim170/unicon-noisy-label/blob/HEAD/Train_TinyImageNet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"666a24a593ecf0e9","mcp_get_code":{"code_sha256":"666a24a593ecf0e9"}},{"arxiv_id":"2110.15739","paper":"/paper/scalable-inference-in-sdes-by-direct-matching","title":"Scalable Inference in SDEs by Direct Matching of the Fokker-Planck-Kolmogorov Equation","date":"2021-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aaltoml/scalable-inference-in-sdes","path":"experiments/mnist/utility.py","file_url":"https://github.com/aaltoml/scalable-inference-in-sdes/blob/HEAD/experiments/mnist/utility.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6a2016f963be610b","mcp_get_code":{"code_sha256":"6a2016f963be610b"}},{"arxiv_id":"2106.13195","paper":"/paper/fitvid-overfitting-in-pixel-level-video","title":"FitVid: Overfitting in Pixel-Level Video Prediction","date":"2021-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-research/fitvid","path":"utils.py","file_url":"https://github.com/google-research/fitvid/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":"edaff51d9900895f","mcp_get_code":{"code_sha256":"edaff51d9900895f"}},{"arxiv_id":"2106.07551","paper":"/paper/malib-a-parallel-framework-for-population","title":"MALib: A Parallel Framework for Population-based Multi-agent Reinforcement Learning","date":"2021-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sjtu-marl/malib","path":"malib/common/distributions.py","file_url":"https://github.com/sjtu-marl/malib/blob/HEAD/malib/common/distributions.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f421411323056f50","mcp_get_code":{"code_sha256":"f421411323056f50"}},{"arxiv_id":"2105.14203","paper":"/paper/understanding-instance-based-interpretability","title":"Understanding Instance-based Interpretability of Variational Auto-Encoders","date":"2021-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fengnima/vae-tracin-pytorch","path":"tracin.py","file_url":"https://github.com/fengnima/vae-tracin-pytorch/blob/HEAD/tracin.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"39b467466c64b8ed","mcp_get_code":{"code_sha256":"39b467466c64b8ed"}},{"arxiv_id":"2010.14484","paper":"/paper/one-solution-is-not-all-you-need-few-shot","title":"One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL","date":"2020-10-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"egiob/diversityisallyouneed-sb3","path":"stable_baselines3/common/distributions.py","file_url":"https://github.com/egiob/diversityisallyouneed-sb3/blob/HEAD/stable_baselines3/common/distributions.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"df19469790ae30d9","mcp_get_code":{"code_sha256":"df19469790ae30d9"}},{"arxiv_id":"2009.01006","paper":"/paper/nonlinear-stochastic-modeling-with-langevin","title":"Nonlinear stochastic modeling with Langevin regression","date":null,"month_inferred_from_arxiv_id":"2020-09","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":"dec4ae98a83e72ce","mcp_get_code":{"code_sha256":"dec4ae98a83e72ce"}},{"arxiv_id":"2008.03312","paper":"/paper/complete-parameter-inference-for-gw150914","title":"Complete parameter inference for GW150914 using deep learning","date":"2020-08-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AI-HPC-Research-Team/GW","path":"evaluate_PCL_test_sh.py","file_url":"https://github.com/AI-HPC-Research-Team/GW/blob/HEAD/evaluate_PCL_test_sh.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f546f0fd69ff1ae0","mcp_get_code":{"code_sha256":"f546f0fd69ff1ae0"}},{"arxiv_id":"2007.11412","paper":"/paper/coarse-graining-molecular-dynamics-with-graph","title":"Coarse Graining Molecular Dynamics with Graph Neural Networks","date":"2020-07-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"coarse-graining/cgnet","path":"cgnet/feature/statistics.py","file_url":"https://github.com/coarse-graining/cgnet/blob/HEAD/cgnet/feature/statistics.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":"a5407c20e5c64c1c","mcp_get_code":{"code_sha256":"a5407c20e5c64c1c"}},{"arxiv_id":"2006.13169","paper":"/paper/experience-replay-with-likelihood-free","title":"Experience Replay with Likelihood-free Importance Weights","date":"2020-06-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AIDefender/MyDiscor","path":"discor/algorithm/rlkit/torch/iwq/iwq.py","file_url":"https://github.com/AIDefender/MyDiscor/blob/HEAD/discor/algorithm/rlkit/torch/iwq/iwq.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"310c696192de629c","mcp_get_code":{"code_sha256":"310c696192de629c"}},{"arxiv_id":"2004.07229","paper":"/paper/network-medicine-framework-for-identifying","title":"Network Medicine Framework for Identifying Drug Repurposing Opportunities for COVID-19","date":"2020-04-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Barabasi-Lab/COVID-19","path":"03_1_DR_Diff_matrix_generator.py","file_url":"https://github.com/Barabasi-Lab/COVID-19/blob/HEAD/03_1_DR_Diff_matrix_generator.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"08d9e207afab098a","mcp_get_code":{"code_sha256":"08d9e207afab098a"}},{"arxiv_id":"2001.08957","paper":"/paper/an-explicit-local-and-global-representation","title":"An Explicit Local and Global Representation Disentanglement Framework with Applications in Deep Clustering and Unsupervised Object Detection","date":"2020-01-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"51616/split-vae","path":"vae/trainer.py","file_url":"https://github.com/51616/split-vae/blob/HEAD/vae/trainer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"978b2197d45a49c5","mcp_get_code":{"code_sha256":"978b2197d45a49c5"}},{"arxiv_id":"2001.08957","paper":"/paper/an-explicit-local-and-global-representation","title":"An Explicit Local and Global Representation Disentanglement Framework with Applications in Deep Clustering and Unsupervised Object Detection","date":"2020-01-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"51616/split-vae","path":"spair/trainer.py","file_url":"https://github.com/51616/split-vae/blob/HEAD/spair/trainer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"06d6e95f7b14b7dd","mcp_get_code":{"code_sha256":"06d6e95f7b14b7dd"}},{"arxiv_id":"1912.13361","paper":"/paper/learning-representations-by-maximizing-mutual-1","title":"Learning Representations by Maximizing Mutual Information in Variational Autoencoders","date":"2019-12-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AliLotfi92/InfoMaxVAE","path":"CelebA/InfoMaxVAE_CelebA.py","file_url":"https://github.com/AliLotfi92/InfoMaxVAE/blob/HEAD/CelebA/InfoMaxVAE_CelebA.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":"36190b3f24d53e67","mcp_get_code":{"code_sha256":"36190b3f24d53e67"}},{"arxiv_id":"1912.13361","paper":"/paper/learning-representations-by-maximizing-mutual-1","title":"Learning Representations by Maximizing Mutual Information in Variational Autoencoders","date":"2019-12-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AliLotfi92/InfoMaxVAE","path":"utils/loss.py","file_url":"https://github.com/AliLotfi92/InfoMaxVAE/blob/HEAD/utils/loss.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":"c1a0329ea6182b87","mcp_get_code":{"code_sha256":"c1a0329ea6182b87"}},{"arxiv_id":"1905.10876","paper":"/paper/expressibility-and-entangling-capability-of","title":"Expressibility and entangling capability of parameterized quantum circuits for hybrid quantum-classical algorithms","date":null,"month_inferred_from_arxiv_id":"2019-05","title_source":"archive","repo":"String137/Create-your-design-of-Parameterized-Quantum-Circuits","path":"PQC.py","file_url":"https://github.com/String137/Create-your-design-of-Parameterized-Quantum-Circuits/blob/HEAD/PQC.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c8335906d9819c62","mcp_get_code":{"code_sha256":"c8335906d9819c62"}},{"arxiv_id":"1905.10876","paper":"/paper/expressibility-and-entangling-capability-of","title":"Expressibility and entangling capability of parameterized quantum circuits for hybrid quantum-classical algorithms","date":null,"month_inferred_from_arxiv_id":"2019-05","title_source":"archive","repo":"mballarin97/mps_qnn","path":"qcircha/expressivity.py","file_url":"https://github.com/mballarin97/mps_qnn/blob/HEAD/qcircha/expressivity.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":"186b27d35573175a","mcp_get_code":{"code_sha256":"186b27d35573175a"}},{"arxiv_id":"1903.08066","paper":"/paper/trained-uniform-quantization-for-accurate-and","title":"Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networks","date":"2019-03-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PannenetsF/TQT","path":"tqt/analyse/kl.py","file_url":"https://github.com/PannenetsF/TQT/blob/HEAD/tqt/analyse/kl.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":"ed42e29f9cacc3f3","mcp_get_code":{"code_sha256":"ed42e29f9cacc3f3"}},{"arxiv_id":"1902.01568","paper":"/paper/relevance-factor-vae-learning-and-identifying","title":"Relevance Factor VAE: Learning and Identifying Disentangled Factors","date":"2019-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ThomasMrY/RF-VAE","path":"ops.py","file_url":"https://github.com/ThomasMrY/RF-VAE/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":"915d409704261ce3","mcp_get_code":{"code_sha256":"915d409704261ce3"}},{"arxiv_id":"1811.11165","paper":"/paper/label-noise-robust-generative-adversarial","title":"Label-Noise Robust Generative Adversarial Networks","date":"2018-11-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"takuhirok/CP-GAN","path":"utils/util.py","file_url":"https://github.com/takuhirok/CP-GAN/blob/HEAD/utils/util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"16904ff198a1b88e","mcp_get_code":{"code_sha256":"16904ff198a1b88e"}},{"arxiv_id":"1807.10300","paper":"/paper/discovering-physical-concepts-with-neural","title":"Discovering physical concepts with neural networks","date":"2018-07-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fd17/SciNet_PyTorch","path":"models.py","file_url":"https://github.com/fd17/SciNet_PyTorch/blob/HEAD/models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b7ecf10c7192ae78","mcp_get_code":{"code_sha256":"b7ecf10c7192ae78"}},{"arxiv_id":"1807.00412","paper":"/paper/learning-to-drive-in-a-day","title":"Learning to Drive in a Day","date":"2018-07-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bitsauce/Carla-ppo","path":"vae/models.py","file_url":"https://github.com/bitsauce/Carla-ppo/blob/HEAD/vae/models.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c58cb9a54a9aab94","mcp_get_code":{"code_sha256":"c58cb9a54a9aab94"}},{"arxiv_id":"1806.04225","paper":"/paper/pac-bayes-control-synthesizing-controllers","title":"PAC-Bayes Control: Learning Policies that Provably Generalize to Novel Environments","date":"2018-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"irom-lab/PAC-Bayes-Control","path":"Extension-Domain_Shifts/utils.py","file_url":"https://github.com/irom-lab/PAC-Bayes-Control/blob/HEAD/Extension-Domain_Shifts/utils.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":"cbbc4f939b2eef2f","mcp_get_code":{"code_sha256":"cbbc4f939b2eef2f"}},{"arxiv_id":"1805.08318","paper":"/paper/self-attention-generative-adversarial","title":"Self-Attention Generative Adversarial Networks","date":"2018-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ilyakava/gan","path":"tensorflow_gan/python/eval/classifier_metrics.py","file_url":"https://github.com/ilyakava/gan/blob/HEAD/tensorflow_gan/python/eval/classifier_metrics.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":"a3e29c3eb31126b7","mcp_get_code":{"code_sha256":"a3e29c3eb31126b7"}},{"arxiv_id":"1802.05983","paper":"/paper/disentangling-by-factorising","title":"Disentangling by Factorising","date":"2018-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"1Konny/FactorVAE","path":"ops.py","file_url":"https://github.com/1Konny/FactorVAE/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":"36190b3f24d53e67","mcp_get_code":{"code_sha256":"36190b3f24d53e67"}},{"arxiv_id":"1712.02432","paper":"/paper/sparse-learning-of-stochastic-dynamic","title":"Sparse learning of stochastic dynamic equations","date":"2017-12-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dynamicslab/langevin-regression","path":"utils.py","file_url":"https://github.com/dynamicslab/langevin-regression/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"dec4ae98a83e72ce","mcp_get_code":{"code_sha256":"dec4ae98a83e72ce"}},{"arxiv_id":"1704.03976","paper":"/paper/virtual-adversarial-training-a-regularization","title":"Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning","date":"2017-04-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cherise215/maxstyle","path":"src/models/custom_loss.py","file_url":"https://github.com/cherise215/maxstyle/blob/HEAD/src/models/custom_loss.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"6a0687b01242a053","mcp_get_code":{"code_sha256":"6a0687b01242a053"}},{"arxiv_id":"1312.6114","paper":"/paper/auto-encoding-variational-bayes","title":"Auto-Encoding Variational Bayes","date":"2013-12-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"maxfrenzel/CompressionVAE","path":"cvae/lib/model_iaf.py","file_url":"https://github.com/maxfrenzel/CompressionVAE/blob/HEAD/cvae/lib/model_iaf.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":"37f8868e1e5d0997","mcp_get_code":{"code_sha256":"37f8868e1e5d0997"}},{"arxiv_id":"aaai_28598","paper":null,"title":"arXiv:aaai_28598","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"zzzzzzzzjy/MMNCD-main","path":"main_discover.py","file_url":"https://github.com/zzzzzzzzjy/MMNCD-main/blob/HEAD/main_discover.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7bc6fff975001381","mcp_get_code":{"code_sha256":"7bc6fff975001381"}},{"arxiv_id":"aaai_28598","paper":null,"title":"arXiv:aaai_28598","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"zzzzzzzzjy/MMNCD-main","path":"utils/pseudo_label_generation.py","file_url":"https://github.com/zzzzzzzzjy/MMNCD-main/blob/HEAD/utils/pseudo_label_generation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"38cc01da1aef35f9","mcp_get_code":{"code_sha256":"38cc01da1aef35f9"}},{"arxiv_id":"2022.findings-naacl.196","paper":null,"title":"arXiv:2022.findings-naacl.196","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"KindRoach/NAACL-ZEOP","path":"model/base_model.py","file_url":"https://github.com/KindRoach/NAACL-ZEOP/blob/HEAD/model/base_model.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":"87632c474e63a734","mcp_get_code":{"code_sha256":"87632c474e63a734"}}]}