{"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/mmd","entry":"mmd","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":21,"n_papers_ran":8,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":19,"n_samples_ran":7,"n_samples_fingerprinted":3,"n_places":21,"n_places_pointer_only":5,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":1,"ran":3,"unverified":12},"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":"2604.04567","paper":"/paper/arxiv-2604-04567","title":"Generative Modeling under Non-Monotone MAR Missingness via Approximate Wasserstein Gradient Flows","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"yujhml/MIRI-Imputation","path":"src/imputer.py","file_url":"https://github.com/yujhml/MIRI-Imputation/blob/HEAD/src/imputer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d4d24272a4c0a1b3","mcp_get_code":{"code_sha256":"d4d24272a4c0a1b3"}},{"arxiv_id":"2602.03625","paper":"/paper/arxiv-2602-03625","title":"Multi-Objective Optimization for Synthetic-to-Real Style Transfer","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"echigot/MOOSS","path":"mooss/cmmd.py","file_url":"https://github.com/echigot/MOOSS/blob/HEAD/mooss/cmmd.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"99ac6ca026cab870","mcp_get_code":{"code_sha256":"99ac6ca026cab870"}},{"arxiv_id":"2509.20177","paper":"/paper/arxiv-2509-20177","title":"Generative Model Inversion Through the Lens of the Manifold Hypothesis","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"tmlr-group/AlignMI","path":"high_resolution/criteria/mmd_loss.py","file_url":"https://github.com/tmlr-group/AlignMI/blob/HEAD/high_resolution/criteria/mmd_loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"931e13e1f2b410bc","mcp_get_code":{"code_sha256":"931e13e1f2b410bc"}},{"arxiv_id":"2410.22872","paper":"/paper/data-subsampling-for-poisson-regression-with","title":"Data subsampling for Poisson regression with pth-root-link","date":"2024-10-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Tim907/poisson-regression","path":"efficient_poisson_regression/metrics.py","file_url":"https://github.com/Tim907/poisson-regression/blob/HEAD/efficient_poisson_regression/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3c164ca8797dd680","mcp_get_code":{"code_sha256":"3c164ca8797dd680"}},{"arxiv_id":"2408.16543","paper":"/paper/statistical-and-geometrical-properties-of","title":"Statistical and Geometrical properties of regularized Kernel Kullback-Leibler divergence","date":"2024-08-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"clementinechazal/KKL-divergence-gradient-flows","path":"Regularized/kale_flow_master/kernel_wasserstein_flows/kernel_wasserstein_flows/mmd.py","file_url":"https://github.com/clementinechazal/KKL-divergence-gradient-flows/blob/HEAD/Regularized/kale_flow_master/kernel_wasserstein_flows/kernel_wasserstein_flows/mmd.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8d45b931b21286e0","mcp_get_code":{"code_sha256":"8d45b931b21286e0"}},{"arxiv_id":"2406.12042","paper":"/paper/not-all-prompts-are-made-equal-prompt-based","title":"Not All Prompts Are Made Equal: Prompt-based Pruning of Text-to-Image Diffusion Models","date":"2024-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rezashkv/diffusion_pruning","path":"cmmd-pytorch/distance.py","file_url":"https://github.com/rezashkv/diffusion_pruning/blob/HEAD/cmmd-pytorch/distance.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cbf43bceb31b386b","mcp_get_code":{"code_sha256":"cbf43bceb31b386b"}},{"arxiv_id":"2405.14449","paper":"/paper/adversarial-schrodinger-bridge-matching","title":"Adversarial Schrödinger Bridge Matching","date":"2024-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"daniil-selikhanovych/asbm","path":"notebooks_utils.py","file_url":"https://github.com/daniil-selikhanovych/asbm/blob/HEAD/notebooks_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"8314a8186f319b02","mcp_get_code":{"code_sha256":"8314a8186f319b02"}},{"arxiv_id":"2402.16041","paper":"/paper/detecting-machine-generated-texts-by-multi","title":"Detecting Machine-Generated Texts by Multi-Population Aware Optimization for Maximum Mean Discrepancy","date":"2024-02-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZSHsh98/MMD-MP","path":"MMD_calculate.py","file_url":"https://github.com/ZSHsh98/MMD-MP/blob/HEAD/MMD_calculate.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"93ebe405ab37744d","mcp_get_code":{"code_sha256":"93ebe405ab37744d"}},{"arxiv_id":"2402.08530","paper":"/paper/a-distributional-analogue-to-the-successor","title":"A Distributional Analogue to the Successor Representation","date":"2024-02-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jessefarebro/distributional-sr","path":"dsm/kernels.py","file_url":"https://github.com/jessefarebro/distributional-sr/blob/HEAD/dsm/kernels.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"966cb709a6527c2e","mcp_get_code":{"code_sha256":"966cb709a6527c2e"}},{"arxiv_id":"2401.09603","paper":"/paper/rethinking-fid-towards-a-better-evaluation","title":"Rethinking FID: Towards a Better Evaluation Metric for Image Generation","date":"2023-11-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sayakpaul/cmmd-pytorch","path":"distance.py","file_url":"https://github.com/sayakpaul/cmmd-pytorch/blob/HEAD/distance.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":"cbf43bceb31b386b","mcp_get_code":{"code_sha256":"cbf43bceb31b386b"}},{"arxiv_id":"2302.10607","paper":"/paper/differentiable-multi-target-causal-bayesian","title":"Differentiable Multi-Target Causal Bayesian Experimental Design","date":"2023-02-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yannadani/DiffCBED","path":"envs/causal_environment.py","file_url":"https://github.com/yannadani/DiffCBED/blob/HEAD/envs/causal_environment.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"067bb4384d99a74d","mcp_get_code":{"code_sha256":"067bb4384d99a74d"}},{"arxiv_id":"2302.00860","paper":"/paper/interventional-and-counterfactual-inference","title":"Modeling Causal Mechanisms with Diffusion Models for Interventional and Counterfactual Queries","date":"2023-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tatsu432/BDCM","path":"src/bdcm/infrastructure/mmd.py","file_url":"https://github.com/tatsu432/BDCM/blob/HEAD/src/bdcm/infrastructure/mmd.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e1188dd6fec1ecd6","mcp_get_code":{"code_sha256":"e1188dd6fec1ecd6"}},{"arxiv_id":"2210.12048","paper":"/paper/ollivier-ricci-curvature-for-hypergraphs-a","title":"Ollivier-Ricci Curvature for Hypergraphs: A Unified Framework","date":"2022-10-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aidos-lab/orchid","path":"experiments/mmd.py","file_url":"https://github.com/aidos-lab/orchid/blob/HEAD/experiments/mmd.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ef5629d6ce56031e","mcp_get_code":{"code_sha256":"ef5629d6ce56031e"}},{"arxiv_id":"2203.13568","paper":"/paper/p-generalized-probit-regression-and-scalable","title":"$p$-Generalized Probit Regression and Scalable Maximum Likelihood Estimation via Sketching and Coresets","date":"2022-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cxan96/efficient-probit-regression","path":"efficient_probit_regression/metrics.py","file_url":"https://github.com/cxan96/efficient-probit-regression/blob/HEAD/efficient_probit_regression/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3c164ca8797dd680","mcp_get_code":{"code_sha256":"3c164ca8797dd680"}},{"arxiv_id":"2201.01003","paper":"/paper/aligning-domain-specific-distribution-and","title":"Aligning Domain-specific Distribution and Classifier for Cross-domain Classification from Multiple Sources","date":"2022-01-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"easezyc/deep-transfer-learning","path":"MUDA/MFSAN/MFSAN_2src/mmd.py","file_url":"https://github.com/easezyc/deep-transfer-learning/blob/HEAD/MUDA/MFSAN/MFSAN_2src/mmd.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2bc0e2e480b078d3","mcp_get_code":{"code_sha256":"2bc0e2e480b078d3"}},{"arxiv_id":"2106.08161","paper":"/paper/contrastive-mixture-of-posteriors-for","title":"Contrastive Mixture of Posteriors for Counterfactual Inference, Data Integration and Fairness","date":"2021-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"BenevolentAI/CoMP","path":"comp/nn/loss.py","file_url":"https://github.com/BenevolentAI/CoMP/blob/HEAD/comp/nn/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6af69a37e94494a8","mcp_get_code":{"code_sha256":"6af69a37e94494a8"}},{"arxiv_id":"2106.01098","paper":"/paper/evaluation-metrics-for-graph-generative","title":"Evaluation Metrics for Graph Generative Models: Problems, Pitfalls, and Practical Solutions","date":"2021-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"borgwardtlab/ggme","path":"src/metrics/mmd.py","file_url":"https://github.com/borgwardtlab/ggme/blob/HEAD/src/metrics/mmd.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":"b8ddf9e892aa4b13","mcp_get_code":{"code_sha256":"b8ddf9e892aa4b13"}},{"arxiv_id":"2007.00163","paper":"/paper/identifying-causal-effect-inference-failure","title":"Identifying Causal-Effect Inference Failure with Uncertainty-Aware Models","date":"2020-07-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OATML/ucate","path":"ucate/library/models/tarnet.py","file_url":"https://github.com/OATML/ucate/blob/HEAD/ucate/library/models/tarnet.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":"6226c7421bb125b3","mcp_get_code":{"code_sha256":"6226c7421bb125b3"}},{"arxiv_id":"1910.09779","paper":"/paper/bridging-the-gap-between-f-gans-and","title":"Bridging the Gap Between $f$-GANs and Wasserstein GANs","date":"2019-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ermongroup/f-wgan","path":"synthetic/kl_wgan.py","file_url":"https://github.com/ermongroup/f-wgan/blob/HEAD/synthetic/kl_wgan.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5b24443b72aa5cc0","mcp_get_code":{"code_sha256":"5b24443b72aa5cc0"}},{"arxiv_id":"1807.11176","paper":"/paper/human-motion-analysis-with-deep-metric","title":"Human Motion Analysis with Deep Metric Learning","date":"2018-07-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dhesenkamp/attentive-lstm","path":"loss.py","file_url":"https://github.com/dhesenkamp/attentive-lstm/blob/HEAD/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"36f20b488dfdc730","mcp_get_code":{"code_sha256":"36f20b488dfdc730"}},{"arxiv_id":"1804.11271","paper":"/paper/gaussian-process-behaviour-in-wide-deep","title":"Gaussian Process Behaviour in Wide Deep Neural Networks","date":"2018-04-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"widedeepnetworks/widedeepnetworks","path":"mmd.py","file_url":"https://github.com/widedeepnetworks/widedeepnetworks/blob/HEAD/mmd.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":"b008cca820414f30","mcp_get_code":{"code_sha256":"b008cca820414f30"}}]}