{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EBSDLCC4JOF4AFD7X6PMO2TR5C","short_pith_number":"pith:EBSDLCC4","schema_version":"1.0","canonical_sha256":"206435885c4b8bc0147fbf9ec76a71e8879126f0440b2903863ec5db2ab17d9c","source":{"kind":"arxiv","id":"2402.11736","version":3},"attestation_state":"computed","paper":{"title":"Monte Carlo with kernel-based Gibbs measures: Guarantees for probabilistic herding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.PR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Martin Rouault, Myl\\`ene Ma\\\"ida, R\\'emi Bardenet","submitted_at":"2024-02-18T23:39:00Z","abstract_excerpt":"Kernel herding belongs to a family of deterministic quadratures that seek to minimize the maximum mean discrepancy (MMD), that is, the worst-case integration error over a reproducing kernel Hilbert space (RKHS). These MMD minimization procedures come with strong experimental support, but comparatively less theoretical footing. In particular, apart from recent progress in distribution compression, little has been proved in favor of an improvement of MMD minimization over classical Monte Carlo quadrature when the RKHS is infinite-dimensional. In this paper, we study a joint probability distribut"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2402.11736","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-18T23:39:00Z","cross_cats_sorted":["math.PR","stat.ML"],"title_canon_sha256":"d3856976ed0551ffe25e00263c705e073f158a5b7a120c00b57e7198835310d2","abstract_canon_sha256":"a18c7a3f8d721458d8f45a875b03bc37862a21477197c5a2c8bd255813d93518"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:15:01.685273Z","signature_b64":"0s63u9XG9R3flCYmD1ZMffIxqtPKUDoiMLejQegbbXXQf0dQ4qii9cPL+koAmoKOt8HfWTkyb+6XRpPhsOLgAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"206435885c4b8bc0147fbf9ec76a71e8879126f0440b2903863ec5db2ab17d9c","last_reissued_at":"2026-06-29T01:15:01.684853Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:15:01.684853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Monte Carlo with kernel-based Gibbs measures: Guarantees for probabilistic herding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.PR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Martin Rouault, Myl\\`ene Ma\\\"ida, R\\'emi Bardenet","submitted_at":"2024-02-18T23:39:00Z","abstract_excerpt":"Kernel herding belongs to a family of deterministic quadratures that seek to minimize the maximum mean discrepancy (MMD), that is, the worst-case integration error over a reproducing kernel Hilbert space (RKHS). These MMD minimization procedures come with strong experimental support, but comparatively less theoretical footing. In particular, apart from recent progress in distribution compression, little has been proved in favor of an improvement of MMD minimization over classical Monte Carlo quadrature when the RKHS is infinite-dimensional. In this paper, we study a joint probability distribut"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11736","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.11736/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2402.11736","created_at":"2026-06-29T01:15:01.684913+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.11736v3","created_at":"2026-06-29T01:15:01.684913+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11736","created_at":"2026-06-29T01:15:01.684913+00:00"},{"alias_kind":"pith_short_12","alias_value":"EBSDLCC4JOF4","created_at":"2026-06-29T01:15:01.684913+00:00"},{"alias_kind":"pith_short_16","alias_value":"EBSDLCC4JOF4AFD7","created_at":"2026-06-29T01:15:01.684913+00:00"},{"alias_kind":"pith_short_8","alias_value":"EBSDLCC4","created_at":"2026-06-29T01:15:01.684913+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.13127","citing_title":"State-of-art minibatches via novel DPP kernels: discretization, wavelets, and rough objectives","ref_index":69,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EBSDLCC4JOF4AFD7X6PMO2TR5C","json":"https://pith.science/pith/EBSDLCC4JOF4AFD7X6PMO2TR5C.json","graph_json":"https://pith.science/api/pith-number/EBSDLCC4JOF4AFD7X6PMO2TR5C/graph.json","events_json":"https://pith.science/api/pith-number/EBSDLCC4JOF4AFD7X6PMO2TR5C/events.json","paper":"https://pith.science/paper/EBSDLCC4"},"agent_actions":{"view_html":"https://pith.science/pith/EBSDLCC4JOF4AFD7X6PMO2TR5C","download_json":"https://pith.science/pith/EBSDLCC4JOF4AFD7X6PMO2TR5C.json","view_paper":"https://pith.science/paper/EBSDLCC4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.11736&json=true","fetch_graph":"https://pith.science/api/pith-number/EBSDLCC4JOF4AFD7X6PMO2TR5C/graph.json","fetch_events":"https://pith.science/api/pith-number/EBSDLCC4JOF4AFD7X6PMO2TR5C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EBSDLCC4JOF4AFD7X6PMO2TR5C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EBSDLCC4JOF4AFD7X6PMO2TR5C/action/storage_attestation","attest_author":"https://pith.science/pith/EBSDLCC4JOF4AFD7X6PMO2TR5C/action/author_attestation","sign_citation":"https://pith.science/pith/EBSDLCC4JOF4AFD7X6PMO2TR5C/action/citation_signature","submit_replication":"https://pith.science/pith/EBSDLCC4JOF4AFD7X6PMO2TR5C/action/replication_record"}},"created_at":"2026-06-29T01:15:01.684913+00:00","updated_at":"2026-06-29T01:15:01.684913+00:00"}