{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:P3L5U44AGMPOZ3F52RCX7IKDL5","short_pith_number":"pith:P3L5U44A","schema_version":"1.0","canonical_sha256":"7ed7da7380331eececbdd4457fa1435f4a222730c49c75782c2b6b5483b18141","source":{"kind":"arxiv","id":"2106.09994","version":2},"attestation_state":"computed","paper":{"title":"A Note on Optimizing Distributions using Kernel Mean Embeddings","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alessandro Rudi, Boris Muzellec, Francis Bach","submitted_at":"2021-06-18T08:33:45Z","abstract_excerpt":"Kernel mean embeddings are a popular tool that consists in representing probability measures by their infinite-dimensional mean embeddings in a reproducing kernel Hilbert space. When the kernel is characteristic, mean embeddings can be used to define a distance between probability measures, known as the maximum mean discrepancy (MMD). A well-known advantage of mean embeddings and MMD is their low computational cost and low sample complexity. However, kernel mean embeddings have had limited applications to problems that consist in optimizing distributions, due to the difficulty of characterizin"},"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":"2106.09994","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-18T08:33:45Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9f48a66902ee137e7df4d002353210dc9a79207271c8507ef7c9216249090ede","abstract_canon_sha256":"e82bff46a3898c539756a0da5e1745b0e9ec39259aad85e3ba444ab7ffde59ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:52:45.852278Z","signature_b64":"xkmPlfMuD93RGqkcO95NmLMsujgAddc/23rnjn1KN2beweRKAIlNsd2DKxCzCoUyVjBfz0LHWrSLlxjEUCAVAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ed7da7380331eececbdd4457fa1435f4a222730c49c75782c2b6b5483b18141","last_reissued_at":"2026-07-05T02:52:45.851870Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:52:45.851870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Note on Optimizing Distributions using Kernel Mean Embeddings","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alessandro Rudi, Boris Muzellec, Francis Bach","submitted_at":"2021-06-18T08:33:45Z","abstract_excerpt":"Kernel mean embeddings are a popular tool that consists in representing probability measures by their infinite-dimensional mean embeddings in a reproducing kernel Hilbert space. When the kernel is characteristic, mean embeddings can be used to define a distance between probability measures, known as the maximum mean discrepancy (MMD). A well-known advantage of mean embeddings and MMD is their low computational cost and low sample complexity. However, kernel mean embeddings have had limited applications to problems that consist in optimizing distributions, due to the difficulty of characterizin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09994","kind":"arxiv","version":2},"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/2106.09994/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":"2106.09994","created_at":"2026-07-05T02:52:45.851922+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.09994v2","created_at":"2026-07-05T02:52:45.851922+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09994","created_at":"2026-07-05T02:52:45.851922+00:00"},{"alias_kind":"pith_short_12","alias_value":"P3L5U44AGMPO","created_at":"2026-07-05T02:52:45.851922+00:00"},{"alias_kind":"pith_short_16","alias_value":"P3L5U44AGMPOZ3F5","created_at":"2026-07-05T02:52:45.851922+00:00"},{"alias_kind":"pith_short_8","alias_value":"P3L5U44A","created_at":"2026-07-05T02:52:45.851922+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P3L5U44AGMPOZ3F52RCX7IKDL5","json":"https://pith.science/pith/P3L5U44AGMPOZ3F52RCX7IKDL5.json","graph_json":"https://pith.science/api/pith-number/P3L5U44AGMPOZ3F52RCX7IKDL5/graph.json","events_json":"https://pith.science/api/pith-number/P3L5U44AGMPOZ3F52RCX7IKDL5/events.json","paper":"https://pith.science/paper/P3L5U44A"},"agent_actions":{"view_html":"https://pith.science/pith/P3L5U44AGMPOZ3F52RCX7IKDL5","download_json":"https://pith.science/pith/P3L5U44AGMPOZ3F52RCX7IKDL5.json","view_paper":"https://pith.science/paper/P3L5U44A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.09994&json=true","fetch_graph":"https://pith.science/api/pith-number/P3L5U44AGMPOZ3F52RCX7IKDL5/graph.json","fetch_events":"https://pith.science/api/pith-number/P3L5U44AGMPOZ3F52RCX7IKDL5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P3L5U44AGMPOZ3F52RCX7IKDL5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P3L5U44AGMPOZ3F52RCX7IKDL5/action/storage_attestation","attest_author":"https://pith.science/pith/P3L5U44AGMPOZ3F52RCX7IKDL5/action/author_attestation","sign_citation":"https://pith.science/pith/P3L5U44AGMPOZ3F52RCX7IKDL5/action/citation_signature","submit_replication":"https://pith.science/pith/P3L5U44AGMPOZ3F52RCX7IKDL5/action/replication_record"}},"created_at":"2026-07-05T02:52:45.851922+00:00","updated_at":"2026-07-05T02:52:45.851922+00:00"}