{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FJH6K3COUAQLD6TDD7X6YA5DBZ","short_pith_number":"pith:FJH6K3CO","schema_version":"1.0","canonical_sha256":"2a4fe56c4ea020b1fa631fefec03a30e78b93ee7f781cff063b4ba4eee81c82b","source":{"kind":"arxiv","id":"2510.04602","version":4},"attestation_state":"computed","paper":{"title":"Wasserstein Gradient Flows for Scalable and Regularized Barycenter Computation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Eduardo Fernandes Montesuma, Mike Gartrell, Yassir Bendou","submitted_at":"2025-10-06T09:07:12Z","abstract_excerpt":"Wasserstein barycenters provide a principled approach for aggregating probability measures, while preserving the geometry of their ambient space. Existing discrete methods are not because as they assume access to the complete set of samples from the input measures. Meanwhile, neural network approaches do scale well, but rely on complex optimization problems and cannot easily incorporate label information. We address these limitations through gradient flows in the space of probability measures. Through time discretization, we achieve a scalable algorithm that i) relies on mini-batch optimal tra"},"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":"2510.04602","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-10-06T09:07:12Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"7b4cdc1ea2074d139f3065a95d7319ec287129b1b856a74761ce55cb105233d1","abstract_canon_sha256":"6ef1bc8940ea8185cf548a41b2c6d6b4b797d9e8af84e617c9ce0552e1369749"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T01:19:50.859233Z","signature_b64":"RSbLvl1qbp5hkUnyAZGeu4sSV0oureFs6Yz0gjpNw4wFdSdI+QcE/EoFBS743rBnWmqKLY7vpmMi5nAz0aZ5AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a4fe56c4ea020b1fa631fefec03a30e78b93ee7f781cff063b4ba4eee81c82b","last_reissued_at":"2026-07-27T01:19:50.858271Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T01:19:50.858271Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Wasserstein Gradient Flows for Scalable and Regularized Barycenter Computation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Eduardo Fernandes Montesuma, Mike Gartrell, Yassir Bendou","submitted_at":"2025-10-06T09:07:12Z","abstract_excerpt":"Wasserstein barycenters provide a principled approach for aggregating probability measures, while preserving the geometry of their ambient space. Existing discrete methods are not because as they assume access to the complete set of samples from the input measures. Meanwhile, neural network approaches do scale well, but rely on complex optimization problems and cannot easily incorporate label information. We address these limitations through gradient flows in the space of probability measures. Through time discretization, we achieve a scalable algorithm that i) relies on mini-batch optimal tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.04602","kind":"arxiv","version":4},"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/2510.04602/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":"2510.04602","created_at":"2026-07-27T01:19:50.858733+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.04602v4","created_at":"2026-07-27T01:19:50.858733+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.04602","created_at":"2026-07-27T01:19:50.858733+00:00"},{"alias_kind":"pith_short_12","alias_value":"FJH6K3COUAQL","created_at":"2026-07-27T01:19:50.858733+00:00"},{"alias_kind":"pith_short_16","alias_value":"FJH6K3COUAQLD6TD","created_at":"2026-07-27T01:19:50.858733+00:00"},{"alias_kind":"pith_short_8","alias_value":"FJH6K3CO","created_at":"2026-07-27T01:19:50.858733+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.24384","citing_title":"Provably convergent stochastic fixed-point algorithm for free-support Wasserstein barycenter of continuous non-parametric measures","ref_index":61,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FJH6K3COUAQLD6TDD7X6YA5DBZ","json":"https://pith.science/pith/FJH6K3COUAQLD6TDD7X6YA5DBZ.json","graph_json":"https://pith.science/api/pith-number/FJH6K3COUAQLD6TDD7X6YA5DBZ/graph.json","events_json":"https://pith.science/api/pith-number/FJH6K3COUAQLD6TDD7X6YA5DBZ/events.json","paper":"https://pith.science/paper/FJH6K3CO"},"agent_actions":{"view_html":"https://pith.science/pith/FJH6K3COUAQLD6TDD7X6YA5DBZ","download_json":"https://pith.science/pith/FJH6K3COUAQLD6TDD7X6YA5DBZ.json","view_paper":"https://pith.science/paper/FJH6K3CO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.04602&json=true","fetch_graph":"https://pith.science/api/pith-number/FJH6K3COUAQLD6TDD7X6YA5DBZ/graph.json","fetch_events":"https://pith.science/api/pith-number/FJH6K3COUAQLD6TDD7X6YA5DBZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FJH6K3COUAQLD6TDD7X6YA5DBZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FJH6K3COUAQLD6TDD7X6YA5DBZ/action/storage_attestation","attest_author":"https://pith.science/pith/FJH6K3COUAQLD6TDD7X6YA5DBZ/action/author_attestation","sign_citation":"https://pith.science/pith/FJH6K3COUAQLD6TDD7X6YA5DBZ/action/citation_signature","submit_replication":"https://pith.science/pith/FJH6K3COUAQLD6TDD7X6YA5DBZ/action/replication_record"}},"created_at":"2026-07-27T01:19:50.858733+00:00","updated_at":"2026-07-27T01:19:50.858733+00:00"}