{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JLHH3XTWE3F5E3ZRB2FF4AG5LY","short_pith_number":"pith:JLHH3XTW","schema_version":"1.0","canonical_sha256":"4ace7dde7626cbd26f310e8a5e00dd5e27b0abe9291173e42f3b1bfb91d1ebf1","source":{"kind":"arxiv","id":"2402.02239","version":3},"attestation_state":"computed","paper":{"title":"Distributional Reduction: Unifying Dimensionality Reduction and Clustering with Gromov-Wasserstein","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"C\\'edric Vincent-Cuaz, Hugues Van Assel, Nicolas Courty, Pascal Frossard, R\\'emi Flamary, Titouan Vayer","submitted_at":"2024-02-03T19:00:19Z","abstract_excerpt":"Unsupervised learning aims to capture the underlying structure of potentially large and high-dimensional datasets. Traditionally, this involves using dimensionality reduction (DR) methods to project data onto lower-dimensional spaces or organizing points into meaningful clusters (clustering). In this work, we revisit these approaches under the lens of optimal transport and exhibit relationships with the Gromov-Wasserstein problem. This unveils a new general framework, called distributional reduction, that recovers DR and clustering as special cases and allows addressing them jointly within a s"},"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":"2402.02239","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-03T19:00:19Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b3defde2d9bb093a3e3ac92fd59bd1a131d64867fd2af8ed673a0dfb01a79325","abstract_canon_sha256":"23f3cae6bdbecc70ef64d20271d01a64335e023b0d900e2e1d9763d57ff4a511"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:09.684156Z","signature_b64":"JclM3A8+YYodOVudhJVpFan8sVSr4KabPFjREIEyCTKsWR7MWdRPp/Hhu02iU7qNR7D3pGd+Q7yE60Ndr0BHAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ace7dde7626cbd26f310e8a5e00dd5e27b0abe9291173e42f3b1bfb91d1ebf1","last_reissued_at":"2026-07-05T11:28:09.683497Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:09.683497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distributional Reduction: Unifying Dimensionality Reduction and Clustering with Gromov-Wasserstein","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"C\\'edric Vincent-Cuaz, Hugues Van Assel, Nicolas Courty, Pascal Frossard, R\\'emi Flamary, Titouan Vayer","submitted_at":"2024-02-03T19:00:19Z","abstract_excerpt":"Unsupervised learning aims to capture the underlying structure of potentially large and high-dimensional datasets. Traditionally, this involves using dimensionality reduction (DR) methods to project data onto lower-dimensional spaces or organizing points into meaningful clusters (clustering). In this work, we revisit these approaches under the lens of optimal transport and exhibit relationships with the Gromov-Wasserstein problem. This unveils a new general framework, called distributional reduction, that recovers DR and clustering as special cases and allows addressing them jointly within a s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02239","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/2402.02239/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":"2402.02239","created_at":"2026-07-05T11:28:09.683678+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.02239v3","created_at":"2026-07-05T11:28:09.683678+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02239","created_at":"2026-07-05T11:28:09.683678+00:00"},{"alias_kind":"pith_short_12","alias_value":"JLHH3XTWE3F5","created_at":"2026-07-05T11:28:09.683678+00:00"},{"alias_kind":"pith_short_16","alias_value":"JLHH3XTWE3F5E3ZR","created_at":"2026-07-05T11:28:09.683678+00:00"},{"alias_kind":"pith_short_8","alias_value":"JLHH3XTW","created_at":"2026-07-05T11:28:09.683678+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06646","citing_title":"Diffusion enabled Optimal Transport distances for graph matching","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JLHH3XTWE3F5E3ZRB2FF4AG5LY","json":"https://pith.science/pith/JLHH3XTWE3F5E3ZRB2FF4AG5LY.json","graph_json":"https://pith.science/api/pith-number/JLHH3XTWE3F5E3ZRB2FF4AG5LY/graph.json","events_json":"https://pith.science/api/pith-number/JLHH3XTWE3F5E3ZRB2FF4AG5LY/events.json","paper":"https://pith.science/paper/JLHH3XTW"},"agent_actions":{"view_html":"https://pith.science/pith/JLHH3XTWE3F5E3ZRB2FF4AG5LY","download_json":"https://pith.science/pith/JLHH3XTWE3F5E3ZRB2FF4AG5LY.json","view_paper":"https://pith.science/paper/JLHH3XTW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.02239&json=true","fetch_graph":"https://pith.science/api/pith-number/JLHH3XTWE3F5E3ZRB2FF4AG5LY/graph.json","fetch_events":"https://pith.science/api/pith-number/JLHH3XTWE3F5E3ZRB2FF4AG5LY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JLHH3XTWE3F5E3ZRB2FF4AG5LY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JLHH3XTWE3F5E3ZRB2FF4AG5LY/action/storage_attestation","attest_author":"https://pith.science/pith/JLHH3XTWE3F5E3ZRB2FF4AG5LY/action/author_attestation","sign_citation":"https://pith.science/pith/JLHH3XTWE3F5E3ZRB2FF4AG5LY/action/citation_signature","submit_replication":"https://pith.science/pith/JLHH3XTWE3F5E3ZRB2FF4AG5LY/action/replication_record"}},"created_at":"2026-07-05T11:28:09.683678+00:00","updated_at":"2026-07-05T11:28:09.683678+00:00"}