{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JFYRNV3U2MZ2OR7NL3HXGEUZSB","short_pith_number":"pith:JFYRNV3U","schema_version":"1.0","canonical_sha256":"497116d774d333a747ed5ecf731299906c67b1a645a9b987e372267904083cd8","source":{"kind":"arxiv","id":"2401.13913","version":2},"attestation_state":"computed","paper":{"title":"Spectral Clustering for Discrete Distributions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dong Qiao, Jicong Fan, Zixiao Wang","submitted_at":"2024-01-25T03:17:03Z","abstract_excerpt":"The discrete distribution is often used to describe complex instances in machine learning, such as images, sequences, and documents. Traditionally, clustering of discrete distributions (D2C) has been approached using Wasserstein barycenter methods. These methods operate under the assumption that clusters can be well-represented by barycenters, which is seldom true in many real-world applications. Additionally, these methods are not scalable for large datasets due to the high computational cost of calculating Wasserstein barycenters. In this work, we explore the feasibility of using spectral cl"},"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":"2401.13913","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-25T03:17:03Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"14ffa659ac972f9b43270302af3e11c340bf40dbd24c08955e27bf772bcd4619","abstract_canon_sha256":"8f64678d1a018a69d7e1931b79c29d7f28382652744026d152720f62f898ad05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:49.570966Z","signature_b64":"zCVvV1dHE1EV3mezcKsHfhVDz/6zRO+lfBYNfnVeqPbjPoz7BUlYikuVkd/YDonxd76XkRPa3QtOsGgzZcNQDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"497116d774d333a747ed5ecf731299906c67b1a645a9b987e372267904083cd8","last_reissued_at":"2026-07-05T08:55:49.570480Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:49.570480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spectral Clustering for Discrete Distributions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dong Qiao, Jicong Fan, Zixiao Wang","submitted_at":"2024-01-25T03:17:03Z","abstract_excerpt":"The discrete distribution is often used to describe complex instances in machine learning, such as images, sequences, and documents. Traditionally, clustering of discrete distributions (D2C) has been approached using Wasserstein barycenter methods. These methods operate under the assumption that clusters can be well-represented by barycenters, which is seldom true in many real-world applications. Additionally, these methods are not scalable for large datasets due to the high computational cost of calculating Wasserstein barycenters. In this work, we explore the feasibility of using spectral cl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.13913","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/2401.13913/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":"2401.13913","created_at":"2026-07-05T08:55:49.570545+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.13913v2","created_at":"2026-07-05T08:55:49.570545+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.13913","created_at":"2026-07-05T08:55:49.570545+00:00"},{"alias_kind":"pith_short_12","alias_value":"JFYRNV3U2MZ2","created_at":"2026-07-05T08:55:49.570545+00:00"},{"alias_kind":"pith_short_16","alias_value":"JFYRNV3U2MZ2OR7N","created_at":"2026-07-05T08:55:49.570545+00:00"},{"alias_kind":"pith_short_8","alias_value":"JFYRNV3U","created_at":"2026-07-05T08:55:49.570545+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/JFYRNV3U2MZ2OR7NL3HXGEUZSB","json":"https://pith.science/pith/JFYRNV3U2MZ2OR7NL3HXGEUZSB.json","graph_json":"https://pith.science/api/pith-number/JFYRNV3U2MZ2OR7NL3HXGEUZSB/graph.json","events_json":"https://pith.science/api/pith-number/JFYRNV3U2MZ2OR7NL3HXGEUZSB/events.json","paper":"https://pith.science/paper/JFYRNV3U"},"agent_actions":{"view_html":"https://pith.science/pith/JFYRNV3U2MZ2OR7NL3HXGEUZSB","download_json":"https://pith.science/pith/JFYRNV3U2MZ2OR7NL3HXGEUZSB.json","view_paper":"https://pith.science/paper/JFYRNV3U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.13913&json=true","fetch_graph":"https://pith.science/api/pith-number/JFYRNV3U2MZ2OR7NL3HXGEUZSB/graph.json","fetch_events":"https://pith.science/api/pith-number/JFYRNV3U2MZ2OR7NL3HXGEUZSB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JFYRNV3U2MZ2OR7NL3HXGEUZSB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JFYRNV3U2MZ2OR7NL3HXGEUZSB/action/storage_attestation","attest_author":"https://pith.science/pith/JFYRNV3U2MZ2OR7NL3HXGEUZSB/action/author_attestation","sign_citation":"https://pith.science/pith/JFYRNV3U2MZ2OR7NL3HXGEUZSB/action/citation_signature","submit_replication":"https://pith.science/pith/JFYRNV3U2MZ2OR7NL3HXGEUZSB/action/replication_record"}},"created_at":"2026-07-05T08:55:49.570545+00:00","updated_at":"2026-07-05T08:55:49.570545+00:00"}