{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CQFJM2CSIM3BKR2XEF7HZYZ6CW","short_pith_number":"pith:CQFJM2CS","schema_version":"1.0","canonical_sha256":"140a9668524336154757217e7ce33e159364f294b917a639e3e4dfbdc05e5b6a","source":{"kind":"arxiv","id":"2508.04200","version":1},"attestation_state":"computed","paper":{"title":"Bootstrap Deep Spectral Clustering with Optimal Transport","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Christian B\\\"ohm, Chunchun Chen, Claudia Plant, Susanto Rahardja, Wei Ye, Wengang Guo, Xin Sun","submitted_at":"2025-08-06T08:30:30Z","abstract_excerpt":"Spectral clustering is a leading clustering method. Two of its major shortcomings are the disjoint optimization process and the limited representation capacity. To address these issues, we propose a deep spectral clustering model (named BootSC), which jointly learns all stages of spectral clustering -- affinity matrix construction, spectral embedding, and $k$-means clustering -- using a single network in an end-to-end manner. BootSC leverages effective and efficient optimal-transport-derived supervision to bootstrap the affinity matrix and the cluster assignment matrix. Moreover, a semanticall"},"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":"2508.04200","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-06T08:30:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2dea10982e5eebd75f135b8c64d62d389ac5abcacf1d1081802937c9f7021466","abstract_canon_sha256":"3994265e850906ad7b485c39534dd03f135215ae5a6da6d0a8d66500bdc4cf35"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:22.706367Z","signature_b64":"qCXKhXfPoTD4qm54UpgXSoj3F4wRLPXO6rXBq3oUvyrgAAovDLC2lRyz+RegZf7VObj3ED/3foilU/qos26RDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"140a9668524336154757217e7ce33e159364f294b917a639e3e4dfbdc05e5b6a","last_reissued_at":"2026-07-05T11:49:22.705839Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:22.705839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bootstrap Deep Spectral Clustering with Optimal Transport","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Christian B\\\"ohm, Chunchun Chen, Claudia Plant, Susanto Rahardja, Wei Ye, Wengang Guo, Xin Sun","submitted_at":"2025-08-06T08:30:30Z","abstract_excerpt":"Spectral clustering is a leading clustering method. Two of its major shortcomings are the disjoint optimization process and the limited representation capacity. To address these issues, we propose a deep spectral clustering model (named BootSC), which jointly learns all stages of spectral clustering -- affinity matrix construction, spectral embedding, and $k$-means clustering -- using a single network in an end-to-end manner. BootSC leverages effective and efficient optimal-transport-derived supervision to bootstrap the affinity matrix and the cluster assignment matrix. Moreover, a semanticall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.04200","kind":"arxiv","version":1},"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/2508.04200/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":"2508.04200","created_at":"2026-07-05T11:49:22.705900+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.04200v1","created_at":"2026-07-05T11:49:22.705900+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.04200","created_at":"2026-07-05T11:49:22.705900+00:00"},{"alias_kind":"pith_short_12","alias_value":"CQFJM2CSIM3B","created_at":"2026-07-05T11:49:22.705900+00:00"},{"alias_kind":"pith_short_16","alias_value":"CQFJM2CSIM3BKR2X","created_at":"2026-07-05T11:49:22.705900+00:00"},{"alias_kind":"pith_short_8","alias_value":"CQFJM2CS","created_at":"2026-07-05T11:49:22.705900+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/CQFJM2CSIM3BKR2XEF7HZYZ6CW","json":"https://pith.science/pith/CQFJM2CSIM3BKR2XEF7HZYZ6CW.json","graph_json":"https://pith.science/api/pith-number/CQFJM2CSIM3BKR2XEF7HZYZ6CW/graph.json","events_json":"https://pith.science/api/pith-number/CQFJM2CSIM3BKR2XEF7HZYZ6CW/events.json","paper":"https://pith.science/paper/CQFJM2CS"},"agent_actions":{"view_html":"https://pith.science/pith/CQFJM2CSIM3BKR2XEF7HZYZ6CW","download_json":"https://pith.science/pith/CQFJM2CSIM3BKR2XEF7HZYZ6CW.json","view_paper":"https://pith.science/paper/CQFJM2CS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.04200&json=true","fetch_graph":"https://pith.science/api/pith-number/CQFJM2CSIM3BKR2XEF7HZYZ6CW/graph.json","fetch_events":"https://pith.science/api/pith-number/CQFJM2CSIM3BKR2XEF7HZYZ6CW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CQFJM2CSIM3BKR2XEF7HZYZ6CW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CQFJM2CSIM3BKR2XEF7HZYZ6CW/action/storage_attestation","attest_author":"https://pith.science/pith/CQFJM2CSIM3BKR2XEF7HZYZ6CW/action/author_attestation","sign_citation":"https://pith.science/pith/CQFJM2CSIM3BKR2XEF7HZYZ6CW/action/citation_signature","submit_replication":"https://pith.science/pith/CQFJM2CSIM3BKR2XEF7HZYZ6CW/action/replication_record"}},"created_at":"2026-07-05T11:49:22.705900+00:00","updated_at":"2026-07-05T11:49:22.705900+00:00"}