{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HD7VX67YIDGEXOGONWIMKKB745","short_pith_number":"pith:HD7VX67Y","schema_version":"1.0","canonical_sha256":"38ff5bfbf840cc4bb8ce6d90c5283fe77c97fbe76be89138243512ad7a719a65","source":{"kind":"arxiv","id":"2403.10897","version":2},"attestation_state":"computed","paper":{"title":"Rethinking Multi-view Representation Learning via Distilled Disentangling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Bo Wang, Guanzhou Ke, Shengfeng He, Xiaoli Wang","submitted_at":"2024-03-16T11:21:24Z","abstract_excerpt":"Multi-view representation learning aims to derive robust representations that are both view-consistent and view-specific from diverse data sources. This paper presents an in-depth analysis of existing approaches in this domain, highlighting a commonly overlooked aspect: the redundancy between view-consistent and view-specific representations. To this end, we propose an innovative framework for multi-view representation learning, which incorporates a technique we term 'distilled disentangling'. Our method introduces the concept of masked cross-view prediction, enabling the extraction of compact"},"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":"2403.10897","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-16T11:21:24Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"79fd4992b84584230bd0a1cc3438ae0bd3966e3bbfed314fa1521f6393af66c4","abstract_canon_sha256":"6235ca57aefe1a7d7276db7d0a61ddb5a18161d887d51104c1ef466aa91bca15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:05.749004Z","signature_b64":"0mTSgxloFKIm1GETAIwHZWnIp4skgELBir27LFTiGUNA1/eJPvBkwF+G/0b1VEvhHzJmnwxJkVyYe4428KJbDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38ff5bfbf840cc4bb8ce6d90c5283fe77c97fbe76be89138243512ad7a719a65","last_reissued_at":"2026-07-05T08:02:05.748510Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:05.748510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Multi-view Representation Learning via Distilled Disentangling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Bo Wang, Guanzhou Ke, Shengfeng He, Xiaoli Wang","submitted_at":"2024-03-16T11:21:24Z","abstract_excerpt":"Multi-view representation learning aims to derive robust representations that are both view-consistent and view-specific from diverse data sources. This paper presents an in-depth analysis of existing approaches in this domain, highlighting a commonly overlooked aspect: the redundancy between view-consistent and view-specific representations. To this end, we propose an innovative framework for multi-view representation learning, which incorporates a technique we term 'distilled disentangling'. Our method introduces the concept of masked cross-view prediction, enabling the extraction of compact"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10897","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/2403.10897/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":"2403.10897","created_at":"2026-07-05T08:02:05.748575+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.10897v2","created_at":"2026-07-05T08:02:05.748575+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10897","created_at":"2026-07-05T08:02:05.748575+00:00"},{"alias_kind":"pith_short_12","alias_value":"HD7VX67YIDGE","created_at":"2026-07-05T08:02:05.748575+00:00"},{"alias_kind":"pith_short_16","alias_value":"HD7VX67YIDGEXOGO","created_at":"2026-07-05T08:02:05.748575+00:00"},{"alias_kind":"pith_short_8","alias_value":"HD7VX67Y","created_at":"2026-07-05T08:02:05.748575+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.06524","citing_title":"Multi-View Factorizing and Disentangling: A Novel Framework for Incomplete Multi-View Multi-Label Classification","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HD7VX67YIDGEXOGONWIMKKB745","json":"https://pith.science/pith/HD7VX67YIDGEXOGONWIMKKB745.json","graph_json":"https://pith.science/api/pith-number/HD7VX67YIDGEXOGONWIMKKB745/graph.json","events_json":"https://pith.science/api/pith-number/HD7VX67YIDGEXOGONWIMKKB745/events.json","paper":"https://pith.science/paper/HD7VX67Y"},"agent_actions":{"view_html":"https://pith.science/pith/HD7VX67YIDGEXOGONWIMKKB745","download_json":"https://pith.science/pith/HD7VX67YIDGEXOGONWIMKKB745.json","view_paper":"https://pith.science/paper/HD7VX67Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.10897&json=true","fetch_graph":"https://pith.science/api/pith-number/HD7VX67YIDGEXOGONWIMKKB745/graph.json","fetch_events":"https://pith.science/api/pith-number/HD7VX67YIDGEXOGONWIMKKB745/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HD7VX67YIDGEXOGONWIMKKB745/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HD7VX67YIDGEXOGONWIMKKB745/action/storage_attestation","attest_author":"https://pith.science/pith/HD7VX67YIDGEXOGONWIMKKB745/action/author_attestation","sign_citation":"https://pith.science/pith/HD7VX67YIDGEXOGONWIMKKB745/action/citation_signature","submit_replication":"https://pith.science/pith/HD7VX67YIDGEXOGONWIMKKB745/action/replication_record"}},"created_at":"2026-07-05T08:02:05.748575+00:00","updated_at":"2026-07-05T08:02:05.748575+00:00"}