{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SIJ7NMCGJV5HC4CMTCABYSNXKG","short_pith_number":"pith:SIJ7NMCG","schema_version":"1.0","canonical_sha256":"9213f6b0464d7a71704c98801c49b751949f05a20f0eb4ef21e1527a9d9fba0f","source":{"kind":"arxiv","id":"2505.04046","version":2},"attestation_state":"computed","paper":{"title":"Reliable Disentanglement Multi-view Learning Against View Adversarial Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.CV"],"primary_cat":"cs.LG","authors_text":"Dezhong Peng, Guiduo Duan, Qizhi Li, Siyuan Duan, Xuyang Wang, Yuan Sun","submitted_at":"2025-05-07T01:12:00Z","abstract_excerpt":"Trustworthy multi-view learning has attracted extensive attention because evidence learning can provide reliable uncertainty estimation to enhance the credibility of multi-view predictions. Existing trusted multi-view learning methods implicitly assume that multi-view data is secure. However, in safety-sensitive applications such as autonomous driving and security monitoring, multi-view data often faces threats from adversarial perturbations, thereby deceiving or disrupting multi-view models. This inevitably leads to the adversarial unreliability problem (AUP) in trusted multi-view learning. T"},"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":"2505.04046","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-07T01:12:00Z","cross_cats_sorted":["cs.CR","cs.CV"],"title_canon_sha256":"a133f51c72cc54e5a7a9569ddc205610dd7450216ced84030c6e742b58669325","abstract_canon_sha256":"3311a0133e5159c5169cfdf354015a3ded9006a4f5a2b9cba37d2f64a25cd4a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:31.686674Z","signature_b64":"ajArxEs4gEuFa/PLvvv/aDg/yu2K1Ii3SszVBlHNC78DuCV1IfkZ1uMy72atkkqapFnrsPe+Yftj5vptymXuDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9213f6b0464d7a71704c98801c49b751949f05a20f0eb4ef21e1527a9d9fba0f","last_reissued_at":"2026-07-05T11:06:31.686188Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:31.686188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reliable Disentanglement Multi-view Learning Against View Adversarial Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.CV"],"primary_cat":"cs.LG","authors_text":"Dezhong Peng, Guiduo Duan, Qizhi Li, Siyuan Duan, Xuyang Wang, Yuan Sun","submitted_at":"2025-05-07T01:12:00Z","abstract_excerpt":"Trustworthy multi-view learning has attracted extensive attention because evidence learning can provide reliable uncertainty estimation to enhance the credibility of multi-view predictions. Existing trusted multi-view learning methods implicitly assume that multi-view data is secure. However, in safety-sensitive applications such as autonomous driving and security monitoring, multi-view data often faces threats from adversarial perturbations, thereby deceiving or disrupting multi-view models. This inevitably leads to the adversarial unreliability problem (AUP) in trusted multi-view learning. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04046","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/2505.04046/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":"2505.04046","created_at":"2026-07-05T11:06:31.686238+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.04046v2","created_at":"2026-07-05T11:06:31.686238+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04046","created_at":"2026-07-05T11:06:31.686238+00:00"},{"alias_kind":"pith_short_12","alias_value":"SIJ7NMCGJV5H","created_at":"2026-07-05T11:06:31.686238+00:00"},{"alias_kind":"pith_short_16","alias_value":"SIJ7NMCGJV5HC4CM","created_at":"2026-07-05T11:06:31.686238+00:00"},{"alias_kind":"pith_short_8","alias_value":"SIJ7NMCG","created_at":"2026-07-05T11:06:31.686238+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24475","citing_title":"Robust Fuzzy Multi-view Learning under View Conflict","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SIJ7NMCGJV5HC4CMTCABYSNXKG","json":"https://pith.science/pith/SIJ7NMCGJV5HC4CMTCABYSNXKG.json","graph_json":"https://pith.science/api/pith-number/SIJ7NMCGJV5HC4CMTCABYSNXKG/graph.json","events_json":"https://pith.science/api/pith-number/SIJ7NMCGJV5HC4CMTCABYSNXKG/events.json","paper":"https://pith.science/paper/SIJ7NMCG"},"agent_actions":{"view_html":"https://pith.science/pith/SIJ7NMCGJV5HC4CMTCABYSNXKG","download_json":"https://pith.science/pith/SIJ7NMCGJV5HC4CMTCABYSNXKG.json","view_paper":"https://pith.science/paper/SIJ7NMCG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.04046&json=true","fetch_graph":"https://pith.science/api/pith-number/SIJ7NMCGJV5HC4CMTCABYSNXKG/graph.json","fetch_events":"https://pith.science/api/pith-number/SIJ7NMCGJV5HC4CMTCABYSNXKG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SIJ7NMCGJV5HC4CMTCABYSNXKG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SIJ7NMCGJV5HC4CMTCABYSNXKG/action/storage_attestation","attest_author":"https://pith.science/pith/SIJ7NMCGJV5HC4CMTCABYSNXKG/action/author_attestation","sign_citation":"https://pith.science/pith/SIJ7NMCGJV5HC4CMTCABYSNXKG/action/citation_signature","submit_replication":"https://pith.science/pith/SIJ7NMCGJV5HC4CMTCABYSNXKG/action/replication_record"}},"created_at":"2026-07-05T11:06:31.686238+00:00","updated_at":"2026-07-05T11:06:31.686238+00:00"}