{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:L7YLQZPGLF3DIDERVDI2TZF6DH","short_pith_number":"pith:L7YLQZPG","schema_version":"1.0","canonical_sha256":"5ff0b865e65976340c91a8d1a9e4be19e5f0d4ed1ae6b863595dcace4bf80a87","source":{"kind":"arxiv","id":"2305.05882","version":1},"attestation_state":"computed","paper":{"title":"Deep Partial Multi-Label Learning with Graph Disambiguation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gang Chen, Gengyu Lyu, Haobo Wang, Ke Chen, Shisong Yang, Songhe Feng, Tianlei Hu, Weiwei Liu","submitted_at":"2023-05-10T04:02:08Z","abstract_excerpt":"In partial multi-label learning (PML), each data example is equipped with a candidate label set, which consists of multiple ground-truth labels and other false-positive labels. Recently, graph-based methods, which demonstrate a good ability to estimate accurate confidence scores from candidate labels, have been prevalent to deal with PML problems. However, we observe that existing graph-based PML methods typically adopt linear multi-label classifiers and thus fail to achieve superior performance. In this work, we attempt to remove several obstacles for extending them to deep models and propose"},"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":"2305.05882","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-10T04:02:08Z","cross_cats_sorted":[],"title_canon_sha256":"cbec9211deffba30752ac553cdc6bb7c48d64738f1c3d168aaf8c4bf6b6c21d2","abstract_canon_sha256":"c73c1229fecd190db028db5945659de9d13eb14efe0340c368fba21513b58cab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:08:57.098605Z","signature_b64":"cOTHSYwyg8S80PN8vBkYWeWo0GR80SOwRxC9HFw7CldbqfGJvS6Bu2UNwQ5UCt9O2owM8AxtaPi2mQOtoDQ7Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ff0b865e65976340c91a8d1a9e4be19e5f0d4ed1ae6b863595dcace4bf80a87","last_reissued_at":"2026-07-05T06:08:57.098108Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:08:57.098108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Partial Multi-Label Learning with Graph Disambiguation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gang Chen, Gengyu Lyu, Haobo Wang, Ke Chen, Shisong Yang, Songhe Feng, Tianlei Hu, Weiwei Liu","submitted_at":"2023-05-10T04:02:08Z","abstract_excerpt":"In partial multi-label learning (PML), each data example is equipped with a candidate label set, which consists of multiple ground-truth labels and other false-positive labels. Recently, graph-based methods, which demonstrate a good ability to estimate accurate confidence scores from candidate labels, have been prevalent to deal with PML problems. However, we observe that existing graph-based PML methods typically adopt linear multi-label classifiers and thus fail to achieve superior performance. In this work, we attempt to remove several obstacles for extending them to deep models and propose"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.05882","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/2305.05882/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":"2305.05882","created_at":"2026-07-05T06:08:57.098181+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.05882v1","created_at":"2026-07-05T06:08:57.098181+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.05882","created_at":"2026-07-05T06:08:57.098181+00:00"},{"alias_kind":"pith_short_12","alias_value":"L7YLQZPGLF3D","created_at":"2026-07-05T06:08:57.098181+00:00"},{"alias_kind":"pith_short_16","alias_value":"L7YLQZPGLF3DIDER","created_at":"2026-07-05T06:08:57.098181+00:00"},{"alias_kind":"pith_short_8","alias_value":"L7YLQZPG","created_at":"2026-07-05T06:08:57.098181+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20938","citing_title":"Revisiting Sparsity Constraint Under High-Rank Property in Partial Multi-Label Learning","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L7YLQZPGLF3DIDERVDI2TZF6DH","json":"https://pith.science/pith/L7YLQZPGLF3DIDERVDI2TZF6DH.json","graph_json":"https://pith.science/api/pith-number/L7YLQZPGLF3DIDERVDI2TZF6DH/graph.json","events_json":"https://pith.science/api/pith-number/L7YLQZPGLF3DIDERVDI2TZF6DH/events.json","paper":"https://pith.science/paper/L7YLQZPG"},"agent_actions":{"view_html":"https://pith.science/pith/L7YLQZPGLF3DIDERVDI2TZF6DH","download_json":"https://pith.science/pith/L7YLQZPGLF3DIDERVDI2TZF6DH.json","view_paper":"https://pith.science/paper/L7YLQZPG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.05882&json=true","fetch_graph":"https://pith.science/api/pith-number/L7YLQZPGLF3DIDERVDI2TZF6DH/graph.json","fetch_events":"https://pith.science/api/pith-number/L7YLQZPGLF3DIDERVDI2TZF6DH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L7YLQZPGLF3DIDERVDI2TZF6DH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L7YLQZPGLF3DIDERVDI2TZF6DH/action/storage_attestation","attest_author":"https://pith.science/pith/L7YLQZPGLF3DIDERVDI2TZF6DH/action/author_attestation","sign_citation":"https://pith.science/pith/L7YLQZPGLF3DIDERVDI2TZF6DH/action/citation_signature","submit_replication":"https://pith.science/pith/L7YLQZPGLF3DIDERVDI2TZF6DH/action/replication_record"}},"created_at":"2026-07-05T06:08:57.098181+00:00","updated_at":"2026-07-05T06:08:57.098181+00:00"}