{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:V5PLZTXC4HFCMBVADWYEAEM6EG","short_pith_number":"pith:V5PLZTXC","schema_version":"1.0","canonical_sha256":"af5ebccee2e1ca2606a01db040119e219ee410081427298e179155a8c87aae59","source":{"kind":"arxiv","id":"2305.09897","version":1},"attestation_state":"computed","paper":{"title":"Complementary Classifier Induced Partial Label Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Chongjie Si, Min-Ling Zhang, Yuheng Jia","submitted_at":"2023-05-17T02:13:23Z","abstract_excerpt":"In partial label learning (PLL), each training sample is associated with a set of candidate labels, among which only one is valid. The core of PLL is to disambiguate the candidate labels to get the ground-truth one. In disambiguation, the existing works usually do not fully investigate the effectiveness of the non-candidate label set (a.k.a. complementary labels), which accurately indicates a set of labels that do not belong to a sample. In this paper, we use the non-candidate labels to induce a complementary classifier, which naturally forms an adversarial relationship against the traditional"},"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":"2305.09897","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-17T02:13:23Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"20b9900cb83735723138cb98304b33abbd9c883831dd077255ee55f36196de76","abstract_canon_sha256":"de272be4e44f306ec6ee0fa9d041423c87f8743b9d3c75d4bd3c9e503f21ab46"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:50.160756Z","signature_b64":"7pad8EFPDEHsHX3KFnsfRirxb1q2b8PwHO+bSQCGOTTALK18slzLtcT2tTvSMQUbFTJB974iF2TrVGX1N3SLBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af5ebccee2e1ca2606a01db040119e219ee410081427298e179155a8c87aae59","last_reissued_at":"2026-07-05T07:24:50.160258Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:50.160258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Complementary Classifier Induced Partial Label Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Chongjie Si, Min-Ling Zhang, Yuheng Jia","submitted_at":"2023-05-17T02:13:23Z","abstract_excerpt":"In partial label learning (PLL), each training sample is associated with a set of candidate labels, among which only one is valid. The core of PLL is to disambiguate the candidate labels to get the ground-truth one. In disambiguation, the existing works usually do not fully investigate the effectiveness of the non-candidate label set (a.k.a. complementary labels), which accurately indicates a set of labels that do not belong to a sample. In this paper, we use the non-candidate labels to induce a complementary classifier, which naturally forms an adversarial relationship against the traditional"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.09897","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/2305.09897/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":"2305.09897","created_at":"2026-07-05T07:24:50.160323+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.09897v1","created_at":"2026-07-05T07:24:50.160323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.09897","created_at":"2026-07-05T07:24:50.160323+00:00"},{"alias_kind":"pith_short_12","alias_value":"V5PLZTXC4HFC","created_at":"2026-07-05T07:24:50.160323+00:00"},{"alias_kind":"pith_short_16","alias_value":"V5PLZTXC4HFCMBVA","created_at":"2026-07-05T07:24:50.160323+00:00"},{"alias_kind":"pith_short_8","alias_value":"V5PLZTXC","created_at":"2026-07-05T07:24:50.160323+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.16159","citing_title":"Why Can Accurate Models Be Learned from Inaccurate Annotations?","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V5PLZTXC4HFCMBVADWYEAEM6EG","json":"https://pith.science/pith/V5PLZTXC4HFCMBVADWYEAEM6EG.json","graph_json":"https://pith.science/api/pith-number/V5PLZTXC4HFCMBVADWYEAEM6EG/graph.json","events_json":"https://pith.science/api/pith-number/V5PLZTXC4HFCMBVADWYEAEM6EG/events.json","paper":"https://pith.science/paper/V5PLZTXC"},"agent_actions":{"view_html":"https://pith.science/pith/V5PLZTXC4HFCMBVADWYEAEM6EG","download_json":"https://pith.science/pith/V5PLZTXC4HFCMBVADWYEAEM6EG.json","view_paper":"https://pith.science/paper/V5PLZTXC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.09897&json=true","fetch_graph":"https://pith.science/api/pith-number/V5PLZTXC4HFCMBVADWYEAEM6EG/graph.json","fetch_events":"https://pith.science/api/pith-number/V5PLZTXC4HFCMBVADWYEAEM6EG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V5PLZTXC4HFCMBVADWYEAEM6EG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V5PLZTXC4HFCMBVADWYEAEM6EG/action/storage_attestation","attest_author":"https://pith.science/pith/V5PLZTXC4HFCMBVADWYEAEM6EG/action/author_attestation","sign_citation":"https://pith.science/pith/V5PLZTXC4HFCMBVADWYEAEM6EG/action/citation_signature","submit_replication":"https://pith.science/pith/V5PLZTXC4HFCMBVADWYEAEM6EG/action/replication_record"}},"created_at":"2026-07-05T07:24:50.160323+00:00","updated_at":"2026-07-05T07:24:50.160323+00:00"}