{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RQJCU5VIS4W5XZXXPPCCBDSOQ3","short_pith_number":"pith:RQJCU5VI","schema_version":"1.0","canonical_sha256":"8c122a76a8972ddbe6f77bc4208e4e86c21a8615500f1246c26a366ee8b0fcf2","source":{"kind":"arxiv","id":"2305.08344","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Label Sharing Efficiency in Complementary-Label Learning with Label Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gang Niu, Hsuan-Tien Lin, Masashi Sugiyama, Wei-I Lin","submitted_at":"2023-05-15T04:43:14Z","abstract_excerpt":"Complementary-label Learning (CLL) is a form of weakly supervised learning that trains an ordinary classifier using only complementary labels, which are the classes that certain instances do not belong to. While existing CLL studies typically use novel loss functions or training techniques to solve this problem, few studies focus on how complementary labels collectively provide information to train the ordinary classifier. In this paper, we fill the gap by analyzing the implicit sharing of complementary labels on nearby instances during training. Our analysis reveals that the efficiency of imp"},"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":"2305.08344","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-15T04:43:14Z","cross_cats_sorted":[],"title_canon_sha256":"638dcd65b8cc6abcf4329bd77e474056e4812728b4286aa92cf02728b421cf30","abstract_canon_sha256":"09c8b7df422cf552832e7edcb1ead7e4764870ae246e270317e9276f0ab6d2e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:10:00.389787Z","signature_b64":"/PlrXtTzoP9upRjtyTD22Pp7J9pKK+TboWteBHfRtr7japVfqFd+EopF/UK5U1BfiOdHBpFLFwJKyYXcDmjGDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c122a76a8972ddbe6f77bc4208e4e86c21a8615500f1246c26a366ee8b0fcf2","last_reissued_at":"2026-07-05T06:10:00.389388Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:10:00.389388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Label Sharing Efficiency in Complementary-Label Learning with Label Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gang Niu, Hsuan-Tien Lin, Masashi Sugiyama, Wei-I Lin","submitted_at":"2023-05-15T04:43:14Z","abstract_excerpt":"Complementary-label Learning (CLL) is a form of weakly supervised learning that trains an ordinary classifier using only complementary labels, which are the classes that certain instances do not belong to. While existing CLL studies typically use novel loss functions or training techniques to solve this problem, few studies focus on how complementary labels collectively provide information to train the ordinary classifier. In this paper, we fill the gap by analyzing the implicit sharing of complementary labels on nearby instances during training. Our analysis reveals that the efficiency of imp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.08344","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/2305.08344/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":"2305.08344","created_at":"2026-07-05T06:10:00.389450+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.08344v1","created_at":"2026-07-05T06:10:00.389450+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.08344","created_at":"2026-07-05T06:10:00.389450+00:00"},{"alias_kind":"pith_short_12","alias_value":"RQJCU5VIS4W5","created_at":"2026-07-05T06:10:00.389450+00:00"},{"alias_kind":"pith_short_16","alias_value":"RQJCU5VIS4W5XZXX","created_at":"2026-07-05T06:10:00.389450+00:00"},{"alias_kind":"pith_short_8","alias_value":"RQJCU5VI","created_at":"2026-07-05T06:10:00.389450+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/RQJCU5VIS4W5XZXXPPCCBDSOQ3","json":"https://pith.science/pith/RQJCU5VIS4W5XZXXPPCCBDSOQ3.json","graph_json":"https://pith.science/api/pith-number/RQJCU5VIS4W5XZXXPPCCBDSOQ3/graph.json","events_json":"https://pith.science/api/pith-number/RQJCU5VIS4W5XZXXPPCCBDSOQ3/events.json","paper":"https://pith.science/paper/RQJCU5VI"},"agent_actions":{"view_html":"https://pith.science/pith/RQJCU5VIS4W5XZXXPPCCBDSOQ3","download_json":"https://pith.science/pith/RQJCU5VIS4W5XZXXPPCCBDSOQ3.json","view_paper":"https://pith.science/paper/RQJCU5VI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.08344&json=true","fetch_graph":"https://pith.science/api/pith-number/RQJCU5VIS4W5XZXXPPCCBDSOQ3/graph.json","fetch_events":"https://pith.science/api/pith-number/RQJCU5VIS4W5XZXXPPCCBDSOQ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RQJCU5VIS4W5XZXXPPCCBDSOQ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RQJCU5VIS4W5XZXXPPCCBDSOQ3/action/storage_attestation","attest_author":"https://pith.science/pith/RQJCU5VIS4W5XZXXPPCCBDSOQ3/action/author_attestation","sign_citation":"https://pith.science/pith/RQJCU5VIS4W5XZXXPPCCBDSOQ3/action/citation_signature","submit_replication":"https://pith.science/pith/RQJCU5VIS4W5XZXXPPCCBDSOQ3/action/replication_record"}},"created_at":"2026-07-05T06:10:00.389450+00:00","updated_at":"2026-07-05T06:10:00.389450+00:00"}