{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PVO7EVDWUV7KCJH3ZNVZPYHTRP","short_pith_number":"pith:PVO7EVDW","schema_version":"1.0","canonical_sha256":"7d5df25476a57ea124fbcb6b97e0f38bde1880b0569731c38accee129ec3073f","source":{"kind":"arxiv","id":"2508.20381","version":1},"attestation_state":"computed","paper":{"title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anh Nguyen, Luong Tran, Sang Dinh, Thieu Vo, Van Nguyen","submitted_at":"2025-08-28T03:07:57Z","abstract_excerpt":"Multi-label learning is a challenging computer vision task that requires assigning multiple categories to each image. However, fully annotating large-scale datasets is often impractical due to high costs and effort, motivating the study of learning from partially annotated data. In the extreme case of Single Positive Multi-Label Learning (SPML), each image is provided with only one positive label, while all other labels remain unannotated. Traditional SPML methods that treat missing labels as unknown or negative tend to yield inaccuracies and false negatives, and integrating various pseudo-lab"},"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":"2508.20381","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-28T03:07:57Z","cross_cats_sorted":[],"title_canon_sha256":"7ffaee739be002d9ce8ba0761987d988a0be6800efa0ab08b268ea1f4a098413","abstract_canon_sha256":"6858a906dfcca4e04a02276e442b6dda1fb97156bd1ec6f1d988272d77231ea2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:35.770205Z","signature_b64":"TyaWz0h7R/GhdNYG85Ryrq1T1Tlb0xE+EmpzeiJoQ/BmYo5yMVImu0gnZhhE3sfsN3Iq3jmwkfPsbA6L5n+ECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d5df25476a57ea124fbcb6b97e0f38bde1880b0569731c38accee129ec3073f","last_reissued_at":"2026-07-05T12:00:35.769674Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:35.769674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anh Nguyen, Luong Tran, Sang Dinh, Thieu Vo, Van Nguyen","submitted_at":"2025-08-28T03:07:57Z","abstract_excerpt":"Multi-label learning is a challenging computer vision task that requires assigning multiple categories to each image. However, fully annotating large-scale datasets is often impractical due to high costs and effort, motivating the study of learning from partially annotated data. In the extreme case of Single Positive Multi-Label Learning (SPML), each image is provided with only one positive label, while all other labels remain unannotated. Traditional SPML methods that treat missing labels as unknown or negative tend to yield inaccuracies and false negatives, and integrating various pseudo-lab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.20381","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/2508.20381/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":"2508.20381","created_at":"2026-07-05T12:00:35.769741+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.20381v1","created_at":"2026-07-05T12:00:35.769741+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20381","created_at":"2026-07-05T12:00:35.769741+00:00"},{"alias_kind":"pith_short_12","alias_value":"PVO7EVDWUV7K","created_at":"2026-07-05T12:00:35.769741+00:00"},{"alias_kind":"pith_short_16","alias_value":"PVO7EVDWUV7KCJH3","created_at":"2026-07-05T12:00:35.769741+00:00"},{"alias_kind":"pith_short_8","alias_value":"PVO7EVDW","created_at":"2026-07-05T12:00:35.769741+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/PVO7EVDWUV7KCJH3ZNVZPYHTRP","json":"https://pith.science/pith/PVO7EVDWUV7KCJH3ZNVZPYHTRP.json","graph_json":"https://pith.science/api/pith-number/PVO7EVDWUV7KCJH3ZNVZPYHTRP/graph.json","events_json":"https://pith.science/api/pith-number/PVO7EVDWUV7KCJH3ZNVZPYHTRP/events.json","paper":"https://pith.science/paper/PVO7EVDW"},"agent_actions":{"view_html":"https://pith.science/pith/PVO7EVDWUV7KCJH3ZNVZPYHTRP","download_json":"https://pith.science/pith/PVO7EVDWUV7KCJH3ZNVZPYHTRP.json","view_paper":"https://pith.science/paper/PVO7EVDW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.20381&json=true","fetch_graph":"https://pith.science/api/pith-number/PVO7EVDWUV7KCJH3ZNVZPYHTRP/graph.json","fetch_events":"https://pith.science/api/pith-number/PVO7EVDWUV7KCJH3ZNVZPYHTRP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PVO7EVDWUV7KCJH3ZNVZPYHTRP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PVO7EVDWUV7KCJH3ZNVZPYHTRP/action/storage_attestation","attest_author":"https://pith.science/pith/PVO7EVDWUV7KCJH3ZNVZPYHTRP/action/author_attestation","sign_citation":"https://pith.science/pith/PVO7EVDWUV7KCJH3ZNVZPYHTRP/action/citation_signature","submit_replication":"https://pith.science/pith/PVO7EVDWUV7KCJH3ZNVZPYHTRP/action/replication_record"}},"created_at":"2026-07-05T12:00:35.769741+00:00","updated_at":"2026-07-05T12:00:35.769741+00:00"}