{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QTUIZQCVRS6VHC4HU3OAH2IOG7","short_pith_number":"pith:QTUIZQCV","schema_version":"1.0","canonical_sha256":"84e88cc0558cbd538b87a6dc03e90e37c7e6f91831dbabd9b2bf50f3ae4616d9","source":{"kind":"arxiv","id":"2212.01461","version":1},"attestation_state":"computed","paper":{"title":"Learning Disentangled Label Representations for Multi-label Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fei He, Jian Jia, Kaiqi Huang, Naiyu Gao, Xiaotang Chen","submitted_at":"2022-12-02T21:49:34Z","abstract_excerpt":"Although various methods have been proposed for multi-label classification, most approaches still follow the feature learning mechanism of the single-label (multi-class) classification, namely, learning a shared image feature to classify multiple labels. However, we find this One-shared-Feature-for-Multiple-Labels (OFML) mechanism is not conducive to learning discriminative label features and makes the model non-robustness. For the first time, we mathematically prove that the inferiority of the OFML mechanism is that the optimal learned image feature cannot maintain high similarities with mult"},"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":"2212.01461","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-02T21:49:34Z","cross_cats_sorted":[],"title_canon_sha256":"b69e8e0a152cae0196ddaa528aaf5bbad364477dd8f9359e1a798a945ecc9ddc","abstract_canon_sha256":"a3cc5ffd5bd94cf20e07543f81a170ad4bc7acedb037dabf9fd09699c0fa91df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:21:55.297720Z","signature_b64":"zG6rmMCkXrwTCyWqcEtYXj0l9d1jYg0BDcBo0ifYhf6VaCmxgKFhP6HM5dPrViUV04/k5uUeYeBL8t3CTEN6Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84e88cc0558cbd538b87a6dc03e90e37c7e6f91831dbabd9b2bf50f3ae4616d9","last_reissued_at":"2026-07-05T05:21:55.297356Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:21:55.297356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Disentangled Label Representations for Multi-label Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fei He, Jian Jia, Kaiqi Huang, Naiyu Gao, Xiaotang Chen","submitted_at":"2022-12-02T21:49:34Z","abstract_excerpt":"Although various methods have been proposed for multi-label classification, most approaches still follow the feature learning mechanism of the single-label (multi-class) classification, namely, learning a shared image feature to classify multiple labels. However, we find this One-shared-Feature-for-Multiple-Labels (OFML) mechanism is not conducive to learning discriminative label features and makes the model non-robustness. For the first time, we mathematically prove that the inferiority of the OFML mechanism is that the optimal learned image feature cannot maintain high similarities with mult"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.01461","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/2212.01461/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":"2212.01461","created_at":"2026-07-05T05:21:55.297413+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.01461v1","created_at":"2026-07-05T05:21:55.297413+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.01461","created_at":"2026-07-05T05:21:55.297413+00:00"},{"alias_kind":"pith_short_12","alias_value":"QTUIZQCVRS6V","created_at":"2026-07-05T05:21:55.297413+00:00"},{"alias_kind":"pith_short_16","alias_value":"QTUIZQCVRS6VHC4H","created_at":"2026-07-05T05:21:55.297413+00:00"},{"alias_kind":"pith_short_8","alias_value":"QTUIZQCV","created_at":"2026-07-05T05:21:55.297413+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/QTUIZQCVRS6VHC4HU3OAH2IOG7","json":"https://pith.science/pith/QTUIZQCVRS6VHC4HU3OAH2IOG7.json","graph_json":"https://pith.science/api/pith-number/QTUIZQCVRS6VHC4HU3OAH2IOG7/graph.json","events_json":"https://pith.science/api/pith-number/QTUIZQCVRS6VHC4HU3OAH2IOG7/events.json","paper":"https://pith.science/paper/QTUIZQCV"},"agent_actions":{"view_html":"https://pith.science/pith/QTUIZQCVRS6VHC4HU3OAH2IOG7","download_json":"https://pith.science/pith/QTUIZQCVRS6VHC4HU3OAH2IOG7.json","view_paper":"https://pith.science/paper/QTUIZQCV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.01461&json=true","fetch_graph":"https://pith.science/api/pith-number/QTUIZQCVRS6VHC4HU3OAH2IOG7/graph.json","fetch_events":"https://pith.science/api/pith-number/QTUIZQCVRS6VHC4HU3OAH2IOG7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QTUIZQCVRS6VHC4HU3OAH2IOG7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QTUIZQCVRS6VHC4HU3OAH2IOG7/action/storage_attestation","attest_author":"https://pith.science/pith/QTUIZQCVRS6VHC4HU3OAH2IOG7/action/author_attestation","sign_citation":"https://pith.science/pith/QTUIZQCVRS6VHC4HU3OAH2IOG7/action/citation_signature","submit_replication":"https://pith.science/pith/QTUIZQCVRS6VHC4HU3OAH2IOG7/action/replication_record"}},"created_at":"2026-07-05T05:21:55.297413+00:00","updated_at":"2026-07-05T05:21:55.297413+00:00"}