{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:JIYW4GCOAQSGIFF6WZP3JPXGCZ","short_pith_number":"pith:JIYW4GCO","schema_version":"1.0","canonical_sha256":"4a316e184e04246414beb65fb4bee6164d55640eeb76ce24a5fc197899dcfda6","source":{"kind":"arxiv","id":"1704.03135","version":3},"attestation_state":"computed","paper":{"title":"Improving Pairwise Ranking for Multi-label Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiebo Luo, Yale Song, Yuncheng Li","submitted_at":"2017-04-11T04:04:54Z","abstract_excerpt":"Learning to rank has recently emerged as an attractive technique to train deep convolutional neural networks for various computer vision tasks. Pairwise ranking, in particular, has been successful in multi-label image classification, achieving state-of-the-art results on various benchmarks. However, most existing approaches use the hinge loss to train their models, which is non-smooth and thus is difficult to optimize especially with deep networks. Furthermore, they employ simple heuristics, such as top-k or thresholding, to determine which labels to include in the output from a ranked list of"},"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":"1704.03135","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-11T04:04:54Z","cross_cats_sorted":[],"title_canon_sha256":"24635f5e3f5e1778cbfe9b97f61ce9ab54ea331c12f51244e6413d07c04caf55","abstract_canon_sha256":"72198c325412a7e5b6fbf9e7c263d42706597a6f9e8be6b1ea3ac47ca637bea7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:15.493993Z","signature_b64":"o9Tx0dA37XZXKagIrv0VjurU4NKWwunQczQD/97jvMha8RRa5BXn28fcHQlg0IHplG/8WesO748mM85tdz30CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a316e184e04246414beb65fb4bee6164d55640eeb76ce24a5fc197899dcfda6","last_reissued_at":"2026-05-18T00:43:15.493521Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:15.493521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Pairwise Ranking for Multi-label Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiebo Luo, Yale Song, Yuncheng Li","submitted_at":"2017-04-11T04:04:54Z","abstract_excerpt":"Learning to rank has recently emerged as an attractive technique to train deep convolutional neural networks for various computer vision tasks. Pairwise ranking, in particular, has been successful in multi-label image classification, achieving state-of-the-art results on various benchmarks. However, most existing approaches use the hinge loss to train their models, which is non-smooth and thus is difficult to optimize especially with deep networks. Furthermore, they employ simple heuristics, such as top-k or thresholding, to determine which labels to include in the output from a ranked list of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.03135","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1704.03135","created_at":"2026-05-18T00:43:15.493593+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.03135v3","created_at":"2026-05-18T00:43:15.493593+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.03135","created_at":"2026-05-18T00:43:15.493593+00:00"},{"alias_kind":"pith_short_12","alias_value":"JIYW4GCOAQSG","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_16","alias_value":"JIYW4GCOAQSGIFF6","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_8","alias_value":"JIYW4GCO","created_at":"2026-05-18T12:31:24.725408+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/JIYW4GCOAQSGIFF6WZP3JPXGCZ","json":"https://pith.science/pith/JIYW4GCOAQSGIFF6WZP3JPXGCZ.json","graph_json":"https://pith.science/api/pith-number/JIYW4GCOAQSGIFF6WZP3JPXGCZ/graph.json","events_json":"https://pith.science/api/pith-number/JIYW4GCOAQSGIFF6WZP3JPXGCZ/events.json","paper":"https://pith.science/paper/JIYW4GCO"},"agent_actions":{"view_html":"https://pith.science/pith/JIYW4GCOAQSGIFF6WZP3JPXGCZ","download_json":"https://pith.science/pith/JIYW4GCOAQSGIFF6WZP3JPXGCZ.json","view_paper":"https://pith.science/paper/JIYW4GCO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.03135&json=true","fetch_graph":"https://pith.science/api/pith-number/JIYW4GCOAQSGIFF6WZP3JPXGCZ/graph.json","fetch_events":"https://pith.science/api/pith-number/JIYW4GCOAQSGIFF6WZP3JPXGCZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JIYW4GCOAQSGIFF6WZP3JPXGCZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JIYW4GCOAQSGIFF6WZP3JPXGCZ/action/storage_attestation","attest_author":"https://pith.science/pith/JIYW4GCOAQSGIFF6WZP3JPXGCZ/action/author_attestation","sign_citation":"https://pith.science/pith/JIYW4GCOAQSGIFF6WZP3JPXGCZ/action/citation_signature","submit_replication":"https://pith.science/pith/JIYW4GCOAQSGIFF6WZP3JPXGCZ/action/replication_record"}},"created_at":"2026-05-18T00:43:15.493593+00:00","updated_at":"2026-05-18T00:43:15.493593+00:00"}