{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:CCL2OG5A5MRGQ6NV3X652BNFMH","short_pith_number":"pith:CCL2OG5A","schema_version":"1.0","canonical_sha256":"1097a71ba0eb226879b5ddfddd05a561fc712b327850a54b0d7334248a168620","source":{"kind":"arxiv","id":"1612.03663","version":1},"attestation_state":"computed","paper":{"title":"Analysis and Optimization of Loss Functions for Multiclass, Top-k, and Multilabel Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Bernt Schiele, Maksim Lapin, Matthias Hein","submitted_at":"2016-12-12T13:20:09Z","abstract_excerpt":"Top-k error is currently a popular performance measure on large scale image classification benchmarks such as ImageNet and Places. Despite its wide acceptance, our understanding of this metric is limited as most of the previous research is focused on its special case, the top-1 error. In this work, we explore two directions that shed more light on the top-k error. First, we provide an in-depth analysis of established and recently proposed single-label multiclass methods along with a detailed account of efficient optimization algorithms for them. Our results indicate that the softmax loss and t"},"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":"1612.03663","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-12T13:20:09Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"7ebcc9c3c8bf3f8daa0ba031bf3c29996e0df01d37b28d8a383add2b6d199b08","abstract_canon_sha256":"212c136e81f9787af08c8fd5a34a058b25f9e2a4ba404bacd01190b00e5dbde7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:54:52.345755Z","signature_b64":"Q4n8Ihh2Fkk+Rh+0lkAVIzuwoOupfpreFoGrHqAkc/O6eLWR98KNrEWBW2ki0ua0YfOAKsAqA8xhIl052Gf3BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1097a71ba0eb226879b5ddfddd05a561fc712b327850a54b0d7334248a168620","last_reissued_at":"2026-05-18T00:54:52.345219Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:54:52.345219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Analysis and Optimization of Loss Functions for Multiclass, Top-k, and Multilabel Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Bernt Schiele, Maksim Lapin, Matthias Hein","submitted_at":"2016-12-12T13:20:09Z","abstract_excerpt":"Top-k error is currently a popular performance measure on large scale image classification benchmarks such as ImageNet and Places. Despite its wide acceptance, our understanding of this metric is limited as most of the previous research is focused on its special case, the top-1 error. In this work, we explore two directions that shed more light on the top-k error. First, we provide an in-depth analysis of established and recently proposed single-label multiclass methods along with a detailed account of efficient optimization algorithms for them. Our results indicate that the softmax loss and t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.03663","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":""},"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":"1612.03663","created_at":"2026-05-18T00:54:52.345291+00:00"},{"alias_kind":"arxiv_version","alias_value":"1612.03663v1","created_at":"2026-05-18T00:54:52.345291+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.03663","created_at":"2026-05-18T00:54:52.345291+00:00"},{"alias_kind":"pith_short_12","alias_value":"CCL2OG5A5MRG","created_at":"2026-05-18T12:30:09.641336+00:00"},{"alias_kind":"pith_short_16","alias_value":"CCL2OG5A5MRGQ6NV","created_at":"2026-05-18T12:30:09.641336+00:00"},{"alias_kind":"pith_short_8","alias_value":"CCL2OG5A","created_at":"2026-05-18T12:30:09.641336+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/CCL2OG5A5MRGQ6NV3X652BNFMH","json":"https://pith.science/pith/CCL2OG5A5MRGQ6NV3X652BNFMH.json","graph_json":"https://pith.science/api/pith-number/CCL2OG5A5MRGQ6NV3X652BNFMH/graph.json","events_json":"https://pith.science/api/pith-number/CCL2OG5A5MRGQ6NV3X652BNFMH/events.json","paper":"https://pith.science/paper/CCL2OG5A"},"agent_actions":{"view_html":"https://pith.science/pith/CCL2OG5A5MRGQ6NV3X652BNFMH","download_json":"https://pith.science/pith/CCL2OG5A5MRGQ6NV3X652BNFMH.json","view_paper":"https://pith.science/paper/CCL2OG5A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1612.03663&json=true","fetch_graph":"https://pith.science/api/pith-number/CCL2OG5A5MRGQ6NV3X652BNFMH/graph.json","fetch_events":"https://pith.science/api/pith-number/CCL2OG5A5MRGQ6NV3X652BNFMH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CCL2OG5A5MRGQ6NV3X652BNFMH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CCL2OG5A5MRGQ6NV3X652BNFMH/action/storage_attestation","attest_author":"https://pith.science/pith/CCL2OG5A5MRGQ6NV3X652BNFMH/action/author_attestation","sign_citation":"https://pith.science/pith/CCL2OG5A5MRGQ6NV3X652BNFMH/action/citation_signature","submit_replication":"https://pith.science/pith/CCL2OG5A5MRGQ6NV3X652BNFMH/action/replication_record"}},"created_at":"2026-05-18T00:54:52.345291+00:00","updated_at":"2026-05-18T00:54:52.345291+00:00"}