{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:NZKYGTVQZD3M42HC7COMD6MBHF","short_pith_number":"pith:NZKYGTVQ","schema_version":"1.0","canonical_sha256":"6e55834eb0c8f6ce68e2f89cc1f981394b19ad2f2ab762b34254eb0e6b2b4399","source":{"kind":"arxiv","id":"1512.00486","version":2},"attestation_state":"computed","paper":{"title":"Loss Functions for Top-k Error: Analysis and Insights","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Bernt Schiele, Maksim Lapin, Matthias Hein","submitted_at":"2015-12-01T21:22:35Z","abstract_excerpt":"In order to push the performance on realistic computer vision tasks, the number of classes in modern benchmark datasets has significantly increased in recent years. This increase in the number of classes comes along with increased ambiguity between the class labels, raising the question if top-1 error is the right performance measure. In this paper, we provide an extensive comparison and evaluation of established multiclass methods comparing their top-k performance both from a practical as well as from a theoretical perspective. Moreover, we introduce novel top-k loss functions as modification"},"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":"1512.00486","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-12-01T21:22:35Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"1f3409011aa145e1c56e12e3368695f4b82bdd1bb2bddb6a49ae41d23a6f150e","abstract_canon_sha256":"867b1356fa3c93db1e8a240472fb98e98bcf51f3382049ed11114a3e8e8eb64c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:11.457783Z","signature_b64":"VP81zzhgxZf5Fbm9SXALmOokEKY++PsgvbD5Sa8MVCXHOgRqUvWKIYYkSdA7hhLlayseTqCVuxfNo4lBr5cVDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e55834eb0c8f6ce68e2f89cc1f981394b19ad2f2ab762b34254eb0e6b2b4399","last_reissued_at":"2026-05-18T01:17:11.457112Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:11.457112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Loss Functions for Top-k Error: Analysis and Insights","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Bernt Schiele, Maksim Lapin, Matthias Hein","submitted_at":"2015-12-01T21:22:35Z","abstract_excerpt":"In order to push the performance on realistic computer vision tasks, the number of classes in modern benchmark datasets has significantly increased in recent years. This increase in the number of classes comes along with increased ambiguity between the class labels, raising the question if top-1 error is the right performance measure. In this paper, we provide an extensive comparison and evaluation of established multiclass methods comparing their top-k performance both from a practical as well as from a theoretical perspective. Moreover, we introduce novel top-k loss functions as modification"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.00486","kind":"arxiv","version":2},"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":"1512.00486","created_at":"2026-05-18T01:17:11.457218+00:00"},{"alias_kind":"arxiv_version","alias_value":"1512.00486v2","created_at":"2026-05-18T01:17:11.457218+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.00486","created_at":"2026-05-18T01:17:11.457218+00:00"},{"alias_kind":"pith_short_12","alias_value":"NZKYGTVQZD3M","created_at":"2026-05-18T12:29:34.919912+00:00"},{"alias_kind":"pith_short_16","alias_value":"NZKYGTVQZD3M42HC","created_at":"2026-05-18T12:29:34.919912+00:00"},{"alias_kind":"pith_short_8","alias_value":"NZKYGTVQ","created_at":"2026-05-18T12:29:34.919912+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/NZKYGTVQZD3M42HC7COMD6MBHF","json":"https://pith.science/pith/NZKYGTVQZD3M42HC7COMD6MBHF.json","graph_json":"https://pith.science/api/pith-number/NZKYGTVQZD3M42HC7COMD6MBHF/graph.json","events_json":"https://pith.science/api/pith-number/NZKYGTVQZD3M42HC7COMD6MBHF/events.json","paper":"https://pith.science/paper/NZKYGTVQ"},"agent_actions":{"view_html":"https://pith.science/pith/NZKYGTVQZD3M42HC7COMD6MBHF","download_json":"https://pith.science/pith/NZKYGTVQZD3M42HC7COMD6MBHF.json","view_paper":"https://pith.science/paper/NZKYGTVQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1512.00486&json=true","fetch_graph":"https://pith.science/api/pith-number/NZKYGTVQZD3M42HC7COMD6MBHF/graph.json","fetch_events":"https://pith.science/api/pith-number/NZKYGTVQZD3M42HC7COMD6MBHF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NZKYGTVQZD3M42HC7COMD6MBHF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NZKYGTVQZD3M42HC7COMD6MBHF/action/storage_attestation","attest_author":"https://pith.science/pith/NZKYGTVQZD3M42HC7COMD6MBHF/action/author_attestation","sign_citation":"https://pith.science/pith/NZKYGTVQZD3M42HC7COMD6MBHF/action/citation_signature","submit_replication":"https://pith.science/pith/NZKYGTVQZD3M42HC7COMD6MBHF/action/replication_record"}},"created_at":"2026-05-18T01:17:11.457218+00:00","updated_at":"2026-05-18T01:17:11.457218+00:00"}