{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:KS2WZOUU722FYBWENKZYH3ZPMD","short_pith_number":"pith:KS2WZOUU","schema_version":"1.0","canonical_sha256":"54b56cba94feb45c06c46ab383ef2f60f1c836c4c809b557dd7a6fedce766f0c","source":{"kind":"arxiv","id":"1511.09337","version":3},"attestation_state":"computed","paper":{"title":"Cost-aware Pre-training for Multiclass Cost-sensitive Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Hsuan-Tien Lin, Shao-Wen Yang, Yu-An Chung","submitted_at":"2015-11-30T14:54:28Z","abstract_excerpt":"Deep learning has been one of the most prominent machine learning techniques nowadays, being the state-of-the-art on a broad range of applications where automatic feature extraction is needed. Many such applications also demand varying costs for different types of mis-classification errors, but it is not clear whether or how such cost information can be incorporated into deep learning to improve performance. In this work, we propose a novel cost-aware algorithm that takes into account the cost information into not only the training stage but also the pre-training stage of deep learning. The ap"},"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":"1511.09337","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-30T14:54:28Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"33ad242fd8555f86115890e7330e8e6d265937a6e9ed8353909a3be2f4d42b54","abstract_canon_sha256":"a5095012ce4bd1c65494c94bd33e3f28f490f4f4222905ec482deacdfe3447c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:14:02.030548Z","signature_b64":"keVdCIjfG39e7D/bJdSzQVvV5ZEdDaHYWkslTOUuKDBlymbyku1tfgKDUR2TnvaHZfs90KUzQR8f79bgQ3nbDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54b56cba94feb45c06c46ab383ef2f60f1c836c4c809b557dd7a6fedce766f0c","last_reissued_at":"2026-05-18T01:14:02.029936Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:14:02.029936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cost-aware Pre-training for Multiclass Cost-sensitive Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Hsuan-Tien Lin, Shao-Wen Yang, Yu-An Chung","submitted_at":"2015-11-30T14:54:28Z","abstract_excerpt":"Deep learning has been one of the most prominent machine learning techniques nowadays, being the state-of-the-art on a broad range of applications where automatic feature extraction is needed. Many such applications also demand varying costs for different types of mis-classification errors, but it is not clear whether or how such cost information can be incorporated into deep learning to improve performance. In this work, we propose a novel cost-aware algorithm that takes into account the cost information into not only the training stage but also the pre-training stage of deep learning. The ap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.09337","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":"1511.09337","created_at":"2026-05-18T01:14:02.030024+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.09337v3","created_at":"2026-05-18T01:14:02.030024+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.09337","created_at":"2026-05-18T01:14:02.030024+00:00"},{"alias_kind":"pith_short_12","alias_value":"KS2WZOUU722F","created_at":"2026-05-18T12:29:29.992203+00:00"},{"alias_kind":"pith_short_16","alias_value":"KS2WZOUU722FYBWE","created_at":"2026-05-18T12:29:29.992203+00:00"},{"alias_kind":"pith_short_8","alias_value":"KS2WZOUU","created_at":"2026-05-18T12:29:29.992203+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/KS2WZOUU722FYBWENKZYH3ZPMD","json":"https://pith.science/pith/KS2WZOUU722FYBWENKZYH3ZPMD.json","graph_json":"https://pith.science/api/pith-number/KS2WZOUU722FYBWENKZYH3ZPMD/graph.json","events_json":"https://pith.science/api/pith-number/KS2WZOUU722FYBWENKZYH3ZPMD/events.json","paper":"https://pith.science/paper/KS2WZOUU"},"agent_actions":{"view_html":"https://pith.science/pith/KS2WZOUU722FYBWENKZYH3ZPMD","download_json":"https://pith.science/pith/KS2WZOUU722FYBWENKZYH3ZPMD.json","view_paper":"https://pith.science/paper/KS2WZOUU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.09337&json=true","fetch_graph":"https://pith.science/api/pith-number/KS2WZOUU722FYBWENKZYH3ZPMD/graph.json","fetch_events":"https://pith.science/api/pith-number/KS2WZOUU722FYBWENKZYH3ZPMD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KS2WZOUU722FYBWENKZYH3ZPMD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KS2WZOUU722FYBWENKZYH3ZPMD/action/storage_attestation","attest_author":"https://pith.science/pith/KS2WZOUU722FYBWENKZYH3ZPMD/action/author_attestation","sign_citation":"https://pith.science/pith/KS2WZOUU722FYBWENKZYH3ZPMD/action/citation_signature","submit_replication":"https://pith.science/pith/KS2WZOUU722FYBWENKZYH3ZPMD/action/replication_record"}},"created_at":"2026-05-18T01:14:02.030024+00:00","updated_at":"2026-05-18T01:14:02.030024+00:00"}