{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:XGTOLHOB6TZ7DHHO6KEW6ICY4J","short_pith_number":"pith:XGTOLHOB","schema_version":"1.0","canonical_sha256":"b9a6e59dc1f4f3f19ceef2896f2058e264b5ce9f3a5a064f84529e750f9729b5","source":{"kind":"arxiv","id":"2007.01458","version":3},"attestation_state":"computed","paper":{"title":"Confidence-Aware Learning for Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jihyo Kim, Jooyoung Moon, Sangheum Hwang, Younghak Shin","submitted_at":"2020-07-03T02:00:35Z","abstract_excerpt":"Despite the power of deep neural networks for a wide range of tasks, an overconfident prediction issue has limited their practical use in many safety-critical applications. Many recent works have been proposed to mitigate this issue, but most of them require either additional computational costs in training and/or inference phases or customized architectures to output confidence estimates separately. In this paper, we propose a method of training deep neural networks with a novel loss function, named Correctness Ranking Loss, which regularizes class probabilities explicitly to be better confid"},"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":"2007.01458","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-03T02:00:35Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9982344e9336a4e0520195268f7ea322082efa9598163d97c7bfafe7798fb797","abstract_canon_sha256":"44bffd721a109b055510bea293986801feec5af9dbcf168628e94046bf64e0c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:26:52.818895Z","signature_b64":"9wNp7012vtfM7b6sY/925KAdRaT1pO8RcTOa/Rj/JF1XiJ95vxAzPCn+57iwcaEWPqsbjtIO4Tiz9+1EvFxuBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9a6e59dc1f4f3f19ceef2896f2058e264b5ce9f3a5a064f84529e750f9729b5","last_reissued_at":"2026-07-05T01:26:52.818442Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:26:52.818442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Confidence-Aware Learning for Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jihyo Kim, Jooyoung Moon, Sangheum Hwang, Younghak Shin","submitted_at":"2020-07-03T02:00:35Z","abstract_excerpt":"Despite the power of deep neural networks for a wide range of tasks, an overconfident prediction issue has limited their practical use in many safety-critical applications. Many recent works have been proposed to mitigate this issue, but most of them require either additional computational costs in training and/or inference phases or customized architectures to output confidence estimates separately. In this paper, we propose a method of training deep neural networks with a novel loss function, named Correctness Ranking Loss, which regularizes class probabilities explicitly to be better confid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.01458","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2007.01458/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":"2007.01458","created_at":"2026-07-05T01:26:52.818501+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.01458v3","created_at":"2026-07-05T01:26:52.818501+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.01458","created_at":"2026-07-05T01:26:52.818501+00:00"},{"alias_kind":"pith_short_12","alias_value":"XGTOLHOB6TZ7","created_at":"2026-07-05T01:26:52.818501+00:00"},{"alias_kind":"pith_short_16","alias_value":"XGTOLHOB6TZ7DHHO","created_at":"2026-07-05T01:26:52.818501+00:00"},{"alias_kind":"pith_short_8","alias_value":"XGTOLHOB","created_at":"2026-07-05T01:26:52.818501+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.05275","citing_title":"Interpretable Failure Detection with Human-Level Concepts","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XGTOLHOB6TZ7DHHO6KEW6ICY4J","json":"https://pith.science/pith/XGTOLHOB6TZ7DHHO6KEW6ICY4J.json","graph_json":"https://pith.science/api/pith-number/XGTOLHOB6TZ7DHHO6KEW6ICY4J/graph.json","events_json":"https://pith.science/api/pith-number/XGTOLHOB6TZ7DHHO6KEW6ICY4J/events.json","paper":"https://pith.science/paper/XGTOLHOB"},"agent_actions":{"view_html":"https://pith.science/pith/XGTOLHOB6TZ7DHHO6KEW6ICY4J","download_json":"https://pith.science/pith/XGTOLHOB6TZ7DHHO6KEW6ICY4J.json","view_paper":"https://pith.science/paper/XGTOLHOB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.01458&json=true","fetch_graph":"https://pith.science/api/pith-number/XGTOLHOB6TZ7DHHO6KEW6ICY4J/graph.json","fetch_events":"https://pith.science/api/pith-number/XGTOLHOB6TZ7DHHO6KEW6ICY4J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XGTOLHOB6TZ7DHHO6KEW6ICY4J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XGTOLHOB6TZ7DHHO6KEW6ICY4J/action/storage_attestation","attest_author":"https://pith.science/pith/XGTOLHOB6TZ7DHHO6KEW6ICY4J/action/author_attestation","sign_citation":"https://pith.science/pith/XGTOLHOB6TZ7DHHO6KEW6ICY4J/action/citation_signature","submit_replication":"https://pith.science/pith/XGTOLHOB6TZ7DHHO6KEW6ICY4J/action/replication_record"}},"created_at":"2026-07-05T01:26:52.818501+00:00","updated_at":"2026-07-05T01:26:52.818501+00:00"}