{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:2YJD4IVXK7WFTB2INT4RXMN4YB","short_pith_number":"pith:2YJD4IVX","schema_version":"1.0","canonical_sha256":"d6123e22b757ec5987486cf91bb1bcc05253379b897e58a22fe6459558b0c71f","source":{"kind":"arxiv","id":"1802.04865","version":1},"attestation_state":"computed","paper":{"title":"Learning Confidence for Out-of-Distribution Detection in Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Graham W. Taylor, Terrance DeVries","submitted_at":"2018-02-13T21:31:36Z","abstract_excerpt":"Modern neural networks are very powerful predictive models, but they are often incapable of recognizing when their predictions may be wrong. Closely related to this is the task of out-of-distribution detection, where a network must determine whether or not an input is outside of the set on which it is expected to safely perform. To jointly address these issues, we propose a method of learning confidence estimates for neural networks that is simple to implement and produces intuitively interpretable outputs. We demonstrate that on the task of out-of-distribution detection, our technique surpass"},"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":"1802.04865","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-13T21:31:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"43db7dad01bda6e598952dc0d2495a426844e5fafc47a24361b4a5178f2d06f1","abstract_canon_sha256":"8c2357c373f0cfa977c52edd19b4c879e4eeefe7fd2fdd19bb2e9eb8acbf93ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:22.396602Z","signature_b64":"Jlf9GxOeeyki1LjQTf3bXKm5p0XbLvQA97gtP1uggCMrhcjafT8PalAYRkYieGkAjBBE2rkGjoQgDPdb81zKAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6123e22b757ec5987486cf91bb1bcc05253379b897e58a22fe6459558b0c71f","last_reissued_at":"2026-05-18T00:23:22.395900Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:22.395900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Confidence for Out-of-Distribution Detection in Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Graham W. Taylor, Terrance DeVries","submitted_at":"2018-02-13T21:31:36Z","abstract_excerpt":"Modern neural networks are very powerful predictive models, but they are often incapable of recognizing when their predictions may be wrong. Closely related to this is the task of out-of-distribution detection, where a network must determine whether or not an input is outside of the set on which it is expected to safely perform. To jointly address these issues, we propose a method of learning confidence estimates for neural networks that is simple to implement and produces intuitively interpretable outputs. We demonstrate that on the task of out-of-distribution detection, our technique surpass"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04865","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":"1802.04865","created_at":"2026-05-18T00:23:22.395995+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.04865v1","created_at":"2026-05-18T00:23:22.395995+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04865","created_at":"2026-05-18T00:23:22.395995+00:00"},{"alias_kind":"pith_short_12","alias_value":"2YJD4IVXK7WF","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"2YJD4IVXK7WFTB2I","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"2YJD4IVX","created_at":"2026-05-18T12:32:02.567920+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2504.14129","citing_title":"PVLM: Parsing-Aware Vision Language Model with Dynamic Contrastive Learning for Zero-Shot Deepfake Attribution","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2511.11934","citing_title":"A Systematic Analysis of Out-of-Distribution Detection Under Representation and Training Paradigm Shifts","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2511.19996","citing_title":"RankOOD -- Class Ranking-based Out-of-Distribution Detection","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2604.01798","citing_title":"A deep learning pipeline for PAM50 subtype classification using histopathology images and multi-objective patch selection","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01063","citing_title":"GEODE: Angle-Adaptive OOD Detection with Universal Scorer Compatibility","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00640","citing_title":"Knowing when to trust machine-learned interatomic potentials","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13262","citing_title":"Rethinking Uncertainty in Segmentation: From Estimation to Decision","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04614","citing_title":"A Clinical Point Cloud Paradigm for In-Hospital Mortality Prediction from Multi-Level Incomplete Multimodal EHRs","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21546","citing_title":"Component-Based Out-of-Distribution Detection","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2YJD4IVXK7WFTB2INT4RXMN4YB","json":"https://pith.science/pith/2YJD4IVXK7WFTB2INT4RXMN4YB.json","graph_json":"https://pith.science/api/pith-number/2YJD4IVXK7WFTB2INT4RXMN4YB/graph.json","events_json":"https://pith.science/api/pith-number/2YJD4IVXK7WFTB2INT4RXMN4YB/events.json","paper":"https://pith.science/paper/2YJD4IVX"},"agent_actions":{"view_html":"https://pith.science/pith/2YJD4IVXK7WFTB2INT4RXMN4YB","download_json":"https://pith.science/pith/2YJD4IVXK7WFTB2INT4RXMN4YB.json","view_paper":"https://pith.science/paper/2YJD4IVX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.04865&json=true","fetch_graph":"https://pith.science/api/pith-number/2YJD4IVXK7WFTB2INT4RXMN4YB/graph.json","fetch_events":"https://pith.science/api/pith-number/2YJD4IVXK7WFTB2INT4RXMN4YB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2YJD4IVXK7WFTB2INT4RXMN4YB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2YJD4IVXK7WFTB2INT4RXMN4YB/action/storage_attestation","attest_author":"https://pith.science/pith/2YJD4IVXK7WFTB2INT4RXMN4YB/action/author_attestation","sign_citation":"https://pith.science/pith/2YJD4IVXK7WFTB2INT4RXMN4YB/action/citation_signature","submit_replication":"https://pith.science/pith/2YJD4IVXK7WFTB2INT4RXMN4YB/action/replication_record"}},"created_at":"2026-05-18T00:23:22.395995+00:00","updated_at":"2026-05-18T00:23:22.395995+00:00"}