{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SO5MALJO3O5H66Q2BH44N3HZGL","short_pith_number":"pith:SO5MALJO","schema_version":"1.0","canonical_sha256":"93bac02d2edbba7f7a1a09f9c6ecf932d5328264ec58bd57ac27851226c456c8","source":{"kind":"arxiv","id":"2303.13995","version":1},"attestation_state":"computed","paper":{"title":"LINe: Out-of-Distribution Detection by Leveraging Important Neurons","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gyeong-Moon Park, Seong Tae Kim, Yong Hyun Ahn","submitted_at":"2023-03-24T13:49:05Z","abstract_excerpt":"It is important to quantify the uncertainty of input samples, especially in mission-critical domains such as autonomous driving and healthcare, where failure predictions on out-of-distribution (OOD) data are likely to cause big problems. OOD detection problem fundamentally begins in that the model cannot express what it is not aware of. Post-hoc OOD detection approaches are widely explored because they do not require an additional re-training process which might degrade the model's performance and increase the training cost. In this study, from the perspective of neurons in the deep layer of 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":"2303.13995","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-24T13:49:05Z","cross_cats_sorted":[],"title_canon_sha256":"fdfee27f65239fe52fa0fe8503fc23ade29e90e23399844c21bf5a79f213b572","abstract_canon_sha256":"ff90160516767a4b34e06acbb3993eb36a043fb450e3508eea410bb8c87f8238"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:22.349163Z","signature_b64":"btt0uszx9SnhMWPPBgYMrPwcrLX0o7rQlaq+Fw5Z96cVPr5N7DMzsID9Cx7NB95uYuukrizx3aTLcR5EGZ3DBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93bac02d2edbba7f7a1a09f9c6ecf932d5328264ec58bd57ac27851226c456c8","last_reissued_at":"2026-07-05T05:54:22.348673Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:22.348673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LINe: Out-of-Distribution Detection by Leveraging Important Neurons","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gyeong-Moon Park, Seong Tae Kim, Yong Hyun Ahn","submitted_at":"2023-03-24T13:49:05Z","abstract_excerpt":"It is important to quantify the uncertainty of input samples, especially in mission-critical domains such as autonomous driving and healthcare, where failure predictions on out-of-distribution (OOD) data are likely to cause big problems. OOD detection problem fundamentally begins in that the model cannot express what it is not aware of. Post-hoc OOD detection approaches are widely explored because they do not require an additional re-training process which might degrade the model's performance and increase the training cost. In this study, from the perspective of neurons in the deep layer of t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.13995","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2303.13995/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":"2303.13995","created_at":"2026-07-05T05:54:22.348747+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.13995v1","created_at":"2026-07-05T05:54:22.348747+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.13995","created_at":"2026-07-05T05:54:22.348747+00:00"},{"alias_kind":"pith_short_12","alias_value":"SO5MALJO3O5H","created_at":"2026-07-05T05:54:22.348747+00:00"},{"alias_kind":"pith_short_16","alias_value":"SO5MALJO3O5H66Q2","created_at":"2026-07-05T05:54:22.348747+00:00"},{"alias_kind":"pith_short_8","alias_value":"SO5MALJO","created_at":"2026-07-05T05:54:22.348747+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2402.17888","citing_title":"ConjNorm: Tractable Density Estimation for Out-of-Distribution Detection","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SO5MALJO3O5H66Q2BH44N3HZGL","json":"https://pith.science/pith/SO5MALJO3O5H66Q2BH44N3HZGL.json","graph_json":"https://pith.science/api/pith-number/SO5MALJO3O5H66Q2BH44N3HZGL/graph.json","events_json":"https://pith.science/api/pith-number/SO5MALJO3O5H66Q2BH44N3HZGL/events.json","paper":"https://pith.science/paper/SO5MALJO"},"agent_actions":{"view_html":"https://pith.science/pith/SO5MALJO3O5H66Q2BH44N3HZGL","download_json":"https://pith.science/pith/SO5MALJO3O5H66Q2BH44N3HZGL.json","view_paper":"https://pith.science/paper/SO5MALJO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.13995&json=true","fetch_graph":"https://pith.science/api/pith-number/SO5MALJO3O5H66Q2BH44N3HZGL/graph.json","fetch_events":"https://pith.science/api/pith-number/SO5MALJO3O5H66Q2BH44N3HZGL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SO5MALJO3O5H66Q2BH44N3HZGL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SO5MALJO3O5H66Q2BH44N3HZGL/action/storage_attestation","attest_author":"https://pith.science/pith/SO5MALJO3O5H66Q2BH44N3HZGL/action/author_attestation","sign_citation":"https://pith.science/pith/SO5MALJO3O5H66Q2BH44N3HZGL/action/citation_signature","submit_replication":"https://pith.science/pith/SO5MALJO3O5H66Q2BH44N3HZGL/action/replication_record"}},"created_at":"2026-07-05T05:54:22.348747+00:00","updated_at":"2026-07-05T05:54:22.348747+00:00"}