{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:52LGOVCD3E3YJZCV7J6HBM5TTC","short_pith_number":"pith:52LGOVCD","schema_version":"1.0","canonical_sha256":"ee96675443d93784e455fa7c70b3b398be5f215e0eae664b1574804f32098132","source":{"kind":"arxiv","id":"2606.29952","version":1},"attestation_state":"computed","paper":{"title":"Exploiting Local Flatness for Efficient Out-of-Distribution Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Dongyeop Lee, Hyunji Jung, Namhoon Lee, Seonghwan Park","submitted_at":"2026-06-29T08:27:27Z","abstract_excerpt":"Detecting out-of-distribution (OOD) data is crucial for reliable machine learning deployment. Among detection strategies, post-hoc methods are particularly attractive due to their efficiency, as they operate directly on pre-trained networks without requiring retraining. Within this paradigm, one promising direction exploits loss-landscape curvature to estimate model uncertainty; however, such methods incur substantial computational cost and rely on implicit assumptions about how landscape flatness differs between in-distribution (ID) and OOD data. In this work, we provide the first systematic "},"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":"2606.29952","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-29T08:27:27Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"efc8e68662e7f449fe9bcda4bf028d93be25885400030fb8e4a8e61f02186956","abstract_canon_sha256":"1a484875ec725b84319a7f56a54d98056727fb023af62150b078e12dd38483a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:42.466663Z","signature_b64":"zLaDnJrvs4R+496PPD0LG1yzHvR80Q4IhW+PAVvFkFK2xPQJJYfbJtrh2RNNtcgzNfNdzUWfYSKPVjTwB8WLAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee96675443d93784e455fa7c70b3b398be5f215e0eae664b1574804f32098132","last_reissued_at":"2026-06-30T02:17:42.466109Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:42.466109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploiting Local Flatness for Efficient Out-of-Distribution Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Dongyeop Lee, Hyunji Jung, Namhoon Lee, Seonghwan Park","submitted_at":"2026-06-29T08:27:27Z","abstract_excerpt":"Detecting out-of-distribution (OOD) data is crucial for reliable machine learning deployment. Among detection strategies, post-hoc methods are particularly attractive due to their efficiency, as they operate directly on pre-trained networks without requiring retraining. Within this paradigm, one promising direction exploits loss-landscape curvature to estimate model uncertainty; however, such methods incur substantial computational cost and rely on implicit assumptions about how landscape flatness differs between in-distribution (ID) and OOD data. In this work, we provide the first systematic "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29952","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/2606.29952/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":"2606.29952","created_at":"2026-06-30T02:17:42.466199+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29952v1","created_at":"2026-06-30T02:17:42.466199+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29952","created_at":"2026-06-30T02:17:42.466199+00:00"},{"alias_kind":"pith_short_12","alias_value":"52LGOVCD3E3Y","created_at":"2026-06-30T02:17:42.466199+00:00"},{"alias_kind":"pith_short_16","alias_value":"52LGOVCD3E3YJZCV","created_at":"2026-06-30T02:17:42.466199+00:00"},{"alias_kind":"pith_short_8","alias_value":"52LGOVCD","created_at":"2026-06-30T02:17:42.466199+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/52LGOVCD3E3YJZCV7J6HBM5TTC","json":"https://pith.science/pith/52LGOVCD3E3YJZCV7J6HBM5TTC.json","graph_json":"https://pith.science/api/pith-number/52LGOVCD3E3YJZCV7J6HBM5TTC/graph.json","events_json":"https://pith.science/api/pith-number/52LGOVCD3E3YJZCV7J6HBM5TTC/events.json","paper":"https://pith.science/paper/52LGOVCD"},"agent_actions":{"view_html":"https://pith.science/pith/52LGOVCD3E3YJZCV7J6HBM5TTC","download_json":"https://pith.science/pith/52LGOVCD3E3YJZCV7J6HBM5TTC.json","view_paper":"https://pith.science/paper/52LGOVCD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29952&json=true","fetch_graph":"https://pith.science/api/pith-number/52LGOVCD3E3YJZCV7J6HBM5TTC/graph.json","fetch_events":"https://pith.science/api/pith-number/52LGOVCD3E3YJZCV7J6HBM5TTC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/52LGOVCD3E3YJZCV7J6HBM5TTC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/52LGOVCD3E3YJZCV7J6HBM5TTC/action/storage_attestation","attest_author":"https://pith.science/pith/52LGOVCD3E3YJZCV7J6HBM5TTC/action/author_attestation","sign_citation":"https://pith.science/pith/52LGOVCD3E3YJZCV7J6HBM5TTC/action/citation_signature","submit_replication":"https://pith.science/pith/52LGOVCD3E3YJZCV7J6HBM5TTC/action/replication_record"}},"created_at":"2026-06-30T02:17:42.466199+00:00","updated_at":"2026-06-30T02:17:42.466199+00:00"}