{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SWFGBDFC64N5DYVPDQAI7ILYPT","short_pith_number":"pith:SWFGBDFC","schema_version":"1.0","canonical_sha256":"958a608ca2f71bd1e2af1c008fa1787cdb79044955d4cbf31536a334acc3bf19","source":{"kind":"arxiv","id":"2412.20918","version":1},"attestation_state":"computed","paper":{"title":"Uncertainty-Aware Out-of-Distribution Detection with Gaussian Processes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Arpan Kusari, Chih-Li Sung, Wenbo Sun, Xiaoyang Song, Yang Chen","submitted_at":"2024-12-30T12:57:31Z","abstract_excerpt":"Deep neural networks (DNNs) are often constructed under the closed-world assumption, which may fail to generalize to the out-of-distribution (OOD) data. This leads to DNNs producing overconfident wrong predictions and can result in disastrous consequences in safety-critical applications. Existing OOD detection methods mainly rely on curating a set of OOD data for model training or hyper-parameter tuning to distinguish OOD data from training data (also known as in-distribution data or InD data). However, OOD samples are not always available during the training phase in real-world applications, "},"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":"2412.20918","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-12-30T12:57:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"14d45fde808068325e0b1d6a0dca105fd309c0d13e29fbf8a0a31d0601cd5c64","abstract_canon_sha256":"b2dc0c8df2c0be734f38601e68fd791094a7734640d25578513301cd52f5239b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:24.676839Z","signature_b64":"ON/UhrD+46AYnJuOma8jQzA+1TRiPzHBMXUK1rRMwF6mN0X8oOLHeq4SmJhYoII+pDmN8VXjZVSR+h2y1HdxBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"958a608ca2f71bd1e2af1c008fa1787cdb79044955d4cbf31536a334acc3bf19","last_reissued_at":"2026-07-05T09:55:24.676383Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:24.676383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncertainty-Aware Out-of-Distribution Detection with Gaussian Processes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Arpan Kusari, Chih-Li Sung, Wenbo Sun, Xiaoyang Song, Yang Chen","submitted_at":"2024-12-30T12:57:31Z","abstract_excerpt":"Deep neural networks (DNNs) are often constructed under the closed-world assumption, which may fail to generalize to the out-of-distribution (OOD) data. This leads to DNNs producing overconfident wrong predictions and can result in disastrous consequences in safety-critical applications. Existing OOD detection methods mainly rely on curating a set of OOD data for model training or hyper-parameter tuning to distinguish OOD data from training data (also known as in-distribution data or InD data). However, OOD samples are not always available during the training phase in real-world applications, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.20918","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/2412.20918/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":"2412.20918","created_at":"2026-07-05T09:55:24.676443+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.20918v1","created_at":"2026-07-05T09:55:24.676443+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.20918","created_at":"2026-07-05T09:55:24.676443+00:00"},{"alias_kind":"pith_short_12","alias_value":"SWFGBDFC64N5","created_at":"2026-07-05T09:55:24.676443+00:00"},{"alias_kind":"pith_short_16","alias_value":"SWFGBDFC64N5DYVP","created_at":"2026-07-05T09:55:24.676443+00:00"},{"alias_kind":"pith_short_8","alias_value":"SWFGBDFC","created_at":"2026-07-05T09:55:24.676443+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07102","citing_title":"GP-Adapter: Gaussian Process CLIP-Adapter for Few-Shot Out-of-Distribution Detection","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SWFGBDFC64N5DYVPDQAI7ILYPT","json":"https://pith.science/pith/SWFGBDFC64N5DYVPDQAI7ILYPT.json","graph_json":"https://pith.science/api/pith-number/SWFGBDFC64N5DYVPDQAI7ILYPT/graph.json","events_json":"https://pith.science/api/pith-number/SWFGBDFC64N5DYVPDQAI7ILYPT/events.json","paper":"https://pith.science/paper/SWFGBDFC"},"agent_actions":{"view_html":"https://pith.science/pith/SWFGBDFC64N5DYVPDQAI7ILYPT","download_json":"https://pith.science/pith/SWFGBDFC64N5DYVPDQAI7ILYPT.json","view_paper":"https://pith.science/paper/SWFGBDFC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.20918&json=true","fetch_graph":"https://pith.science/api/pith-number/SWFGBDFC64N5DYVPDQAI7ILYPT/graph.json","fetch_events":"https://pith.science/api/pith-number/SWFGBDFC64N5DYVPDQAI7ILYPT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SWFGBDFC64N5DYVPDQAI7ILYPT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SWFGBDFC64N5DYVPDQAI7ILYPT/action/storage_attestation","attest_author":"https://pith.science/pith/SWFGBDFC64N5DYVPDQAI7ILYPT/action/author_attestation","sign_citation":"https://pith.science/pith/SWFGBDFC64N5DYVPDQAI7ILYPT/action/citation_signature","submit_replication":"https://pith.science/pith/SWFGBDFC64N5DYVPDQAI7ILYPT/action/replication_record"}},"created_at":"2026-07-05T09:55:24.676443+00:00","updated_at":"2026-07-05T09:55:24.676443+00:00"}