{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LKFVPNA26NFLQX6VEJTULACEAO","short_pith_number":"pith:LKFVPNA2","schema_version":"1.0","canonical_sha256":"5a8b57b41af34ab85fd522674580440381761c8e4a7a8cad1f0e5eeee6ed2e1b","source":{"kind":"arxiv","id":"1906.02845","version":2},"attestation_state":"computed","paper":{"title":"Likelihood Ratios for Out-of-Distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Balaji Lakshminarayanan, Emily Fertig, Jasper Snoek, Jie Ren, Joshua V. Dillon, Mark A. DePristo, Peter J. Liu, Ryan Poplin","submitted_at":"2019-06-07T00:01:42Z","abstract_excerpt":"Discriminative neural networks offer little or no performance guarantees when deployed on data not generated by the same process as the training distribution. On such out-of-distribution (OOD) inputs, the prediction may not only be erroneous, but confidently so, limiting the safe deployment of classifiers in real-world applications. One such challenging application is bacteria identification based on genomic sequences, which holds the promise of early detection of diseases, but requires a model that can output low confidence predictions on OOD genomic sequences from new bacteria that were not "},"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":"1906.02845","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-06-07T00:01:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"63f4563e159e18d6b123a983458f1f5fc01911e1d65c2f2bf4329e3abaed50a5","abstract_canon_sha256":"f755ad2a4584086deed3531a56d07b264ba73168a856aa75f03b13eef23512dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:24:17.669400Z","signature_b64":"859lHJ2Oo5rgu+UbWQdjYH98H6s5AmHPiKx86jz8CrIA1sQmCkV9ytVdAqLZu5+W/67UtO2TyyEH7Z74TkR0CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a8b57b41af34ab85fd522674580440381761c8e4a7a8cad1f0e5eeee6ed2e1b","last_reissued_at":"2026-07-05T00:24:17.668900Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:24:17.668900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Likelihood Ratios for Out-of-Distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Balaji Lakshminarayanan, Emily Fertig, Jasper Snoek, Jie Ren, Joshua V. Dillon, Mark A. DePristo, Peter J. Liu, Ryan Poplin","submitted_at":"2019-06-07T00:01:42Z","abstract_excerpt":"Discriminative neural networks offer little or no performance guarantees when deployed on data not generated by the same process as the training distribution. On such out-of-distribution (OOD) inputs, the prediction may not only be erroneous, but confidently so, limiting the safe deployment of classifiers in real-world applications. One such challenging application is bacteria identification based on genomic sequences, which holds the promise of early detection of diseases, but requires a model that can output low confidence predictions on OOD genomic sequences from new bacteria that were not "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.02845","kind":"arxiv","version":2},"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/1906.02845/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":"1906.02845","created_at":"2026-07-05T00:24:17.668957+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.02845v2","created_at":"2026-07-05T00:24:17.668957+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.02845","created_at":"2026-07-05T00:24:17.668957+00:00"},{"alias_kind":"pith_short_12","alias_value":"LKFVPNA26NFL","created_at":"2026-07-05T00:24:17.668957+00:00"},{"alias_kind":"pith_short_16","alias_value":"LKFVPNA26NFLQX6V","created_at":"2026-07-05T00:24:17.668957+00:00"},{"alias_kind":"pith_short_8","alias_value":"LKFVPNA2","created_at":"2026-07-05T00:24:17.668957+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18988","citing_title":"Surviving the Unseen: Predictive Defense for Novel Multi-Turn Multimodal Attacks","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LKFVPNA26NFLQX6VEJTULACEAO","json":"https://pith.science/pith/LKFVPNA26NFLQX6VEJTULACEAO.json","graph_json":"https://pith.science/api/pith-number/LKFVPNA26NFLQX6VEJTULACEAO/graph.json","events_json":"https://pith.science/api/pith-number/LKFVPNA26NFLQX6VEJTULACEAO/events.json","paper":"https://pith.science/paper/LKFVPNA2"},"agent_actions":{"view_html":"https://pith.science/pith/LKFVPNA26NFLQX6VEJTULACEAO","download_json":"https://pith.science/pith/LKFVPNA26NFLQX6VEJTULACEAO.json","view_paper":"https://pith.science/paper/LKFVPNA2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.02845&json=true","fetch_graph":"https://pith.science/api/pith-number/LKFVPNA26NFLQX6VEJTULACEAO/graph.json","fetch_events":"https://pith.science/api/pith-number/LKFVPNA26NFLQX6VEJTULACEAO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LKFVPNA26NFLQX6VEJTULACEAO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LKFVPNA26NFLQX6VEJTULACEAO/action/storage_attestation","attest_author":"https://pith.science/pith/LKFVPNA26NFLQX6VEJTULACEAO/action/author_attestation","sign_citation":"https://pith.science/pith/LKFVPNA26NFLQX6VEJTULACEAO/action/citation_signature","submit_replication":"https://pith.science/pith/LKFVPNA26NFLQX6VEJTULACEAO/action/replication_record"}},"created_at":"2026-07-05T00:24:17.668957+00:00","updated_at":"2026-07-05T00:24:17.668957+00:00"}