{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:G57D3EEKRR5U7SFS5NTCHT2XNS","short_pith_number":"pith:G57D3EEK","schema_version":"1.0","canonical_sha256":"377e3d908a8c7b4fc8b2eb6623cf576ca63d052fa59f3f27d568e9eea0f2910a","source":{"kind":"arxiv","id":"2203.01097","version":1},"attestation_state":"computed","paper":{"title":"Model-agnostic out-of-distribution detection using combined statistical tests","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Federico Bergamin, Hugo Schmutz, Hugo Senetaire, Jakob D. Havtorn, Jes Frellsen, Lars Maal{\\o}e, Pierre-Alexandre Mattei, S{\\o}ren Hauberg","submitted_at":"2022-03-02T13:32:09Z","abstract_excerpt":"We present simple methods for out-of-distribution detection using a trained generative model. These techniques, based on classical statistical tests, are model-agnostic in the sense that they can be applied to any differentiable generative model. The idea is to combine a classical parametric test (Rao's score test) with the recently introduced typicality test. These two test statistics are both theoretically well-founded and exploit different sources of information based on the likelihood for the typicality test and its gradient for the score test. We show that combining them using Fisher's me"},"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":"2203.01097","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-03-02T13:32:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"73570d14c3599bdbc915c09510bcae2d75615d9333cd7e8f59592dddfc4ead2c","abstract_canon_sha256":"2ae512504829b1e3c5dec96a7fdd574b0adf29a6e2c379dea4c39b6203b0cf13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:01:37.042776Z","signature_b64":"um5COAN0vh/U5CiQUL9pjwEHKe2oc1qYVhu9d3O3uXOizUWvZ8C6TgPsT1QUhYTTHuMSsHeIbiO0WORPwpXFBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"377e3d908a8c7b4fc8b2eb6623cf576ca63d052fa59f3f27d568e9eea0f2910a","last_reissued_at":"2026-07-05T04:01:37.042439Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:01:37.042439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-agnostic out-of-distribution detection using combined statistical tests","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Federico Bergamin, Hugo Schmutz, Hugo Senetaire, Jakob D. Havtorn, Jes Frellsen, Lars Maal{\\o}e, Pierre-Alexandre Mattei, S{\\o}ren Hauberg","submitted_at":"2022-03-02T13:32:09Z","abstract_excerpt":"We present simple methods for out-of-distribution detection using a trained generative model. These techniques, based on classical statistical tests, are model-agnostic in the sense that they can be applied to any differentiable generative model. The idea is to combine a classical parametric test (Rao's score test) with the recently introduced typicality test. These two test statistics are both theoretically well-founded and exploit different sources of information based on the likelihood for the typicality test and its gradient for the score test. We show that combining them using Fisher's me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.01097","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/2203.01097/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":"2203.01097","created_at":"2026-07-05T04:01:37.042494+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.01097v1","created_at":"2026-07-05T04:01:37.042494+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.01097","created_at":"2026-07-05T04:01:37.042494+00:00"},{"alias_kind":"pith_short_12","alias_value":"G57D3EEKRR5U","created_at":"2026-07-05T04:01:37.042494+00:00"},{"alias_kind":"pith_short_16","alias_value":"G57D3EEKRR5U7SFS","created_at":"2026-07-05T04:01:37.042494+00:00"},{"alias_kind":"pith_short_8","alias_value":"G57D3EEK","created_at":"2026-07-05T04:01:37.042494+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/G57D3EEKRR5U7SFS5NTCHT2XNS","json":"https://pith.science/pith/G57D3EEKRR5U7SFS5NTCHT2XNS.json","graph_json":"https://pith.science/api/pith-number/G57D3EEKRR5U7SFS5NTCHT2XNS/graph.json","events_json":"https://pith.science/api/pith-number/G57D3EEKRR5U7SFS5NTCHT2XNS/events.json","paper":"https://pith.science/paper/G57D3EEK"},"agent_actions":{"view_html":"https://pith.science/pith/G57D3EEKRR5U7SFS5NTCHT2XNS","download_json":"https://pith.science/pith/G57D3EEKRR5U7SFS5NTCHT2XNS.json","view_paper":"https://pith.science/paper/G57D3EEK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.01097&json=true","fetch_graph":"https://pith.science/api/pith-number/G57D3EEKRR5U7SFS5NTCHT2XNS/graph.json","fetch_events":"https://pith.science/api/pith-number/G57D3EEKRR5U7SFS5NTCHT2XNS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G57D3EEKRR5U7SFS5NTCHT2XNS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G57D3EEKRR5U7SFS5NTCHT2XNS/action/storage_attestation","attest_author":"https://pith.science/pith/G57D3EEKRR5U7SFS5NTCHT2XNS/action/author_attestation","sign_citation":"https://pith.science/pith/G57D3EEKRR5U7SFS5NTCHT2XNS/action/citation_signature","submit_replication":"https://pith.science/pith/G57D3EEKRR5U7SFS5NTCHT2XNS/action/replication_record"}},"created_at":"2026-07-05T04:01:37.042494+00:00","updated_at":"2026-07-05T04:01:37.042494+00:00"}