{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3GE3NZTCZER5UFISEIYNRTEO42","short_pith_number":"pith:3GE3NZTC","schema_version":"1.0","canonical_sha256":"d989b6e662c923da15122230d8cc8ee6885540f3f62651f1af529caf177f239a","source":{"kind":"arxiv","id":"2110.09246","version":1},"attestation_state":"computed","paper":{"title":"Single Layer Predictive Normalized Maximum Likelihood for Out-of-Distribution Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Koby Bibas, Meir Feder, Tal Hassner","submitted_at":"2021-10-18T12:48:05Z","abstract_excerpt":"Detecting out-of-distribution (OOD) samples is vital for developing machine learning based models for critical safety systems. Common approaches for OOD detection assume access to some OOD samples during training which may not be available in a real-life scenario. Instead, we utilize the {\\em predictive normalized maximum likelihood} (pNML) learner, in which no assumptions are made on the tested input. We derive an explicit expression of the pNML and its generalization error, denoted as the {\\em regret}, for a single layer neural network (NN). We show that this learner generalizes well when (i"},"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":"2110.09246","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-18T12:48:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9530833b889a389d48c6b3681420670beb9ce5e8f263222b36d1d1357a84e37d","abstract_canon_sha256":"03f5af8c9820b3044a1a66145257457771f51bec3011a7fc85ddd8a2bf0cc625"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:23:26.097575Z","signature_b64":"qlGmZX/ToA3d7TINam9Y+nPwNJGXrGjgO+XzE+7Zjdb8IqA5MJF1j1MnS9xGT1HAfawTyGdan1VQTJxHPPFOAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d989b6e662c923da15122230d8cc8ee6885540f3f62651f1af529caf177f239a","last_reissued_at":"2026-07-05T03:23:26.097107Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:23:26.097107Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Single Layer Predictive Normalized Maximum Likelihood for Out-of-Distribution Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Koby Bibas, Meir Feder, Tal Hassner","submitted_at":"2021-10-18T12:48:05Z","abstract_excerpt":"Detecting out-of-distribution (OOD) samples is vital for developing machine learning based models for critical safety systems. Common approaches for OOD detection assume access to some OOD samples during training which may not be available in a real-life scenario. Instead, we utilize the {\\em predictive normalized maximum likelihood} (pNML) learner, in which no assumptions are made on the tested input. We derive an explicit expression of the pNML and its generalization error, denoted as the {\\em regret}, for a single layer neural network (NN). We show that this learner generalizes well when (i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.09246","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/2110.09246/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":"2110.09246","created_at":"2026-07-05T03:23:26.097159+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.09246v1","created_at":"2026-07-05T03:23:26.097159+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.09246","created_at":"2026-07-05T03:23:26.097159+00:00"},{"alias_kind":"pith_short_12","alias_value":"3GE3NZTCZER5","created_at":"2026-07-05T03:23:26.097159+00:00"},{"alias_kind":"pith_short_16","alias_value":"3GE3NZTCZER5UFIS","created_at":"2026-07-05T03:23:26.097159+00:00"},{"alias_kind":"pith_short_8","alias_value":"3GE3NZTC","created_at":"2026-07-05T03:23:26.097159+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/3GE3NZTCZER5UFISEIYNRTEO42","json":"https://pith.science/pith/3GE3NZTCZER5UFISEIYNRTEO42.json","graph_json":"https://pith.science/api/pith-number/3GE3NZTCZER5UFISEIYNRTEO42/graph.json","events_json":"https://pith.science/api/pith-number/3GE3NZTCZER5UFISEIYNRTEO42/events.json","paper":"https://pith.science/paper/3GE3NZTC"},"agent_actions":{"view_html":"https://pith.science/pith/3GE3NZTCZER5UFISEIYNRTEO42","download_json":"https://pith.science/pith/3GE3NZTCZER5UFISEIYNRTEO42.json","view_paper":"https://pith.science/paper/3GE3NZTC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.09246&json=true","fetch_graph":"https://pith.science/api/pith-number/3GE3NZTCZER5UFISEIYNRTEO42/graph.json","fetch_events":"https://pith.science/api/pith-number/3GE3NZTCZER5UFISEIYNRTEO42/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3GE3NZTCZER5UFISEIYNRTEO42/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3GE3NZTCZER5UFISEIYNRTEO42/action/storage_attestation","attest_author":"https://pith.science/pith/3GE3NZTCZER5UFISEIYNRTEO42/action/author_attestation","sign_citation":"https://pith.science/pith/3GE3NZTCZER5UFISEIYNRTEO42/action/citation_signature","submit_replication":"https://pith.science/pith/3GE3NZTCZER5UFISEIYNRTEO42/action/replication_record"}},"created_at":"2026-07-05T03:23:26.097159+00:00","updated_at":"2026-07-05T03:23:26.097159+00:00"}