{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:F346JXN3Z3L4OPCTRZSMCNX652","short_pith_number":"pith:F346JXN3","schema_version":"1.0","canonical_sha256":"2ef9e4ddbbced7c73c538e64c136feeebdce9ab7f4863a46081daffaa1bed434","source":{"kind":"arxiv","id":"2010.12995","version":2},"attestation_state":"computed","paper":{"title":"Out-of-distribution detection for regression tasks: parameter versus predictor entropy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alireza Yeganehparast, Fran\\c{c}ois Laviolette, Jos\\'ee Desharnais, Mathieu Alain, Pascal Germain, Patrick Dallaire, Yann Pequignot","submitted_at":"2020-10-24T21:41:21Z","abstract_excerpt":"It is crucial to detect when an instance lies downright too far from the training samples for the machine learning model to be trusted, a challenge known as out-of-distribution (OOD) detection. For neural networks, one approach to this task consists of learning a diversity of predictors that all can explain the training data. This information can be used to estimate the epistemic uncertainty at a given newly observed instance in terms of a measure of the disagreement of the predictions. Evaluation and certification of the ability of a method to detect OOD require specifying instances which are"},"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":"2010.12995","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-24T21:41:21Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"2a10ff232f72c8ca389877863888c3c4bac31465c0a4551b72d14b8042b10463","abstract_canon_sha256":"f489e368b8d8fed1d85e0ed7e64ca4fff608eb800d4caf9959d6b951e231c738"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:49:38.709419Z","signature_b64":"BemY5NUuSGR5sT+5BM7fNRPTgxUxYodrnCjrX1znHeLYvKVnguk854Z576v6Jz64JegFD4YyEe7xaXCdHSobCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ef9e4ddbbced7c73c538e64c136feeebdce9ab7f4863a46081daffaa1bed434","last_reissued_at":"2026-07-05T06:49:38.709003Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:49:38.709003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Out-of-distribution detection for regression tasks: parameter versus predictor entropy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alireza Yeganehparast, Fran\\c{c}ois Laviolette, Jos\\'ee Desharnais, Mathieu Alain, Pascal Germain, Patrick Dallaire, Yann Pequignot","submitted_at":"2020-10-24T21:41:21Z","abstract_excerpt":"It is crucial to detect when an instance lies downright too far from the training samples for the machine learning model to be trusted, a challenge known as out-of-distribution (OOD) detection. For neural networks, one approach to this task consists of learning a diversity of predictors that all can explain the training data. This information can be used to estimate the epistemic uncertainty at a given newly observed instance in terms of a measure of the disagreement of the predictions. Evaluation and certification of the ability of a method to detect OOD require specifying instances which are"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12995","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/2010.12995/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":"2010.12995","created_at":"2026-07-05T06:49:38.709056+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.12995v2","created_at":"2026-07-05T06:49:38.709056+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12995","created_at":"2026-07-05T06:49:38.709056+00:00"},{"alias_kind":"pith_short_12","alias_value":"F346JXN3Z3L4","created_at":"2026-07-05T06:49:38.709056+00:00"},{"alias_kind":"pith_short_16","alias_value":"F346JXN3Z3L4OPCT","created_at":"2026-07-05T06:49:38.709056+00:00"},{"alias_kind":"pith_short_8","alias_value":"F346JXN3","created_at":"2026-07-05T06:49:38.709056+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/F346JXN3Z3L4OPCTRZSMCNX652","json":"https://pith.science/pith/F346JXN3Z3L4OPCTRZSMCNX652.json","graph_json":"https://pith.science/api/pith-number/F346JXN3Z3L4OPCTRZSMCNX652/graph.json","events_json":"https://pith.science/api/pith-number/F346JXN3Z3L4OPCTRZSMCNX652/events.json","paper":"https://pith.science/paper/F346JXN3"},"agent_actions":{"view_html":"https://pith.science/pith/F346JXN3Z3L4OPCTRZSMCNX652","download_json":"https://pith.science/pith/F346JXN3Z3L4OPCTRZSMCNX652.json","view_paper":"https://pith.science/paper/F346JXN3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.12995&json=true","fetch_graph":"https://pith.science/api/pith-number/F346JXN3Z3L4OPCTRZSMCNX652/graph.json","fetch_events":"https://pith.science/api/pith-number/F346JXN3Z3L4OPCTRZSMCNX652/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F346JXN3Z3L4OPCTRZSMCNX652/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F346JXN3Z3L4OPCTRZSMCNX652/action/storage_attestation","attest_author":"https://pith.science/pith/F346JXN3Z3L4OPCTRZSMCNX652/action/author_attestation","sign_citation":"https://pith.science/pith/F346JXN3Z3L4OPCTRZSMCNX652/action/citation_signature","submit_replication":"https://pith.science/pith/F346JXN3Z3L4OPCTRZSMCNX652/action/replication_record"}},"created_at":"2026-07-05T06:49:38.709056+00:00","updated_at":"2026-07-05T06:49:38.709056+00:00"}