{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:EWZIIH7IWH5ID3ARCOCV6QIM7H","short_pith_number":"pith:EWZIIH7I","schema_version":"1.0","canonical_sha256":"25b2841fe8b1fa81ec1113855f410cf9dd474ac83e0f044bcb60908191b3df15","source":{"kind":"arxiv","id":"2002.04683","version":1},"attestation_state":"computed","paper":{"title":"Learning with Out-of-Distribution Data for Audio Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Mark D. Plumbley, Qiuqiang Kong, Turab Iqbal, Wenwu Wang, Yin Cao","submitted_at":"2020-02-11T21:08:06Z","abstract_excerpt":"In supervised machine learning, the assumption that training data is labelled correctly is not always satisfied. In this paper, we investigate an instance of labelling error for classification tasks in which the dataset is corrupted with out-of-distribution (OOD) instances: data that does not belong to any of the target classes, but is labelled as such. We show that detecting and relabelling certain OOD instances, rather than discarding them, can have a positive effect on learning. The proposed method uses an auxiliary classifier, trained on data that is known to be in-distribution, for detect"},"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":"2002.04683","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-02-11T21:08:06Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"a6115f738014474411dbfc583e058b492d1d5a193432ff9587bc7614d3a1185e","abstract_canon_sha256":"ff5d3c2d1757add276c637c84517dc2903f1c3e44018ba6b5664a13cd7fea0fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:40:17.341839Z","signature_b64":"clhnBJaBz7XfrwwRTsv7Vsj8JhIgBbT9bz5sb23aNyNx9g9FXI7qUP9awGKPepZl1i4I2zlM0pMp0kud0zMCCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25b2841fe8b1fa81ec1113855f410cf9dd474ac83e0f044bcb60908191b3df15","last_reissued_at":"2026-07-05T00:40:17.341153Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:40:17.341153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning with Out-of-Distribution Data for Audio Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Mark D. Plumbley, Qiuqiang Kong, Turab Iqbal, Wenwu Wang, Yin Cao","submitted_at":"2020-02-11T21:08:06Z","abstract_excerpt":"In supervised machine learning, the assumption that training data is labelled correctly is not always satisfied. In this paper, we investigate an instance of labelling error for classification tasks in which the dataset is corrupted with out-of-distribution (OOD) instances: data that does not belong to any of the target classes, but is labelled as such. We show that detecting and relabelling certain OOD instances, rather than discarding them, can have a positive effect on learning. The proposed method uses an auxiliary classifier, trained on data that is known to be in-distribution, for detect"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.04683","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/2002.04683/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":"2002.04683","created_at":"2026-07-05T00:40:17.341256+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.04683v1","created_at":"2026-07-05T00:40:17.341256+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.04683","created_at":"2026-07-05T00:40:17.341256+00:00"},{"alias_kind":"pith_short_12","alias_value":"EWZIIH7IWH5I","created_at":"2026-07-05T00:40:17.341256+00:00"},{"alias_kind":"pith_short_16","alias_value":"EWZIIH7IWH5ID3AR","created_at":"2026-07-05T00:40:17.341256+00:00"},{"alias_kind":"pith_short_8","alias_value":"EWZIIH7I","created_at":"2026-07-05T00:40:17.341256+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/EWZIIH7IWH5ID3ARCOCV6QIM7H","json":"https://pith.science/pith/EWZIIH7IWH5ID3ARCOCV6QIM7H.json","graph_json":"https://pith.science/api/pith-number/EWZIIH7IWH5ID3ARCOCV6QIM7H/graph.json","events_json":"https://pith.science/api/pith-number/EWZIIH7IWH5ID3ARCOCV6QIM7H/events.json","paper":"https://pith.science/paper/EWZIIH7I"},"agent_actions":{"view_html":"https://pith.science/pith/EWZIIH7IWH5ID3ARCOCV6QIM7H","download_json":"https://pith.science/pith/EWZIIH7IWH5ID3ARCOCV6QIM7H.json","view_paper":"https://pith.science/paper/EWZIIH7I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.04683&json=true","fetch_graph":"https://pith.science/api/pith-number/EWZIIH7IWH5ID3ARCOCV6QIM7H/graph.json","fetch_events":"https://pith.science/api/pith-number/EWZIIH7IWH5ID3ARCOCV6QIM7H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EWZIIH7IWH5ID3ARCOCV6QIM7H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EWZIIH7IWH5ID3ARCOCV6QIM7H/action/storage_attestation","attest_author":"https://pith.science/pith/EWZIIH7IWH5ID3ARCOCV6QIM7H/action/author_attestation","sign_citation":"https://pith.science/pith/EWZIIH7IWH5ID3ARCOCV6QIM7H/action/citation_signature","submit_replication":"https://pith.science/pith/EWZIIH7IWH5ID3ARCOCV6QIM7H/action/replication_record"}},"created_at":"2026-07-05T00:40:17.341256+00:00","updated_at":"2026-07-05T00:40:17.341256+00:00"}