{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FOAUKIRJ77EQNFHF35KZGXL4YS","short_pith_number":"pith:FOAUKIRJ","schema_version":"1.0","canonical_sha256":"2b81452229ffc90694e5df55935d7cc4bbb7c548ce1a35bdd42149623c1d8956","source":{"kind":"arxiv","id":"2108.12731","version":2},"attestation_state":"computed","paper":{"title":"$k$Folden: $k$-Fold Ensemble for Out-Of-Distribution Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chun Fan, Fei Wu, Jiwei Li, Jun Zhang, Tianwei Zhang, Xiaofei Sun, Xiaoya Li, Yuxian Meng","submitted_at":"2021-08-29T01:52:11Z","abstract_excerpt":"Out-of-Distribution (OOD) detection is an important problem in natural language processing (NLP). In this work, we propose a simple yet effective framework $k$Folden, which mimics the behaviors of OOD detection during training without the use of any external data. For a task with $k$ training labels, $k$Folden induces $k$ sub-models, each of which is trained on a subset with $k-1$ categories with the left category masked unknown to the sub-model. Exposing an unknown label to the sub-model during training, the model is encouraged to learn to equally attribute the probability to the seen $k-1$ l"},"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":"2108.12731","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-29T01:52:11Z","cross_cats_sorted":[],"title_canon_sha256":"7c9a9a1070bfb8a60af83256835d0075e55f1cb1290f091f0edfd88a97eb671d","abstract_canon_sha256":"431ef04016682a07a058a0cbeee1e070e534bbcf7d43aaafca9e92f488d19401"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:29:29.826972Z","signature_b64":"uoo6hzBRdCa+Q3uigXoKupMgk3libNndKaPtuSS8kTHuYoUELRUhUzyJXFR2fczkRhKjAxuK/QLaNt56cF0RDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b81452229ffc90694e5df55935d7cc4bbb7c548ce1a35bdd42149623c1d8956","last_reissued_at":"2026-07-05T03:29:29.826501Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:29:29.826501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"$k$Folden: $k$-Fold Ensemble for Out-Of-Distribution Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chun Fan, Fei Wu, Jiwei Li, Jun Zhang, Tianwei Zhang, Xiaofei Sun, Xiaoya Li, Yuxian Meng","submitted_at":"2021-08-29T01:52:11Z","abstract_excerpt":"Out-of-Distribution (OOD) detection is an important problem in natural language processing (NLP). In this work, we propose a simple yet effective framework $k$Folden, which mimics the behaviors of OOD detection during training without the use of any external data. For a task with $k$ training labels, $k$Folden induces $k$ sub-models, each of which is trained on a subset with $k-1$ categories with the left category masked unknown to the sub-model. Exposing an unknown label to the sub-model during training, the model is encouraged to learn to equally attribute the probability to the seen $k-1$ l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.12731","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/2108.12731/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":"2108.12731","created_at":"2026-07-05T03:29:29.826564+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.12731v2","created_at":"2026-07-05T03:29:29.826564+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.12731","created_at":"2026-07-05T03:29:29.826564+00:00"},{"alias_kind":"pith_short_12","alias_value":"FOAUKIRJ77EQ","created_at":"2026-07-05T03:29:29.826564+00:00"},{"alias_kind":"pith_short_16","alias_value":"FOAUKIRJ77EQNFHF","created_at":"2026-07-05T03:29:29.826564+00:00"},{"alias_kind":"pith_short_8","alias_value":"FOAUKIRJ","created_at":"2026-07-05T03:29:29.826564+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/FOAUKIRJ77EQNFHF35KZGXL4YS","json":"https://pith.science/pith/FOAUKIRJ77EQNFHF35KZGXL4YS.json","graph_json":"https://pith.science/api/pith-number/FOAUKIRJ77EQNFHF35KZGXL4YS/graph.json","events_json":"https://pith.science/api/pith-number/FOAUKIRJ77EQNFHF35KZGXL4YS/events.json","paper":"https://pith.science/paper/FOAUKIRJ"},"agent_actions":{"view_html":"https://pith.science/pith/FOAUKIRJ77EQNFHF35KZGXL4YS","download_json":"https://pith.science/pith/FOAUKIRJ77EQNFHF35KZGXL4YS.json","view_paper":"https://pith.science/paper/FOAUKIRJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.12731&json=true","fetch_graph":"https://pith.science/api/pith-number/FOAUKIRJ77EQNFHF35KZGXL4YS/graph.json","fetch_events":"https://pith.science/api/pith-number/FOAUKIRJ77EQNFHF35KZGXL4YS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FOAUKIRJ77EQNFHF35KZGXL4YS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FOAUKIRJ77EQNFHF35KZGXL4YS/action/storage_attestation","attest_author":"https://pith.science/pith/FOAUKIRJ77EQNFHF35KZGXL4YS/action/author_attestation","sign_citation":"https://pith.science/pith/FOAUKIRJ77EQNFHF35KZGXL4YS/action/citation_signature","submit_replication":"https://pith.science/pith/FOAUKIRJ77EQNFHF35KZGXL4YS/action/replication_record"}},"created_at":"2026-07-05T03:29:29.826564+00:00","updated_at":"2026-07-05T03:29:29.826564+00:00"}