{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:V63ETCABS3PLHINZNEK5FSVXSO","short_pith_number":"pith:V63ETCAB","schema_version":"1.0","canonical_sha256":"afb649880196deb3a1b96915d2cab7938d1bb64def66f1e896a0c84a815a638a","source":{"kind":"arxiv","id":"2210.07448","version":2},"attestation_state":"computed","paper":{"title":"Evaluating Out-of-Distribution Performance on Document Image Classifiers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"David Kuang, Gordon Lim, Kevin Leach, Stefan Larson, Yutong Ai","submitted_at":"2022-10-14T01:24:21Z","abstract_excerpt":"The ability of a document classifier to handle inputs that are drawn from a distribution different from the training distribution is crucial for robust deployment and generalizability. The RVL-CDIP corpus is the de facto standard benchmark for document classification, yet to our knowledge all studies that use this corpus do not include evaluation on out-of-distribution documents. In this paper, we curate and release a new out-of-distribution benchmark for evaluating out-of-distribution performance for document classifiers. Our new out-of-distribution benchmark consists of two types of document"},"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":"2210.07448","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-14T01:24:21Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a958c5bee972f55864da0ef43d16f0b987b1c97ee3010efad781e68a16b22e32","abstract_canon_sha256":"28651952ea2372d7422e6450b56ae62ded30f8d4d9f863cbfff5ffaf1fbc2926"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:34:03.010065Z","signature_b64":"Aai/Yw+/lB6U//Rk4HxE+p/O7jjRykO96OwdzPR0MuStaH/Y5xxSTRUZurZpcpZCibr/owwT+uM27JrbRbUmDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afb649880196deb3a1b96915d2cab7938d1bb64def66f1e896a0c84a815a638a","last_reissued_at":"2026-07-05T05:34:03.009528Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:34:03.009528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Out-of-Distribution Performance on Document Image Classifiers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"David Kuang, Gordon Lim, Kevin Leach, Stefan Larson, Yutong Ai","submitted_at":"2022-10-14T01:24:21Z","abstract_excerpt":"The ability of a document classifier to handle inputs that are drawn from a distribution different from the training distribution is crucial for robust deployment and generalizability. The RVL-CDIP corpus is the de facto standard benchmark for document classification, yet to our knowledge all studies that use this corpus do not include evaluation on out-of-distribution documents. In this paper, we curate and release a new out-of-distribution benchmark for evaluating out-of-distribution performance for document classifiers. Our new out-of-distribution benchmark consists of two types of document"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.07448","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/2210.07448/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":"2210.07448","created_at":"2026-07-05T05:34:03.009596+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.07448v2","created_at":"2026-07-05T05:34:03.009596+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.07448","created_at":"2026-07-05T05:34:03.009596+00:00"},{"alias_kind":"pith_short_12","alias_value":"V63ETCABS3PL","created_at":"2026-07-05T05:34:03.009596+00:00"},{"alias_kind":"pith_short_16","alias_value":"V63ETCABS3PLHINZ","created_at":"2026-07-05T05:34:03.009596+00:00"},{"alias_kind":"pith_short_8","alias_value":"V63ETCAB","created_at":"2026-07-05T05:34:03.009596+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/V63ETCABS3PLHINZNEK5FSVXSO","json":"https://pith.science/pith/V63ETCABS3PLHINZNEK5FSVXSO.json","graph_json":"https://pith.science/api/pith-number/V63ETCABS3PLHINZNEK5FSVXSO/graph.json","events_json":"https://pith.science/api/pith-number/V63ETCABS3PLHINZNEK5FSVXSO/events.json","paper":"https://pith.science/paper/V63ETCAB"},"agent_actions":{"view_html":"https://pith.science/pith/V63ETCABS3PLHINZNEK5FSVXSO","download_json":"https://pith.science/pith/V63ETCABS3PLHINZNEK5FSVXSO.json","view_paper":"https://pith.science/paper/V63ETCAB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.07448&json=true","fetch_graph":"https://pith.science/api/pith-number/V63ETCABS3PLHINZNEK5FSVXSO/graph.json","fetch_events":"https://pith.science/api/pith-number/V63ETCABS3PLHINZNEK5FSVXSO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V63ETCABS3PLHINZNEK5FSVXSO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V63ETCABS3PLHINZNEK5FSVXSO/action/storage_attestation","attest_author":"https://pith.science/pith/V63ETCABS3PLHINZNEK5FSVXSO/action/author_attestation","sign_citation":"https://pith.science/pith/V63ETCABS3PLHINZNEK5FSVXSO/action/citation_signature","submit_replication":"https://pith.science/pith/V63ETCABS3PLHINZNEK5FSVXSO/action/replication_record"}},"created_at":"2026-07-05T05:34:03.009596+00:00","updated_at":"2026-07-05T05:34:03.009596+00:00"}