{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:UFXKGODZMBYDXHY2QDWBZATJKY","short_pith_number":"pith:UFXKGODZ","schema_version":"1.0","canonical_sha256":"a16ea3387960703b9f1a80ec1c82695627d81253a469209375858c7c7545d5ac","source":{"kind":"arxiv","id":"2206.11229","version":1},"attestation_state":"computed","paper":{"title":"Business Document Information Extraction: Towards Practical Benchmarks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.IR","authors_text":"Maty\\'a\\v{s} Skalick\\'y, Michal U\\v{r}i\\v{c}\\'a\\v{r}, Milan \\v{S}ulc, \\v{S}t\\v{e}p\\'an \\v{S}imsa","submitted_at":"2022-06-20T15:23:49Z","abstract_excerpt":"Information extraction from semi-structured documents is crucial for frictionless business-to-business (B2B) communication. While machine learning problems related to Document Information Extraction (IE) have been studied for decades, many common problem definitions and benchmarks do not reflect domain-specific aspects and practical needs for automating B2B document communication. We review the landscape of Document IE problems, datasets and benchmarks. We highlight the practical aspects missing in the common definitions and define the Key Information Localization and Extraction (KILE) and Lin"},"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":"2206.11229","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2022-06-20T15:23:49Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"d566ba48fcf5237f6616ce0c5e89eaf6404772f7192231918ccd80a6d93dbca9","abstract_canon_sha256":"12b41cbf0b889fcee31ccd84f4d5f5c8b3c978af50abf257fd4e1c52f93be20e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:34:10.399160Z","signature_b64":"Zdgytd2dbl8sArEjDNgZYtCaS/VdfDLhchVB9ipshxArlYGdfQ5FtEEQSrr1vv2ZLtYq1fhSa1Xboli7QtmADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a16ea3387960703b9f1a80ec1c82695627d81253a469209375858c7c7545d5ac","last_reissued_at":"2026-07-05T04:34:10.398745Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:34:10.398745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Business Document Information Extraction: Towards Practical Benchmarks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.IR","authors_text":"Maty\\'a\\v{s} Skalick\\'y, Michal U\\v{r}i\\v{c}\\'a\\v{r}, Milan \\v{S}ulc, \\v{S}t\\v{e}p\\'an \\v{S}imsa","submitted_at":"2022-06-20T15:23:49Z","abstract_excerpt":"Information extraction from semi-structured documents is crucial for frictionless business-to-business (B2B) communication. While machine learning problems related to Document Information Extraction (IE) have been studied for decades, many common problem definitions and benchmarks do not reflect domain-specific aspects and practical needs for automating B2B document communication. We review the landscape of Document IE problems, datasets and benchmarks. We highlight the practical aspects missing in the common definitions and define the Key Information Localization and Extraction (KILE) and Lin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.11229","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/2206.11229/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":"2206.11229","created_at":"2026-07-05T04:34:10.398802+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.11229v1","created_at":"2026-07-05T04:34:10.398802+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.11229","created_at":"2026-07-05T04:34:10.398802+00:00"},{"alias_kind":"pith_short_12","alias_value":"UFXKGODZMBYD","created_at":"2026-07-05T04:34:10.398802+00:00"},{"alias_kind":"pith_short_16","alias_value":"UFXKGODZMBYDXHY2","created_at":"2026-07-05T04:34:10.398802+00:00"},{"alias_kind":"pith_short_8","alias_value":"UFXKGODZ","created_at":"2026-07-05T04:34:10.398802+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/UFXKGODZMBYDXHY2QDWBZATJKY","json":"https://pith.science/pith/UFXKGODZMBYDXHY2QDWBZATJKY.json","graph_json":"https://pith.science/api/pith-number/UFXKGODZMBYDXHY2QDWBZATJKY/graph.json","events_json":"https://pith.science/api/pith-number/UFXKGODZMBYDXHY2QDWBZATJKY/events.json","paper":"https://pith.science/paper/UFXKGODZ"},"agent_actions":{"view_html":"https://pith.science/pith/UFXKGODZMBYDXHY2QDWBZATJKY","download_json":"https://pith.science/pith/UFXKGODZMBYDXHY2QDWBZATJKY.json","view_paper":"https://pith.science/paper/UFXKGODZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.11229&json=true","fetch_graph":"https://pith.science/api/pith-number/UFXKGODZMBYDXHY2QDWBZATJKY/graph.json","fetch_events":"https://pith.science/api/pith-number/UFXKGODZMBYDXHY2QDWBZATJKY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UFXKGODZMBYDXHY2QDWBZATJKY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UFXKGODZMBYDXHY2QDWBZATJKY/action/storage_attestation","attest_author":"https://pith.science/pith/UFXKGODZMBYDXHY2QDWBZATJKY/action/author_attestation","sign_citation":"https://pith.science/pith/UFXKGODZMBYDXHY2QDWBZATJKY/action/citation_signature","submit_replication":"https://pith.science/pith/UFXKGODZMBYDXHY2QDWBZATJKY/action/replication_record"}},"created_at":"2026-07-05T04:34:10.398802+00:00","updated_at":"2026-07-05T04:34:10.398802+00:00"}