{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QR3K53D72MTWXW66P4ABGAUTZ6","short_pith_number":"pith:QR3K53D7","schema_version":"1.0","canonical_sha256":"8476aeec7fd3276bdbde7f00130293cf819e55f17999b0728247e0ae09904cfb","source":{"kind":"arxiv","id":"2301.12394","version":1},"attestation_state":"computed","paper":{"title":"DocILE 2023 Teaser: Document Information Localization and Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ahmed Hamdi, Maty\\'a\\v{s} Skalick\\'y, Milan \\v{S}ulc, \\v{S}t\\v{e}p\\'an \\v{S}imsa, Yash Patel","submitted_at":"2023-01-29T09:08:58Z","abstract_excerpt":"The lack of data for information extraction (IE) from semi-structured business documents is a real problem for the IE community. Publications relying on large-scale datasets use only proprietary, unpublished data due to the sensitive nature of such documents. Publicly available datasets are mostly small and domain-specific. The absence of a large-scale public dataset or benchmark hinders the reproducibility and cross-evaluation of published methods. The DocILE 2023 competition, hosted as a lab at the CLEF 2023 conference and as an ICDAR 2023 competition, will run the first major benchmark for "},"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":"2301.12394","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-29T09:08:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d6c1cda509e76f203d55b1be7557d5ed85c52c844e53c7ec522c21e4dca88214","abstract_canon_sha256":"f112d2332e21dcac98c8a3e7747afd3a8fa698ab2278ebb85eb96619e1b5b274"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:36:53.773340Z","signature_b64":"iZgbvgllN3aySUruamQ3zg1GKwI9UD8VjMkRXpVkDwd0IfZChIWqcOyjEqcqHVNDqZkDZQ+iAwSMRqXGv2x6Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8476aeec7fd3276bdbde7f00130293cf819e55f17999b0728247e0ae09904cfb","last_reissued_at":"2026-07-05T05:36:53.772772Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:36:53.772772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DocILE 2023 Teaser: Document Information Localization and Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ahmed Hamdi, Maty\\'a\\v{s} Skalick\\'y, Milan \\v{S}ulc, \\v{S}t\\v{e}p\\'an \\v{S}imsa, Yash Patel","submitted_at":"2023-01-29T09:08:58Z","abstract_excerpt":"The lack of data for information extraction (IE) from semi-structured business documents is a real problem for the IE community. Publications relying on large-scale datasets use only proprietary, unpublished data due to the sensitive nature of such documents. Publicly available datasets are mostly small and domain-specific. The absence of a large-scale public dataset or benchmark hinders the reproducibility and cross-evaluation of published methods. The DocILE 2023 competition, hosted as a lab at the CLEF 2023 conference and as an ICDAR 2023 competition, will run the first major benchmark for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.12394","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/2301.12394/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":"2301.12394","created_at":"2026-07-05T05:36:53.772866+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.12394v1","created_at":"2026-07-05T05:36:53.772866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.12394","created_at":"2026-07-05T05:36:53.772866+00:00"},{"alias_kind":"pith_short_12","alias_value":"QR3K53D72MTW","created_at":"2026-07-05T05:36:53.772866+00:00"},{"alias_kind":"pith_short_16","alias_value":"QR3K53D72MTWXW66","created_at":"2026-07-05T05:36:53.772866+00:00"},{"alias_kind":"pith_short_8","alias_value":"QR3K53D7","created_at":"2026-07-05T05:36:53.772866+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/QR3K53D72MTWXW66P4ABGAUTZ6","json":"https://pith.science/pith/QR3K53D72MTWXW66P4ABGAUTZ6.json","graph_json":"https://pith.science/api/pith-number/QR3K53D72MTWXW66P4ABGAUTZ6/graph.json","events_json":"https://pith.science/api/pith-number/QR3K53D72MTWXW66P4ABGAUTZ6/events.json","paper":"https://pith.science/paper/QR3K53D7"},"agent_actions":{"view_html":"https://pith.science/pith/QR3K53D72MTWXW66P4ABGAUTZ6","download_json":"https://pith.science/pith/QR3K53D72MTWXW66P4ABGAUTZ6.json","view_paper":"https://pith.science/paper/QR3K53D7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.12394&json=true","fetch_graph":"https://pith.science/api/pith-number/QR3K53D72MTWXW66P4ABGAUTZ6/graph.json","fetch_events":"https://pith.science/api/pith-number/QR3K53D72MTWXW66P4ABGAUTZ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QR3K53D72MTWXW66P4ABGAUTZ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QR3K53D72MTWXW66P4ABGAUTZ6/action/storage_attestation","attest_author":"https://pith.science/pith/QR3K53D72MTWXW66P4ABGAUTZ6/action/author_attestation","sign_citation":"https://pith.science/pith/QR3K53D72MTWXW66P4ABGAUTZ6/action/citation_signature","submit_replication":"https://pith.science/pith/QR3K53D72MTWXW66P4ABGAUTZ6/action/replication_record"}},"created_at":"2026-07-05T05:36:53.772866+00:00","updated_at":"2026-07-05T05:36:53.772866+00:00"}