{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:C6WZO3DZWBH7RC2EVLTFSLHEJM","short_pith_number":"pith:C6WZO3DZ","schema_version":"1.0","canonical_sha256":"17ad976c79b04ff88b44aae6592ce44b0093f4b33e7d9f8e96f914561ace5281","source":{"kind":"arxiv","id":"2311.11856","version":1},"attestation_state":"computed","paper":{"title":"FATURA: A Multi-Layout Invoice Image Dataset for Document Analysis and Understanding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mahmoud Limam, Marwa Dhiaf, Yousri Kessentini","submitted_at":"2023-11-20T15:51:14Z","abstract_excerpt":"Document analysis and understanding models often require extensive annotated data to be trained. However, various document-related tasks extend beyond mere text transcription, requiring both textual content and precise bounding-box annotations to identify different document elements. Collecting such data becomes particularly challenging, especially in the context of invoices, where privacy concerns add an additional layer of complexity. In this paper, we introduce FATURA, a pivotal resource for researchers in the field of document analysis and understanding. FATURA is a highly diverse dataset "},"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":"2311.11856","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-20T15:51:14Z","cross_cats_sorted":[],"title_canon_sha256":"1fdfedaf668a350fd9c4dd9cdf4c3fbe4b4b0841ec24fce4546dec4746e8b07e","abstract_canon_sha256":"d362cb10721971f50a1610b3956af3df812101d97cb76c52db026738125f68fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:14:40.023981Z","signature_b64":"RSzyAGcgDnpxg6iyf2uVjzJAQKIHOsPNf9NK8whxUvtQGdM5juKO8bPhEizu56hX8G+YXr+FfUuN1cN64RCiBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17ad976c79b04ff88b44aae6592ce44b0093f4b33e7d9f8e96f914561ace5281","last_reissued_at":"2026-07-05T07:14:40.023581Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:14:40.023581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FATURA: A Multi-Layout Invoice Image Dataset for Document Analysis and Understanding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mahmoud Limam, Marwa Dhiaf, Yousri Kessentini","submitted_at":"2023-11-20T15:51:14Z","abstract_excerpt":"Document analysis and understanding models often require extensive annotated data to be trained. However, various document-related tasks extend beyond mere text transcription, requiring both textual content and precise bounding-box annotations to identify different document elements. Collecting such data becomes particularly challenging, especially in the context of invoices, where privacy concerns add an additional layer of complexity. In this paper, we introduce FATURA, a pivotal resource for researchers in the field of document analysis and understanding. FATURA is a highly diverse dataset "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.11856","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/2311.11856/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":"2311.11856","created_at":"2026-07-05T07:14:40.023639+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.11856v1","created_at":"2026-07-05T07:14:40.023639+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.11856","created_at":"2026-07-05T07:14:40.023639+00:00"},{"alias_kind":"pith_short_12","alias_value":"C6WZO3DZWBH7","created_at":"2026-07-05T07:14:40.023639+00:00"},{"alias_kind":"pith_short_16","alias_value":"C6WZO3DZWBH7RC2E","created_at":"2026-07-05T07:14:40.023639+00:00"},{"alias_kind":"pith_short_8","alias_value":"C6WZO3DZ","created_at":"2026-07-05T07:14:40.023639+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19100","citing_title":"AMALIA-VL: A Native European Portuguese Open-Source Vision and Language Model","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19100","citing_title":"AMALIA-VL: A Native European Portuguese Open-Source Vision and Language Model","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19100","citing_title":"AMALIA-VL: A Native European Portuguese Open-Source Vision and Language Model","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C6WZO3DZWBH7RC2EVLTFSLHEJM","json":"https://pith.science/pith/C6WZO3DZWBH7RC2EVLTFSLHEJM.json","graph_json":"https://pith.science/api/pith-number/C6WZO3DZWBH7RC2EVLTFSLHEJM/graph.json","events_json":"https://pith.science/api/pith-number/C6WZO3DZWBH7RC2EVLTFSLHEJM/events.json","paper":"https://pith.science/paper/C6WZO3DZ"},"agent_actions":{"view_html":"https://pith.science/pith/C6WZO3DZWBH7RC2EVLTFSLHEJM","download_json":"https://pith.science/pith/C6WZO3DZWBH7RC2EVLTFSLHEJM.json","view_paper":"https://pith.science/paper/C6WZO3DZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.11856&json=true","fetch_graph":"https://pith.science/api/pith-number/C6WZO3DZWBH7RC2EVLTFSLHEJM/graph.json","fetch_events":"https://pith.science/api/pith-number/C6WZO3DZWBH7RC2EVLTFSLHEJM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C6WZO3DZWBH7RC2EVLTFSLHEJM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C6WZO3DZWBH7RC2EVLTFSLHEJM/action/storage_attestation","attest_author":"https://pith.science/pith/C6WZO3DZWBH7RC2EVLTFSLHEJM/action/author_attestation","sign_citation":"https://pith.science/pith/C6WZO3DZWBH7RC2EVLTFSLHEJM/action/citation_signature","submit_replication":"https://pith.science/pith/C6WZO3DZWBH7RC2EVLTFSLHEJM/action/replication_record"}},"created_at":"2026-07-05T07:14:40.023639+00:00","updated_at":"2026-07-05T07:14:40.023639+00:00"}