{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WMJCTDHDPUFCYR4WQPDFRXRQOW","short_pith_number":"pith:WMJCTDHD","schema_version":"1.0","canonical_sha256":"b312298ce37d0a2c479683c658de3075887a83171d2e44f7e87f2c55ef1eefd0","source":{"kind":"arxiv","id":"2507.08865","version":1},"attestation_state":"computed","paper":{"title":"Spatial ModernBERT: Spatial-Aware Transformer for Table and Key-Value Extraction in Financial Documents at Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dharshan Sampath, Javis AI Team: Amrendra Singh, Maulik Shah","submitted_at":"2025-07-09T14:40:40Z","abstract_excerpt":"Extracting tables and key-value pairs from financial documents is essential for business workflows such as auditing, data analytics, and automated invoice processing. In this work, we introduce Spatial ModernBERT-a transformer-based model augmented with spatial embeddings-to accurately detect and extract tabular data and key-value fields from complex financial documents. We cast the extraction task as token classification across three heads: (1) Label Head, classifying each token as a label (e.g., PO Number, PO Date, Item Description, Quantity, Base Cost, MRP, etc.); (2) Column Head, predictin"},"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":"2507.08865","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-09T14:40:40Z","cross_cats_sorted":[],"title_canon_sha256":"20330c6f514b662c6415669fe87ea45bcfc103af3e0b49d4486750786d2fa154","abstract_canon_sha256":"6488b71ce2d61efebd134c59e8807b773ee98e00aaee83844b44988a71d35af0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:59.602843Z","signature_b64":"RGmP2mbb/+O/rPVpQpeXldSZdv1hEBap42dKT8n0ksxq8JvvYxy6RyNyGZEOvfqJTU6btrNxM0jM8qXMLyliCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b312298ce37d0a2c479683c658de3075887a83171d2e44f7e87f2c55ef1eefd0","last_reissued_at":"2026-07-05T11:35:59.602432Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:59.602432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spatial ModernBERT: Spatial-Aware Transformer for Table and Key-Value Extraction in Financial Documents at Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dharshan Sampath, Javis AI Team: Amrendra Singh, Maulik Shah","submitted_at":"2025-07-09T14:40:40Z","abstract_excerpt":"Extracting tables and key-value pairs from financial documents is essential for business workflows such as auditing, data analytics, and automated invoice processing. In this work, we introduce Spatial ModernBERT-a transformer-based model augmented with spatial embeddings-to accurately detect and extract tabular data and key-value fields from complex financial documents. We cast the extraction task as token classification across three heads: (1) Label Head, classifying each token as a label (e.g., PO Number, PO Date, Item Description, Quantity, Base Cost, MRP, etc.); (2) Column Head, predictin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08865","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/2507.08865/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":"2507.08865","created_at":"2026-07-05T11:35:59.602491+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.08865v1","created_at":"2026-07-05T11:35:59.602491+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08865","created_at":"2026-07-05T11:35:59.602491+00:00"},{"alias_kind":"pith_short_12","alias_value":"WMJCTDHDPUFC","created_at":"2026-07-05T11:35:59.602491+00:00"},{"alias_kind":"pith_short_16","alias_value":"WMJCTDHDPUFCYR4W","created_at":"2026-07-05T11:35:59.602491+00:00"},{"alias_kind":"pith_short_8","alias_value":"WMJCTDHD","created_at":"2026-07-05T11:35:59.602491+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/WMJCTDHDPUFCYR4WQPDFRXRQOW","json":"https://pith.science/pith/WMJCTDHDPUFCYR4WQPDFRXRQOW.json","graph_json":"https://pith.science/api/pith-number/WMJCTDHDPUFCYR4WQPDFRXRQOW/graph.json","events_json":"https://pith.science/api/pith-number/WMJCTDHDPUFCYR4WQPDFRXRQOW/events.json","paper":"https://pith.science/paper/WMJCTDHD"},"agent_actions":{"view_html":"https://pith.science/pith/WMJCTDHDPUFCYR4WQPDFRXRQOW","download_json":"https://pith.science/pith/WMJCTDHDPUFCYR4WQPDFRXRQOW.json","view_paper":"https://pith.science/paper/WMJCTDHD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.08865&json=true","fetch_graph":"https://pith.science/api/pith-number/WMJCTDHDPUFCYR4WQPDFRXRQOW/graph.json","fetch_events":"https://pith.science/api/pith-number/WMJCTDHDPUFCYR4WQPDFRXRQOW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WMJCTDHDPUFCYR4WQPDFRXRQOW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WMJCTDHDPUFCYR4WQPDFRXRQOW/action/storage_attestation","attest_author":"https://pith.science/pith/WMJCTDHDPUFCYR4WQPDFRXRQOW/action/author_attestation","sign_citation":"https://pith.science/pith/WMJCTDHDPUFCYR4WQPDFRXRQOW/action/citation_signature","submit_replication":"https://pith.science/pith/WMJCTDHDPUFCYR4WQPDFRXRQOW/action/replication_record"}},"created_at":"2026-07-05T11:35:59.602491+00:00","updated_at":"2026-07-05T11:35:59.602491+00:00"}