{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WMJCTDHDPUFCYR4WQPDFRXRQOW","short_pith_number":"pith:WMJCTDHD","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"},"canonical_sha256":"b312298ce37d0a2c479683c658de3075887a83171d2e44f7e87f2c55ef1eefd0","source":{"kind":"arxiv","id":"2507.08865","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.08865","created_at":"2026-07-05T11:35:59Z"},{"alias_kind":"arxiv_version","alias_value":"2507.08865v1","created_at":"2026-07-05T11:35:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08865","created_at":"2026-07-05T11:35:59Z"},{"alias_kind":"pith_short_12","alias_value":"WMJCTDHDPUFC","created_at":"2026-07-05T11:35:59Z"},{"alias_kind":"pith_short_16","alias_value":"WMJCTDHDPUFCYR4W","created_at":"2026-07-05T11:35:59Z"},{"alias_kind":"pith_short_8","alias_value":"WMJCTDHD","created_at":"2026-07-05T11:35:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WMJCTDHDPUFCYR4WQPDFRXRQOW","target":"record","payload":{"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"},"canonical_sha256":"b312298ce37d0a2c479683c658de3075887a83171d2e44f7e87f2c55ef1eefd0","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"},"source_kind":"arxiv","source_id":"2507.08865","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:35:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zTaJHAC0cDA2vo6PltXnrTJ8TmvpLVHpTBKPLe+DkfA0JgQbH8NTJpntnsjhRxF8KrgNSBDNS+8DvqCKmr7pBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T21:22:00.926101Z"},"content_sha256":"17d031850314cc147dc7706777d824c36a3118baeb742181f2fc324367db176a","schema_version":"1.0","event_id":"sha256:17d031850314cc147dc7706777d824c36a3118baeb742181f2fc324367db176a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WMJCTDHDPUFCYR4WQPDFRXRQOW","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:35:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gylekmUu3awoyEZ0RJ7WzQGB41SXiduMQj1WcTB1PCvA5quQsSP8kAl9TqlTN3CRNyMIlnkkxVPHaH3Yq4zJAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T21:22:00.927261Z"},"content_sha256":"84d58313ba33b6a7ba8f5187d2e33d0b83d4758e340c0bb19f666fd9ee30299b","schema_version":"1.0","event_id":"sha256:84d58313ba33b6a7ba8f5187d2e33d0b83d4758e340c0bb19f666fd9ee30299b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WMJCTDHDPUFCYR4WQPDFRXRQOW/bundle.json","state_url":"https://pith.science/pith/WMJCTDHDPUFCYR4WQPDFRXRQOW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WMJCTDHDPUFCYR4WQPDFRXRQOW/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T21:22:00Z","links":{"resolver":"https://pith.science/pith/WMJCTDHDPUFCYR4WQPDFRXRQOW","bundle":"https://pith.science/pith/WMJCTDHDPUFCYR4WQPDFRXRQOW/bundle.json","state":"https://pith.science/pith/WMJCTDHDPUFCYR4WQPDFRXRQOW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WMJCTDHDPUFCYR4WQPDFRXRQOW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WMJCTDHDPUFCYR4WQPDFRXRQOW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6488b71ce2d61efebd134c59e8807b773ee98e00aaee83844b44988a71d35af0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-09T14:40:40Z","title_canon_sha256":"20330c6f514b662c6415669fe87ea45bcfc103af3e0b49d4486750786d2fa154"},"schema_version":"1.0","source":{"id":"2507.08865","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.08865","created_at":"2026-07-05T11:35:59Z"},{"alias_kind":"arxiv_version","alias_value":"2507.08865v1","created_at":"2026-07-05T11:35:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08865","created_at":"2026-07-05T11:35:59Z"},{"alias_kind":"pith_short_12","alias_value":"WMJCTDHDPUFC","created_at":"2026-07-05T11:35:59Z"},{"alias_kind":"pith_short_16","alias_value":"WMJCTDHDPUFCYR4W","created_at":"2026-07-05T11:35:59Z"},{"alias_kind":"pith_short_8","alias_value":"WMJCTDHD","created_at":"2026-07-05T11:35:59Z"}],"graph_snapshots":[{"event_id":"sha256:84d58313ba33b6a7ba8f5187d2e33d0b83d4758e340c0bb19f666fd9ee30299b","target":"graph","created_at":"2026-07-05T11:35:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.08865/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dharshan Sampath, Javis AI Team: Amrendra Singh, Maulik Shah","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-09T14:40:40Z","title":"Spatial ModernBERT: Spatial-Aware Transformer for Table and Key-Value Extraction in Financial Documents at Scale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08865","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:17d031850314cc147dc7706777d824c36a3118baeb742181f2fc324367db176a","target":"record","created_at":"2026-07-05T11:35:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6488b71ce2d61efebd134c59e8807b773ee98e00aaee83844b44988a71d35af0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-09T14:40:40Z","title_canon_sha256":"20330c6f514b662c6415669fe87ea45bcfc103af3e0b49d4486750786d2fa154"},"schema_version":"1.0","source":{"id":"2507.08865","kind":"arxiv","version":1}},"canonical_sha256":"b312298ce37d0a2c479683c658de3075887a83171d2e44f7e87f2c55ef1eefd0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b312298ce37d0a2c479683c658de3075887a83171d2e44f7e87f2c55ef1eefd0","first_computed_at":"2026-07-05T11:35:59.602432Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:35:59.602432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RGmP2mbb/+O/rPVpQpeXldSZdv1hEBap42dKT8n0ksxq8JvvYxy6RyNyGZEOvfqJTU6btrNxM0jM8qXMLyliCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:35:59.602843Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.08865","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:17d031850314cc147dc7706777d824c36a3118baeb742181f2fc324367db176a","sha256:84d58313ba33b6a7ba8f5187d2e33d0b83d4758e340c0bb19f666fd9ee30299b"],"state_sha256":"6f7b78ea88f022b8d42f4d062b80b48a87a52e70a54e02e233e201301ba7d144"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HANVr2U4bqcqp/cw/ugpzZ3wZBxcczJJYty90VBlb8mff8a0V65EBar1tN4ka2FzfXVNuFANqgTc48pFDtVyCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T21:22:00.936527Z","bundle_sha256":"4a1722089d6f1946e1c3934c45c54c012dd5c1bca35637efb498f5c194341ede"}}