{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WFKHDCWI3D7XGQEOKOIR2LXMEK","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":"b1fa0c719769db66da3cdc0df3a84479680f06eed1aaa3e7da30b64dd8b4df6a","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T16:54:42Z","title_canon_sha256":"b265bfd0d151630b09b2c3b0d09ee2ce0e74b7da664106d8f379b23f1da4f857"},"schema_version":"1.0","source":{"id":"2405.20245","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.20245","created_at":"2026-07-05T08:25:24Z"},{"alias_kind":"arxiv_version","alias_value":"2405.20245v1","created_at":"2026-07-05T08:25:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20245","created_at":"2026-07-05T08:25:24Z"},{"alias_kind":"pith_short_12","alias_value":"WFKHDCWI3D7X","created_at":"2026-07-05T08:25:24Z"},{"alias_kind":"pith_short_16","alias_value":"WFKHDCWI3D7XGQEO","created_at":"2026-07-05T08:25:24Z"},{"alias_kind":"pith_short_8","alias_value":"WFKHDCWI","created_at":"2026-07-05T08:25:24Z"}],"graph_snapshots":[{"event_id":"sha256:9ab71e83e7b384f15326f20427815b7c9364d0cee48c72b7025cdbfc571d12e7","target":"graph","created_at":"2026-07-05T08:25:24Z","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/2405.20245/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Business Document Information Extraction (BDIE) is the problem of transforming a blob of unstructured information (raw text, scanned documents, etc.) into a structured format that downstream systems can parse and use. It has two main tasks: Key-Information Extraction (KIE) and Line Items Recognition (LIR). In this paper, we argue that BDIE is best modeled as a Tool Use problem, where the tools are these downstream systems. We then present Retrieval Augmented Structured Generation (RASG), a novel general framework for BDIE that achieves state of the art (SOTA) results on both KIE and LIR tasks ","authors_text":"Franz Louis Cesista, Jason Kim, Paolo Acilo, Rui Aguiar","cross_cats":["cs.AI","cs.IR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T16:54:42Z","title":"Retrieval Augmented Structured Generation: Business Document Information Extraction As Tool Use"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20245","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":"sha256:257824a512ad8851c39988d4019a59ab6a87374af553ea34fac6e7975e24c136","target":"record","created_at":"2026-07-05T08:25:24Z","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":"b1fa0c719769db66da3cdc0df3a84479680f06eed1aaa3e7da30b64dd8b4df6a","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T16:54:42Z","title_canon_sha256":"b265bfd0d151630b09b2c3b0d09ee2ce0e74b7da664106d8f379b23f1da4f857"},"schema_version":"1.0","source":{"id":"2405.20245","kind":"arxiv","version":1}},"canonical_sha256":"b154718ac8d8ff73408e53911d2eec2280f2f36d6426f167be4a3f321badde77","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b154718ac8d8ff73408e53911d2eec2280f2f36d6426f167be4a3f321badde77","first_computed_at":"2026-07-05T08:25:24.142466Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:24.142466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a/T0aFb/b9LCjae+7j1OnBXYie+ofDz6kY2C97HDpQALsJaZ4MJhrv5zNHHBZ5JnwODrLHoTjviTllqmUHutDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:24.142974Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.20245","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:257824a512ad8851c39988d4019a59ab6a87374af553ea34fac6e7975e24c136","sha256:9ab71e83e7b384f15326f20427815b7c9364d0cee48c72b7025cdbfc571d12e7"],"state_sha256":"c2d4cdbb6a936fef25304f26a17a1e4ea91e7f4992e9e5f01931af4aaf2ea768"}