{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:DLVQAEOQCNJBSHCPLMFITNS6HO","short_pith_number":"pith:DLVQAEOQ","canonical_record":{"source":{"id":"2506.11156","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-11T16:03:01Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"1ab907fe0b888ca867e018e930ca1ec27a4e696cec1f47c5ceb7f81faee27f6a","abstract_canon_sha256":"6afa394e6835372848043503a0c82dc053c76d155d713bb445cb2be1758969a5"},"schema_version":"1.0"},"canonical_sha256":"1aeb0011d01352191c4f5b0a89b65e3b920106ce1b33cb31817ea4bdabc0eb1a","source":{"kind":"arxiv","id":"2506.11156","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11156","created_at":"2026-07-05T11:21:00Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11156v1","created_at":"2026-07-05T11:21:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11156","created_at":"2026-07-05T11:21:00Z"},{"alias_kind":"pith_short_12","alias_value":"DLVQAEOQCNJB","created_at":"2026-07-05T11:21:00Z"},{"alias_kind":"pith_short_16","alias_value":"DLVQAEOQCNJBSHCP","created_at":"2026-07-05T11:21:00Z"},{"alias_kind":"pith_short_8","alias_value":"DLVQAEOQ","created_at":"2026-07-05T11:21:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:DLVQAEOQCNJBSHCPLMFITNS6HO","target":"record","payload":{"canonical_record":{"source":{"id":"2506.11156","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-11T16:03:01Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"1ab907fe0b888ca867e018e930ca1ec27a4e696cec1f47c5ceb7f81faee27f6a","abstract_canon_sha256":"6afa394e6835372848043503a0c82dc053c76d155d713bb445cb2be1758969a5"},"schema_version":"1.0"},"canonical_sha256":"1aeb0011d01352191c4f5b0a89b65e3b920106ce1b33cb31817ea4bdabc0eb1a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:00.433963Z","signature_b64":"70Fily103GpFPQbRB5PXQxBSmO4urqF3r38TrdBMuzHCsj8yk3/wZdnsbh1aiFHYUIIxzXK9pXEYWO7Jtp5MDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1aeb0011d01352191c4f5b0a89b65e3b920106ce1b33cb31817ea4bdabc0eb1a","last_reissued_at":"2026-07-05T11:21:00.433486Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:00.433486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.11156","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":"2026-07-05T11:21:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vKqpTvkNhFh9PCqlA68q2PvEgsPFAaKf2RkIoHnWyAPbj3Vfb9NxaNHvfNrsUZZWm6RSyhfDYckZwHbIBMOoAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:34:50.255904Z"},"content_sha256":"d31d1f56066c58166ca5033618a5427f5ada14d3a51bcbd72c3ae4b6bbc8d128","schema_version":"1.0","event_id":"sha256:d31d1f56066c58166ca5033618a5427f5ada14d3a51bcbd72c3ae4b6bbc8d128"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:DLVQAEOQCNJBSHCPLMFITNS6HO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Digitization of Document and Information Extraction using OCR","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CV","authors_text":"Rasha Sinha, Rekha B S","submitted_at":"2025-06-11T16:03:01Z","abstract_excerpt":"Retrieving accurate details from documents is a crucial task, especially when handling a combination of scanned images and native digital formats. This document presents a combined framework for text extraction that merges Optical Character Recognition (OCR) techniques with Large Language Models (LLMs) to deliver structured outputs enriched by contextual understanding and confidence indicators. Scanned files are processed using OCR engines, while digital files are interpreted through layout-aware libraries. The extracted raw text is subsequently analyzed by an LLM to identify key-value pairs a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11156","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/2506.11156/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":"2026-07-05T11:21:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PaHu7y6f/SyAve2dUVl7jJQjPBAmw/c3FRvCvcqNlPmY1CQf6XO1EhpWq/dykDjNtbOMX/4TuJY9o6hBVisADg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:34:50.256409Z"},"content_sha256":"ce8afaaa96542984704ae92be76bfd339ff0d11ecb94c1103386b0b90bc3dc83","schema_version":"1.0","event_id":"sha256:ce8afaaa96542984704ae92be76bfd339ff0d11ecb94c1103386b0b90bc3dc83"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DLVQAEOQCNJBSHCPLMFITNS6HO/bundle.json","state_url":"https://pith.science/pith/DLVQAEOQCNJBSHCPLMFITNS6HO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DLVQAEOQCNJBSHCPLMFITNS6HO/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":"2026-08-08T18:34:50Z","links":{"resolver":"https://pith.science/pith/DLVQAEOQCNJBSHCPLMFITNS6HO","bundle":"https://pith.science/pith/DLVQAEOQCNJBSHCPLMFITNS6HO/bundle.json","state":"https://pith.science/pith/DLVQAEOQCNJBSHCPLMFITNS6HO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DLVQAEOQCNJBSHCPLMFITNS6HO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DLVQAEOQCNJBSHCPLMFITNS6HO","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":"6afa394e6835372848043503a0c82dc053c76d155d713bb445cb2be1758969a5","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-11T16:03:01Z","title_canon_sha256":"1ab907fe0b888ca867e018e930ca1ec27a4e696cec1f47c5ceb7f81faee27f6a"},"schema_version":"1.0","source":{"id":"2506.11156","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11156","created_at":"2026-07-05T11:21:00Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11156v1","created_at":"2026-07-05T11:21:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11156","created_at":"2026-07-05T11:21:00Z"},{"alias_kind":"pith_short_12","alias_value":"DLVQAEOQCNJB","created_at":"2026-07-05T11:21:00Z"},{"alias_kind":"pith_short_16","alias_value":"DLVQAEOQCNJBSHCP","created_at":"2026-07-05T11:21:00Z"},{"alias_kind":"pith_short_8","alias_value":"DLVQAEOQ","created_at":"2026-07-05T11:21:00Z"}],"graph_snapshots":[{"event_id":"sha256:ce8afaaa96542984704ae92be76bfd339ff0d11ecb94c1103386b0b90bc3dc83","target":"graph","created_at":"2026-07-05T11:21:00Z","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/2506.11156/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieving accurate details from documents is a crucial task, especially when handling a combination of scanned images and native digital formats. This document presents a combined framework for text extraction that merges Optical Character Recognition (OCR) techniques with Large Language Models (LLMs) to deliver structured outputs enriched by contextual understanding and confidence indicators. Scanned files are processed using OCR engines, while digital files are interpreted through layout-aware libraries. The extracted raw text is subsequently analyzed by an LLM to identify key-value pairs a","authors_text":"Rasha Sinha, Rekha B S","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-11T16:03:01Z","title":"Digitization of Document and Information Extraction using OCR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11156","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:d31d1f56066c58166ca5033618a5427f5ada14d3a51bcbd72c3ae4b6bbc8d128","target":"record","created_at":"2026-07-05T11:21:00Z","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":"6afa394e6835372848043503a0c82dc053c76d155d713bb445cb2be1758969a5","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-11T16:03:01Z","title_canon_sha256":"1ab907fe0b888ca867e018e930ca1ec27a4e696cec1f47c5ceb7f81faee27f6a"},"schema_version":"1.0","source":{"id":"2506.11156","kind":"arxiv","version":1}},"canonical_sha256":"1aeb0011d01352191c4f5b0a89b65e3b920106ce1b33cb31817ea4bdabc0eb1a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1aeb0011d01352191c4f5b0a89b65e3b920106ce1b33cb31817ea4bdabc0eb1a","first_computed_at":"2026-07-05T11:21:00.433486Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:00.433486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"70Fily103GpFPQbRB5PXQxBSmO4urqF3r38TrdBMuzHCsj8yk3/wZdnsbh1aiFHYUIIxzXK9pXEYWO7Jtp5MDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:00.433963Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.11156","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d31d1f56066c58166ca5033618a5427f5ada14d3a51bcbd72c3ae4b6bbc8d128","sha256:ce8afaaa96542984704ae92be76bfd339ff0d11ecb94c1103386b0b90bc3dc83"],"state_sha256":"28514ad64ada6cbb16bde2bf336ee268d27d1a5ba83611c1393549c86d06f87f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V6JZh2upLoYCnnpCEfSEdXYF7cgyrB8Js4UuDYGwppkCwVpvKtLFPhpynPAyP2aPX0sLYfB7lSx5lJZdlXOVAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T18:34:50.260418Z","bundle_sha256":"7943bb362c78dfcac4ae110d2e26dc2b8e65faacd32691f4783e68627e4f05c7"}}