{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:V3HO4VUB2KBAHM5HNWXSWAENQI","short_pith_number":"pith:V3HO4VUB","canonical_record":{"source":{"id":"2607.24745","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-08T07:43:02Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"ae18a88a6447c9c33f82f16850497e9a7a97ff2cd0b57e4090fb521b533b6a60","abstract_canon_sha256":"648c24cf7cc53847c1a6a0a010b50986b6c4599a517b52243ae5674a8e7019ba"},"schema_version":"1.0"},"canonical_sha256":"aeceee5681d28203b3a76daf2b008d822a14d2f1922fb70e9666ead0ee20b739","source":{"kind":"arxiv","id":"2607.24745","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.24745","created_at":"2026-07-29T00:24:41Z"},{"alias_kind":"arxiv_version","alias_value":"2607.24745v1","created_at":"2026-07-29T00:24:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24745","created_at":"2026-07-29T00:24:41Z"},{"alias_kind":"pith_short_12","alias_value":"V3HO4VUB2KBA","created_at":"2026-07-29T00:24:41Z"},{"alias_kind":"pith_short_16","alias_value":"V3HO4VUB2KBAHM5H","created_at":"2026-07-29T00:24:41Z"},{"alias_kind":"pith_short_8","alias_value":"V3HO4VUB","created_at":"2026-07-29T00:24:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:V3HO4VUB2KBAHM5HNWXSWAENQI","target":"record","payload":{"canonical_record":{"source":{"id":"2607.24745","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-08T07:43:02Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"ae18a88a6447c9c33f82f16850497e9a7a97ff2cd0b57e4090fb521b533b6a60","abstract_canon_sha256":"648c24cf7cc53847c1a6a0a010b50986b6c4599a517b52243ae5674a8e7019ba"},"schema_version":"1.0"},"canonical_sha256":"aeceee5681d28203b3a76daf2b008d822a14d2f1922fb70e9666ead0ee20b739","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T00:24:41.796300Z","signature_b64":"iieu4TSILPFGPsET/Hojy4E3ILIx2oWbxo3/Ap2K8AWZU/a8uiaBAOLSPPpvNIljm2Mt+nKKo//mpzEIKCLGBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aeceee5681d28203b3a76daf2b008d822a14d2f1922fb70e9666ead0ee20b739","last_reissued_at":"2026-07-29T00:24:41.795358Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T00:24:41.795358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.24745","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":"2026-07-29T00:24:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xr5mjpS6UUnWzF4UzcYJB01Q6ORT4CS3PYLhmFE3VZ8rbUx2vNEyaTvyWCLfqnIH8cr4a5EtNY92YJzxUn+eCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:00:04.854941Z"},"content_sha256":"bb7af7505668de6f4851cc0315fa8149cd48fe793beac19633fe9949abffb437","schema_version":"1.0","event_id":"sha256:bb7af7505668de6f4851cc0315fa8149cd48fe793beac19633fe9949abffb437"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:V3HO4VUB2KBAHM5HNWXSWAENQI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DocAnnot -- Accelerating the Creation of Key Information Extraction Datasets with GenAI-Powered Auto-annotation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.IR","authors_text":"Goutham Vignesh, Harikrishnan P M, Siddartha Reddy, Varun V, Vishal Vaddina","submitted_at":"2026-05-08T07:43:02Z","abstract_excerpt":"Key Information Extraction (KIE) is vital for many document applications, but creating training datasets is traditionally a time-consuming manual process. We introduce DocAnnot, a framework that significantly accelerates KIE dataset generation. DocAnnot leverages a Large Vision Language Model (LVLM) for label value extraction, OCR for text/bounding box detection, and a novel Spatially Informed Contextual Matching (SICM) algorithm. SICM improves label-value association by combining spatial relationships and proximity analysis with textual matching. We evaluate our framework on the CORD and SROI"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24745","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/2607.24745/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":"2026-07-29T00:24:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z37L6hj6z0ANLjjDue1lVeuC//mhaCw9aDqRccZ0e+4HSt6TY4Z/HZn4SFs3DcoJQpT9uAAVnSZFBVA3rkv5CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:00:04.855800Z"},"content_sha256":"af0022938cdcf3fd9a765b37402ecf1e51252bc78715f2670d011d928e125b2c","schema_version":"1.0","event_id":"sha256:af0022938cdcf3fd9a765b37402ecf1e51252bc78715f2670d011d928e125b2c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V3HO4VUB2KBAHM5HNWXSWAENQI/bundle.json","state_url":"https://pith.science/pith/V3HO4VUB2KBAHM5HNWXSWAENQI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V3HO4VUB2KBAHM5HNWXSWAENQI/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":"2026-08-06T16:00:04Z","links":{"resolver":"https://pith.science/pith/V3HO4VUB2KBAHM5HNWXSWAENQI","bundle":"https://pith.science/pith/V3HO4VUB2KBAHM5HNWXSWAENQI/bundle.json","state":"https://pith.science/pith/V3HO4VUB2KBAHM5HNWXSWAENQI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V3HO4VUB2KBAHM5HNWXSWAENQI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:V3HO4VUB2KBAHM5HNWXSWAENQI","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":"648c24cf7cc53847c1a6a0a010b50986b6c4599a517b52243ae5674a8e7019ba","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-08T07:43:02Z","title_canon_sha256":"ae18a88a6447c9c33f82f16850497e9a7a97ff2cd0b57e4090fb521b533b6a60"},"schema_version":"1.0","source":{"id":"2607.24745","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.24745","created_at":"2026-07-29T00:24:41Z"},{"alias_kind":"arxiv_version","alias_value":"2607.24745v1","created_at":"2026-07-29T00:24:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24745","created_at":"2026-07-29T00:24:41Z"},{"alias_kind":"pith_short_12","alias_value":"V3HO4VUB2KBA","created_at":"2026-07-29T00:24:41Z"},{"alias_kind":"pith_short_16","alias_value":"V3HO4VUB2KBAHM5H","created_at":"2026-07-29T00:24:41Z"},{"alias_kind":"pith_short_8","alias_value":"V3HO4VUB","created_at":"2026-07-29T00:24:41Z"}],"graph_snapshots":[{"event_id":"sha256:af0022938cdcf3fd9a765b37402ecf1e51252bc78715f2670d011d928e125b2c","target":"graph","created_at":"2026-07-29T00:24:41Z","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/2607.24745/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Key Information Extraction (KIE) is vital for many document applications, but creating training datasets is traditionally a time-consuming manual process. We introduce DocAnnot, a framework that significantly accelerates KIE dataset generation. DocAnnot leverages a Large Vision Language Model (LVLM) for label value extraction, OCR for text/bounding box detection, and a novel Spatially Informed Contextual Matching (SICM) algorithm. SICM improves label-value association by combining spatial relationships and proximity analysis with textual matching. We evaluate our framework on the CORD and SROI","authors_text":"Goutham Vignesh, Harikrishnan P M, Siddartha Reddy, Varun V, Vishal Vaddina","cross_cats":["cs.AI","cs.CL","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-08T07:43:02Z","title":"DocAnnot -- Accelerating the Creation of Key Information Extraction Datasets with GenAI-Powered Auto-annotation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24745","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:bb7af7505668de6f4851cc0315fa8149cd48fe793beac19633fe9949abffb437","target":"record","created_at":"2026-07-29T00:24:41Z","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":"648c24cf7cc53847c1a6a0a010b50986b6c4599a517b52243ae5674a8e7019ba","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-08T07:43:02Z","title_canon_sha256":"ae18a88a6447c9c33f82f16850497e9a7a97ff2cd0b57e4090fb521b533b6a60"},"schema_version":"1.0","source":{"id":"2607.24745","kind":"arxiv","version":1}},"canonical_sha256":"aeceee5681d28203b3a76daf2b008d822a14d2f1922fb70e9666ead0ee20b739","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aeceee5681d28203b3a76daf2b008d822a14d2f1922fb70e9666ead0ee20b739","first_computed_at":"2026-07-29T00:24:41.795358Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-29T00:24:41.795358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iieu4TSILPFGPsET/Hojy4E3ILIx2oWbxo3/Ap2K8AWZU/a8uiaBAOLSPPpvNIljm2Mt+nKKo//mpzEIKCLGBQ==","signature_status":"signed_v1","signed_at":"2026-07-29T00:24:41.796300Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.24745","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb7af7505668de6f4851cc0315fa8149cd48fe793beac19633fe9949abffb437","sha256:af0022938cdcf3fd9a765b37402ecf1e51252bc78715f2670d011d928e125b2c"],"state_sha256":"b8937eb84fdc8df78cb7208658ec483d193c4d5840f73f613ec6b3b02dba7ace"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YpXp0nB1d3n1QBAF4HIM85GAyLJgGWP9ndbdEnAvGHOoB18HvwlFpEUhYTAyes5B5g3oiB/0oZ/XXaQvLZF7Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T16:00:04.864012Z","bundle_sha256":"19e9eea2bd37f474f10213803817f95332f64edca9b29adf361bef691191eb7f"}}