{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ENVICIYCEUJZOQXWG7VRDRQZGH","short_pith_number":"pith:ENVICIYC","canonical_record":{"source":{"id":"2604.00003","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-09T02:09:02Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"3f95d96ea3322717039028554be1c982cc737fedc161c7075bc6c6c7c18ce6a6","abstract_canon_sha256":"d5603532fb814f4ce1bb6da1f5b524fcf318c80a9318a969322ffcef810937cb"},"schema_version":"1.0"},"canonical_sha256":"236a81230225139742f637eb11c61931ece80b38d05a9c3cda1ee74747f0e981","source":{"kind":"arxiv","id":"2604.00003","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.00003","created_at":"2026-05-25T02:01:18Z"},{"alias_kind":"arxiv_version","alias_value":"2604.00003v2","created_at":"2026-05-25T02:01:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.00003","created_at":"2026-05-25T02:01:18Z"},{"alias_kind":"pith_short_12","alias_value":"ENVICIYCEUJZ","created_at":"2026-05-25T02:01:18Z"},{"alias_kind":"pith_short_16","alias_value":"ENVICIYCEUJZOQXW","created_at":"2026-05-25T02:01:18Z"},{"alias_kind":"pith_short_8","alias_value":"ENVICIYC","created_at":"2026-05-25T02:01:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ENVICIYCEUJZOQXWG7VRDRQZGH","target":"record","payload":{"canonical_record":{"source":{"id":"2604.00003","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-09T02:09:02Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"3f95d96ea3322717039028554be1c982cc737fedc161c7075bc6c6c7c18ce6a6","abstract_canon_sha256":"d5603532fb814f4ce1bb6da1f5b524fcf318c80a9318a969322ffcef810937cb"},"schema_version":"1.0"},"canonical_sha256":"236a81230225139742f637eb11c61931ece80b38d05a9c3cda1ee74747f0e981","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:18.566365Z","signature_b64":"4WCWStKd44lW+M/SSOdZcHGMpM6YhDuvtZCxEP0ryhNycM7Z6hNGaQ3GK1fekq9jawSC4JHVLwgILE578lm1Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"236a81230225139742f637eb11c61931ece80b38d05a9c3cda1ee74747f0e981","last_reissued_at":"2026-05-25T02:01:18.565518Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:18.565518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.00003","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-25T02:01:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z6Yu6sYIxa42fLTKrZhnY0RhzOO+oJTgR8MYXWjWnFhH3pg8MDGUD0XJSeXtMZ7ZRdox/ynxDUXdrPOhvwteAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T01:10:10.090828Z"},"content_sha256":"4bdc4343f51556199318c8c41596707ed7dd16484dfdc2af12a13ddd1015ccc0","schema_version":"1.0","event_id":"sha256:4bdc4343f51556199318c8c41596707ed7dd16484dfdc2af12a13ddd1015ccc0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ENVICIYCEUJZOQXWG7VRDRQZGH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tabular PDF Information Extraction with Local LLMs and Layout-Aware Parsing: A Reliability Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Azhar Al Afghani, Kurnia Adi Cahyanto, Muhammad Anis Al Hilmi, Musfi Yuliadi, Neelansh Khare, Noel Framil Iglesias","submitted_at":"2026-03-09T02:09:02Z","abstract_excerpt":"Extracting structured information from academic PDF documents is non trivial: a single page typically combines free text metadata with tabular regions, exhibits cross program variation, and is susceptible to Unicode encoding artifacts that interfere with downstream parsing. This study evaluates the reliability of information extraction approaches for tabular PDF documents, using academic course registration documents (Kartu Rencana Studi or KRS) from Indonesian higher education as a case study. Three strategies are compared: LLM only, Hybrid Deterministic - LLM (regex & LLM), and a Camelot bas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.00003","kind":"arxiv","version":2},"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/2604.00003/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":"2026-05-25T02:01:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4BSjSUVks/z1gUopeHTvlMQb3PHC+JOfJmepBuK/YkwXrU+q64oF63FOf6GsA0jUF3j9wVLraVbmEOiwTlEUCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T01:10:10.091464Z"},"content_sha256":"723ef7e9e15c631628bf951d1cdd0fa8b92bf9bce0dc8380627f02b7bf481a68","schema_version":"1.0","event_id":"sha256:723ef7e9e15c631628bf951d1cdd0fa8b92bf9bce0dc8380627f02b7bf481a68"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ENVICIYCEUJZOQXWG7VRDRQZGH/bundle.json","state_url":"https://pith.science/pith/ENVICIYCEUJZOQXWG7VRDRQZGH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ENVICIYCEUJZOQXWG7VRDRQZGH/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":"2026-08-22T01:10:10Z","links":{"resolver":"https://pith.science/pith/ENVICIYCEUJZOQXWG7VRDRQZGH","bundle":"https://pith.science/pith/ENVICIYCEUJZOQXWG7VRDRQZGH/bundle.json","state":"https://pith.science/pith/ENVICIYCEUJZOQXWG7VRDRQZGH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ENVICIYCEUJZOQXWG7VRDRQZGH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ENVICIYCEUJZOQXWG7VRDRQZGH","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":"d5603532fb814f4ce1bb6da1f5b524fcf318c80a9318a969322ffcef810937cb","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-09T02:09:02Z","title_canon_sha256":"3f95d96ea3322717039028554be1c982cc737fedc161c7075bc6c6c7c18ce6a6"},"schema_version":"1.0","source":{"id":"2604.00003","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.00003","created_at":"2026-05-25T02:01:18Z"},{"alias_kind":"arxiv_version","alias_value":"2604.00003v2","created_at":"2026-05-25T02:01:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.00003","created_at":"2026-05-25T02:01:18Z"},{"alias_kind":"pith_short_12","alias_value":"ENVICIYCEUJZ","created_at":"2026-05-25T02:01:18Z"},{"alias_kind":"pith_short_16","alias_value":"ENVICIYCEUJZOQXW","created_at":"2026-05-25T02:01:18Z"},{"alias_kind":"pith_short_8","alias_value":"ENVICIYC","created_at":"2026-05-25T02:01:18Z"}],"graph_snapshots":[{"event_id":"sha256:723ef7e9e15c631628bf951d1cdd0fa8b92bf9bce0dc8380627f02b7bf481a68","target":"graph","created_at":"2026-05-25T02:01:18Z","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/2604.00003/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Extracting structured information from academic PDF documents is non trivial: a single page typically combines free text metadata with tabular regions, exhibits cross program variation, and is susceptible to Unicode encoding artifacts that interfere with downstream parsing. This study evaluates the reliability of information extraction approaches for tabular PDF documents, using academic course registration documents (Kartu Rencana Studi or KRS) from Indonesian higher education as a case study. Three strategies are compared: LLM only, Hybrid Deterministic - LLM (regex & LLM), and a Camelot bas","authors_text":"Azhar Al Afghani, Kurnia Adi Cahyanto, Muhammad Anis Al Hilmi, Musfi Yuliadi, Neelansh Khare, Noel Framil Iglesias","cross_cats":["cs.AI","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-09T02:09:02Z","title":"Tabular PDF Information Extraction with Local LLMs and Layout-Aware Parsing: A Reliability Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.00003","kind":"arxiv","version":2},"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":"sha256:4bdc4343f51556199318c8c41596707ed7dd16484dfdc2af12a13ddd1015ccc0","target":"record","created_at":"2026-05-25T02:01:18Z","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":"d5603532fb814f4ce1bb6da1f5b524fcf318c80a9318a969322ffcef810937cb","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-09T02:09:02Z","title_canon_sha256":"3f95d96ea3322717039028554be1c982cc737fedc161c7075bc6c6c7c18ce6a6"},"schema_version":"1.0","source":{"id":"2604.00003","kind":"arxiv","version":2}},"canonical_sha256":"236a81230225139742f637eb11c61931ece80b38d05a9c3cda1ee74747f0e981","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"236a81230225139742f637eb11c61931ece80b38d05a9c3cda1ee74747f0e981","first_computed_at":"2026-05-25T02:01:18.565518Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:01:18.565518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4WCWStKd44lW+M/SSOdZcHGMpM6YhDuvtZCxEP0ryhNycM7Z6hNGaQ3GK1fekq9jawSC4JHVLwgILE578lm1Ag==","signature_status":"signed_v1","signed_at":"2026-05-25T02:01:18.566365Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.00003","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4bdc4343f51556199318c8c41596707ed7dd16484dfdc2af12a13ddd1015ccc0","sha256:723ef7e9e15c631628bf951d1cdd0fa8b92bf9bce0dc8380627f02b7bf481a68"],"state_sha256":"393fc8e5485fbf3ed3f58b61c3257aeecaf59dfb0ee2d588fb2a77154df9146e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sa4PvyMDgPjaDMmIp2/oaQ+v2xmwLPl3Hbio31a9etQbCgPiYrBwJrSYDPun3Ze4FKg6fBkMMVTn4aU66faqAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T01:10:10.096801Z","bundle_sha256":"f4b05c59dbe6b527f1d50e66ea5776319a2676aafebf9c4370a9ee397f233c9e"}}