{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BN4WUGDJIUQ5IKRJLOCY3FSIZ3","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":"eff32d00ae42bda4d9c449b9428e96aa45141a94972512a26b0862b24c29c5df","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-31T18:33:39Z","title_canon_sha256":"170bc6cef3aa929493a4e71ce290c6dbdf0d96d5be3f5018e9c3131db1e9536f"},"schema_version":"1.0","source":{"id":"2506.00664","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00664","created_at":"2026-07-05T11:13:38Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00664v1","created_at":"2026-07-05T11:13:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00664","created_at":"2026-07-05T11:13:38Z"},{"alias_kind":"pith_short_12","alias_value":"BN4WUGDJIUQ5","created_at":"2026-07-05T11:13:38Z"},{"alias_kind":"pith_short_16","alias_value":"BN4WUGDJIUQ5IKRJ","created_at":"2026-07-05T11:13:38Z"},{"alias_kind":"pith_short_8","alias_value":"BN4WUGDJ","created_at":"2026-07-05T11:13:38Z"}],"graph_snapshots":[{"event_id":"sha256:49c004b551479e8c746800894867694042ad7a87b2b49b282c287229bc01692e","target":"graph","created_at":"2026-07-05T11:13:38Z","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/2506.00664/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Ontologies are pivotal for structuring knowledge bases to enhance question answering (QA) systems powered by Large Language Models (LLMs). However, traditional ontology creation relies on manual efforts by domain experts, a process that is time intensive, error prone, and impractical for large, dynamic knowledge domains. This paper introduces OntoRAG, an automated pipeline designed to derive ontologies from unstructured knowledge bases, with a focus on electrical relay documents. OntoRAG integrates advanced techniques, including web scraping, PDF parsing, hybrid chunking, information extractio","authors_text":"Mayukha Pal, Owais Ahmad Lone, Yash Tiwari","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-31T18:33:39Z","title":"OntoRAG: Enhancing Question-Answering through Automated Ontology Derivation from Unstructured Knowledge Bases"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00664","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":"sha256:0e938cc2c7aa0c5d950987c281d6ebffd03b211acdfe8d27d650293e8db5ef2a","target":"record","created_at":"2026-07-05T11:13:38Z","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":"eff32d00ae42bda4d9c449b9428e96aa45141a94972512a26b0862b24c29c5df","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-31T18:33:39Z","title_canon_sha256":"170bc6cef3aa929493a4e71ce290c6dbdf0d96d5be3f5018e9c3131db1e9536f"},"schema_version":"1.0","source":{"id":"2506.00664","kind":"arxiv","version":1}},"canonical_sha256":"0b796a18694521d42a295b858d9648ced5f2050d30da4b312970cb78b524dc62","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b796a18694521d42a295b858d9648ced5f2050d30da4b312970cb78b524dc62","first_computed_at":"2026-07-05T11:13:38.248980Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:38.248980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NMnyd43Ldp1iDp/VGBUQMQzT7T/hgz3I7fpVHKmNPdPrZ2Q03g6x490aGf9tn6wMVCmtRE3QAPAZKv6xT2uICw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:38.249405Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00664","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e938cc2c7aa0c5d950987c281d6ebffd03b211acdfe8d27d650293e8db5ef2a","sha256:49c004b551479e8c746800894867694042ad7a87b2b49b282c287229bc01692e"],"state_sha256":"876ddba59a4e5fab33c60256f9e93c461a6298090313cfc468c65ec3f9527d10"}