{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BN4WUGDJIUQ5IKRJLOCY3FSIZ3","short_pith_number":"pith:BN4WUGDJ","schema_version":"1.0","canonical_sha256":"0b796a18694521d42a295b858d9648ced5f2050d30da4b312970cb78b524dc62","source":{"kind":"arxiv","id":"2506.00664","version":1},"attestation_state":"computed","paper":{"title":"OntoRAG: Enhancing Question-Answering through Automated Ontology Derivation from Unstructured Knowledge Bases","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Mayukha Pal, Owais Ahmad Lone, Yash Tiwari","submitted_at":"2025-05-31T18:33:39Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.00664","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-31T18:33:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"170bc6cef3aa929493a4e71ce290c6dbdf0d96d5be3f5018e9c3131db1e9536f","abstract_canon_sha256":"eff32d00ae42bda4d9c449b9428e96aa45141a94972512a26b0862b24c29c5df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:38.249405Z","signature_b64":"NMnyd43Ldp1iDp/VGBUQMQzT7T/hgz3I7fpVHKmNPdPrZ2Q03g6x490aGf9tn6wMVCmtRE3QAPAZKv6xT2uICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b796a18694521d42a295b858d9648ced5f2050d30da4b312970cb78b524dc62","last_reissued_at":"2026-07-05T11:13:38.248980Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:38.248980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OntoRAG: Enhancing Question-Answering through Automated Ontology Derivation from Unstructured Knowledge Bases","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Mayukha Pal, Owais Ahmad Lone, Yash Tiwari","submitted_at":"2025-05-31T18:33:39Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00664","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/2506.00664/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.00664","created_at":"2026-07-05T11:13:38.249034+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00664v1","created_at":"2026-07-05T11:13:38.249034+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00664","created_at":"2026-07-05T11:13:38.249034+00:00"},{"alias_kind":"pith_short_12","alias_value":"BN4WUGDJIUQ5","created_at":"2026-07-05T11:13:38.249034+00:00"},{"alias_kind":"pith_short_16","alias_value":"BN4WUGDJIUQ5IKRJ","created_at":"2026-07-05T11:13:38.249034+00:00"},{"alias_kind":"pith_short_8","alias_value":"BN4WUGDJ","created_at":"2026-07-05T11:13:38.249034+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28070","citing_title":"JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28070","citing_title":"JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications","ref_index":78,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BN4WUGDJIUQ5IKRJLOCY3FSIZ3","json":"https://pith.science/pith/BN4WUGDJIUQ5IKRJLOCY3FSIZ3.json","graph_json":"https://pith.science/api/pith-number/BN4WUGDJIUQ5IKRJLOCY3FSIZ3/graph.json","events_json":"https://pith.science/api/pith-number/BN4WUGDJIUQ5IKRJLOCY3FSIZ3/events.json","paper":"https://pith.science/paper/BN4WUGDJ"},"agent_actions":{"view_html":"https://pith.science/pith/BN4WUGDJIUQ5IKRJLOCY3FSIZ3","download_json":"https://pith.science/pith/BN4WUGDJIUQ5IKRJLOCY3FSIZ3.json","view_paper":"https://pith.science/paper/BN4WUGDJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00664&json=true","fetch_graph":"https://pith.science/api/pith-number/BN4WUGDJIUQ5IKRJLOCY3FSIZ3/graph.json","fetch_events":"https://pith.science/api/pith-number/BN4WUGDJIUQ5IKRJLOCY3FSIZ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BN4WUGDJIUQ5IKRJLOCY3FSIZ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BN4WUGDJIUQ5IKRJLOCY3FSIZ3/action/storage_attestation","attest_author":"https://pith.science/pith/BN4WUGDJIUQ5IKRJLOCY3FSIZ3/action/author_attestation","sign_citation":"https://pith.science/pith/BN4WUGDJIUQ5IKRJLOCY3FSIZ3/action/citation_signature","submit_replication":"https://pith.science/pith/BN4WUGDJIUQ5IKRJLOCY3FSIZ3/action/replication_record"}},"created_at":"2026-07-05T11:13:38.249034+00:00","updated_at":"2026-07-05T11:13:38.249034+00:00"}