{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FV4O7QTTYU6NRTXNQSUEFF2EF2","short_pith_number":"pith:FV4O7QTT","schema_version":"1.0","canonical_sha256":"2d78efc273c53cd8ceed84a84297442e88cbcfae1f57610f7a79f8e83a36cd1b","source":{"kind":"arxiv","id":"2507.12425","version":1},"attestation_state":"computed","paper":{"title":"Advancing Retrieval-Augmented Generation for Structured Enterprise and Internal Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CE","cs.IR"],"primary_cat":"cs.CL","authors_text":"Chandana Cheerla","submitted_at":"2025-07-16T17:13:06Z","abstract_excerpt":"Organizations increasingly rely on proprietary enterprise data, including HR records, structured reports, and tabular documents, for critical decision-making. While Large Language Models (LLMs) have strong generative capabilities, they are limited by static pretraining, short context windows, and challenges in processing heterogeneous data formats. Conventional Retrieval-Augmented Generation (RAG) frameworks address some of these gaps but often struggle with structured and semi-structured data.\n  This work proposes an advanced RAG framework that combines hybrid retrieval strategies using dense"},"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":"2507.12425","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-16T17:13:06Z","cross_cats_sorted":["cs.AI","cs.CE","cs.IR"],"title_canon_sha256":"0d456d5bf11cedc995d11e90b00df959d3137109e87496166731ed2a2756f97c","abstract_canon_sha256":"cabb144d4cb1d07d9981293cdbc843d1fe5065ba9fa3bd78e59ad608e8d57c8f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:20.046194Z","signature_b64":"Cb+wppTn0o7LOTkj7gR27pfbi1AvHkeB5LKE9Lh/9yrVfU+TxfQKraS9dQwZqdcM4/CRkQBpO2LJK/DCUI8cCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d78efc273c53cd8ceed84a84297442e88cbcfae1f57610f7a79f8e83a36cd1b","last_reissued_at":"2026-07-05T11:38:20.045690Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:20.045690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Advancing Retrieval-Augmented Generation for Structured Enterprise and Internal Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CE","cs.IR"],"primary_cat":"cs.CL","authors_text":"Chandana Cheerla","submitted_at":"2025-07-16T17:13:06Z","abstract_excerpt":"Organizations increasingly rely on proprietary enterprise data, including HR records, structured reports, and tabular documents, for critical decision-making. While Large Language Models (LLMs) have strong generative capabilities, they are limited by static pretraining, short context windows, and challenges in processing heterogeneous data formats. Conventional Retrieval-Augmented Generation (RAG) frameworks address some of these gaps but often struggle with structured and semi-structured data.\n  This work proposes an advanced RAG framework that combines hybrid retrieval strategies using dense"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12425","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/2507.12425/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":"2507.12425","created_at":"2026-07-05T11:38:20.045754+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.12425v1","created_at":"2026-07-05T11:38:20.045754+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12425","created_at":"2026-07-05T11:38:20.045754+00:00"},{"alias_kind":"pith_short_12","alias_value":"FV4O7QTTYU6N","created_at":"2026-07-05T11:38:20.045754+00:00"},{"alias_kind":"pith_short_16","alias_value":"FV4O7QTTYU6NRTXN","created_at":"2026-07-05T11:38:20.045754+00:00"},{"alias_kind":"pith_short_8","alias_value":"FV4O7QTT","created_at":"2026-07-05T11:38:20.045754+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FV4O7QTTYU6NRTXNQSUEFF2EF2","json":"https://pith.science/pith/FV4O7QTTYU6NRTXNQSUEFF2EF2.json","graph_json":"https://pith.science/api/pith-number/FV4O7QTTYU6NRTXNQSUEFF2EF2/graph.json","events_json":"https://pith.science/api/pith-number/FV4O7QTTYU6NRTXNQSUEFF2EF2/events.json","paper":"https://pith.science/paper/FV4O7QTT"},"agent_actions":{"view_html":"https://pith.science/pith/FV4O7QTTYU6NRTXNQSUEFF2EF2","download_json":"https://pith.science/pith/FV4O7QTTYU6NRTXNQSUEFF2EF2.json","view_paper":"https://pith.science/paper/FV4O7QTT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.12425&json=true","fetch_graph":"https://pith.science/api/pith-number/FV4O7QTTYU6NRTXNQSUEFF2EF2/graph.json","fetch_events":"https://pith.science/api/pith-number/FV4O7QTTYU6NRTXNQSUEFF2EF2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FV4O7QTTYU6NRTXNQSUEFF2EF2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FV4O7QTTYU6NRTXNQSUEFF2EF2/action/storage_attestation","attest_author":"https://pith.science/pith/FV4O7QTTYU6NRTXNQSUEFF2EF2/action/author_attestation","sign_citation":"https://pith.science/pith/FV4O7QTTYU6NRTXNQSUEFF2EF2/action/citation_signature","submit_replication":"https://pith.science/pith/FV4O7QTTYU6NRTXNQSUEFF2EF2/action/replication_record"}},"created_at":"2026-07-05T11:38:20.045754+00:00","updated_at":"2026-07-05T11:38:20.045754+00:00"}