{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EPDHVNUD2JSUOFZXEB7IRTS7EX","short_pith_number":"pith:EPDHVNUD","schema_version":"1.0","canonical_sha256":"23c67ab683d265471737207e88ce5f25d5392be46d97662de2e7b785020950e4","source":{"kind":"arxiv","id":"2405.03963","version":4},"attestation_state":"computed","paper":{"title":"ERATTA: Extreme RAG for Table To Answers with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Anvar Mahammad, Arijit Mukherjee, Brian Moore, Marko Krema, Punit Prakashchandra, Sohini Roychowdhury","submitted_at":"2024-05-07T02:49:59Z","abstract_excerpt":"Large language models (LLMs) with retrieval augmented-generation (RAG) have been the optimal choice for scalable generative AI solutions in the recent past. Although RAG implemented with AI agents (agentic-RAG) has been recently popularized, its suffers from unstable cost and unreliable performances for Enterprise-level data-practices. Most existing use-cases that incorporate RAG with LLMs have been either generic or extremely domain specific, thereby questioning the scalability and generalizability of RAG-LLM approaches. In this work, we propose a unique LLM-based system where multiple LLMs c"},"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":"2405.03963","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-07T02:49:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"29b43978aa5e6c9a79780744bb666c31498bc6ded8cfb55909ce0b7a53942047","abstract_canon_sha256":"f3fdfbd51ca46a6b4fd289a69c7053994f0734943b5c398535cb3d8f0015a4d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:11.355132Z","signature_b64":"niIabIyD1SUH1Zx+l2tcsPfC71k8sMb2uHLfgT1sXCeCWcJlTcaNL0ggMUFDurUtMA4RW4f4BQ9YV/65gkHrDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23c67ab683d265471737207e88ce5f25d5392be46d97662de2e7b785020950e4","last_reissued_at":"2026-07-05T09:36:11.354635Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:11.354635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ERATTA: Extreme RAG for Table To Answers with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Anvar Mahammad, Arijit Mukherjee, Brian Moore, Marko Krema, Punit Prakashchandra, Sohini Roychowdhury","submitted_at":"2024-05-07T02:49:59Z","abstract_excerpt":"Large language models (LLMs) with retrieval augmented-generation (RAG) have been the optimal choice for scalable generative AI solutions in the recent past. Although RAG implemented with AI agents (agentic-RAG) has been recently popularized, its suffers from unstable cost and unreliable performances for Enterprise-level data-practices. Most existing use-cases that incorporate RAG with LLMs have been either generic or extremely domain specific, thereby questioning the scalability and generalizability of RAG-LLM approaches. In this work, we propose a unique LLM-based system where multiple LLMs c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03963","kind":"arxiv","version":4},"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/2405.03963/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":"2405.03963","created_at":"2026-07-05T09:36:11.354699+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.03963v4","created_at":"2026-07-05T09:36:11.354699+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03963","created_at":"2026-07-05T09:36:11.354699+00:00"},{"alias_kind":"pith_short_12","alias_value":"EPDHVNUD2JSU","created_at":"2026-07-05T09:36:11.354699+00:00"},{"alias_kind":"pith_short_16","alias_value":"EPDHVNUD2JSUOFZX","created_at":"2026-07-05T09:36:11.354699+00:00"},{"alias_kind":"pith_short_8","alias_value":"EPDHVNUD","created_at":"2026-07-05T09:36:11.354699+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2402.19473","citing_title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","ref_index":295,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EPDHVNUD2JSUOFZXEB7IRTS7EX","json":"https://pith.science/pith/EPDHVNUD2JSUOFZXEB7IRTS7EX.json","graph_json":"https://pith.science/api/pith-number/EPDHVNUD2JSUOFZXEB7IRTS7EX/graph.json","events_json":"https://pith.science/api/pith-number/EPDHVNUD2JSUOFZXEB7IRTS7EX/events.json","paper":"https://pith.science/paper/EPDHVNUD"},"agent_actions":{"view_html":"https://pith.science/pith/EPDHVNUD2JSUOFZXEB7IRTS7EX","download_json":"https://pith.science/pith/EPDHVNUD2JSUOFZXEB7IRTS7EX.json","view_paper":"https://pith.science/paper/EPDHVNUD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.03963&json=true","fetch_graph":"https://pith.science/api/pith-number/EPDHVNUD2JSUOFZXEB7IRTS7EX/graph.json","fetch_events":"https://pith.science/api/pith-number/EPDHVNUD2JSUOFZXEB7IRTS7EX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EPDHVNUD2JSUOFZXEB7IRTS7EX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EPDHVNUD2JSUOFZXEB7IRTS7EX/action/storage_attestation","attest_author":"https://pith.science/pith/EPDHVNUD2JSUOFZXEB7IRTS7EX/action/author_attestation","sign_citation":"https://pith.science/pith/EPDHVNUD2JSUOFZXEB7IRTS7EX/action/citation_signature","submit_replication":"https://pith.science/pith/EPDHVNUD2JSUOFZXEB7IRTS7EX/action/replication_record"}},"created_at":"2026-07-05T09:36:11.354699+00:00","updated_at":"2026-07-05T09:36:11.354699+00:00"}