{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HGLZVVDVZMCCT4W4KQVL2T4M4I","short_pith_number":"pith:HGLZVVDV","schema_version":"1.0","canonical_sha256":"39979ad475cb0429f2dc542abd4f8ce2007a1228e2747c70a19efdf86a77a519","source":{"kind":"arxiv","id":"2409.13741","version":1},"attestation_state":"computed","paper":{"title":"Knowing When to Ask -- Bridging Large Language Models and Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Adriana Olmos, Bo Xu, Hannah Pho, James Manyika, Jennifer Chen, Prashanth Radhakrishnan, Prem Ramaswami, R. V. Guha","submitted_at":"2024-09-10T17:51:21Z","abstract_excerpt":"Large Language Models (LLMs) are prone to generating factually incorrect information when responding to queries that involve numerical and statistical data or other timely facts. In this paper, we present an approach for enhancing the accuracy of LLMs by integrating them with Data Commons, a vast, open-source repository of public statistics from trusted organizations like the United Nations (UN), Center for Disease Control and Prevention (CDC) and global census bureaus. We explore two primary methods: Retrieval Interleaved Generation (RIG), where the LLM is trained to produce natural language "},"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":"2409.13741","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-10T17:51:21Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"1f492b8fb3f71ea22d05a674116742f0a33a6466440e500b8739a772b2b02016","abstract_canon_sha256":"6befc73a0edde8ae8bb0359c57d2625c4148ec4bc74fd719f06a8c38de8b5abc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:32.916908Z","signature_b64":"Zl2UiDiCWAuLJ7dG7wgP9ldYoUOV0gI/5+GITduuf2h5o9fHe2ozd5tTFwBeAbZ88K8GbTXalIxJc8NJXStpDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39979ad475cb0429f2dc542abd4f8ce2007a1228e2747c70a19efdf86a77a519","last_reissued_at":"2026-07-05T09:10:32.916492Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:32.916492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowing When to Ask -- Bridging Large Language Models and Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Adriana Olmos, Bo Xu, Hannah Pho, James Manyika, Jennifer Chen, Prashanth Radhakrishnan, Prem Ramaswami, R. V. Guha","submitted_at":"2024-09-10T17:51:21Z","abstract_excerpt":"Large Language Models (LLMs) are prone to generating factually incorrect information when responding to queries that involve numerical and statistical data or other timely facts. In this paper, we present an approach for enhancing the accuracy of LLMs by integrating them with Data Commons, a vast, open-source repository of public statistics from trusted organizations like the United Nations (UN), Center for Disease Control and Prevention (CDC) and global census bureaus. We explore two primary methods: Retrieval Interleaved Generation (RIG), where the LLM is trained to produce natural language "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.13741","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/2409.13741/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":"2409.13741","created_at":"2026-07-05T09:10:32.916550+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.13741v1","created_at":"2026-07-05T09:10:32.916550+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.13741","created_at":"2026-07-05T09:10:32.916550+00:00"},{"alias_kind":"pith_short_12","alias_value":"HGLZVVDVZMCC","created_at":"2026-07-05T09:10:32.916550+00:00"},{"alias_kind":"pith_short_16","alias_value":"HGLZVVDVZMCCT4W4","created_at":"2026-07-05T09:10:32.916550+00:00"},{"alias_kind":"pith_short_8","alias_value":"HGLZVVDV","created_at":"2026-07-05T09:10:32.916550+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.21965","citing_title":"SpecHop: Continuous Speculation for Accelerating Multi-Hop Retrieval Agents","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HGLZVVDVZMCCT4W4KQVL2T4M4I","json":"https://pith.science/pith/HGLZVVDVZMCCT4W4KQVL2T4M4I.json","graph_json":"https://pith.science/api/pith-number/HGLZVVDVZMCCT4W4KQVL2T4M4I/graph.json","events_json":"https://pith.science/api/pith-number/HGLZVVDVZMCCT4W4KQVL2T4M4I/events.json","paper":"https://pith.science/paper/HGLZVVDV"},"agent_actions":{"view_html":"https://pith.science/pith/HGLZVVDVZMCCT4W4KQVL2T4M4I","download_json":"https://pith.science/pith/HGLZVVDVZMCCT4W4KQVL2T4M4I.json","view_paper":"https://pith.science/paper/HGLZVVDV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.13741&json=true","fetch_graph":"https://pith.science/api/pith-number/HGLZVVDVZMCCT4W4KQVL2T4M4I/graph.json","fetch_events":"https://pith.science/api/pith-number/HGLZVVDVZMCCT4W4KQVL2T4M4I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HGLZVVDVZMCCT4W4KQVL2T4M4I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HGLZVVDVZMCCT4W4KQVL2T4M4I/action/storage_attestation","attest_author":"https://pith.science/pith/HGLZVVDVZMCCT4W4KQVL2T4M4I/action/author_attestation","sign_citation":"https://pith.science/pith/HGLZVVDVZMCCT4W4KQVL2T4M4I/action/citation_signature","submit_replication":"https://pith.science/pith/HGLZVVDVZMCCT4W4KQVL2T4M4I/action/replication_record"}},"created_at":"2026-07-05T09:10:32.916550+00:00","updated_at":"2026-07-05T09:10:32.916550+00:00"}