{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Q7OREAUEQ7PNMPVPCVGQWL5E6M","short_pith_number":"pith:Q7OREAUE","schema_version":"1.0","canonical_sha256":"87dd12028487ded63eaf154d0b2fa4f32d8930f3ccdf56f30e8cd00049de4bc4","source":{"kind":"arxiv","id":"2406.17987","version":4},"attestation_state":"computed","paper":{"title":"Multi-step Inference over Unstructured Data","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Abraham Bautista-Castillo, Aditya Kalyanpur, CJ McFate, David Ferrucci, Eric Brown, Jose Barrera, Kailash Karthik Saravanakumar, Lori Moon, Maksim Eremeev, Nati Seifu, Victor Barres","submitted_at":"2024-06-26T00:00:45Z","abstract_excerpt":"The advent of Large Language Models (LLMs) and Generative AI has revolutionized natural language applications across various domains. However, high-stakes decision-making tasks in fields such as medical, legal and finance require a level of precision, comprehensiveness, and logical consistency that pure LLM or Retrieval-Augmented-Generation (RAG) approaches often fail to deliver. At Elemental Cognition (EC), we have developed a neuro-symbolic AI platform to tackle these problems. The platform integrates fine-tuned LLMs for knowledge extraction and alignment with a robust symbolic reasoning eng"},"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":"2406.17987","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-26T00:00:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8c1a8e8805101b9748897beeec2df66c1903e356ca043fe03367eec2d11e15b5","abstract_canon_sha256":"7718230c21d9d9d82032f481b6c95aa5b13a9ccfbecdb5bd6c70248819c3d5fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:15.262079Z","signature_b64":"FjMDaNzwg0HkExPdcCPagC0Y+fF3yYjrluOvfvRD52ilS9FZT17ig+5QJ5OQPkBBHHGW7+XU058GDUpVYgz0BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87dd12028487ded63eaf154d0b2fa4f32d8930f3ccdf56f30e8cd00049de4bc4","last_reissued_at":"2026-07-05T08:48:15.261652Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:15.261652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-step Inference over Unstructured Data","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Abraham Bautista-Castillo, Aditya Kalyanpur, CJ McFate, David Ferrucci, Eric Brown, Jose Barrera, Kailash Karthik Saravanakumar, Lori Moon, Maksim Eremeev, Nati Seifu, Victor Barres","submitted_at":"2024-06-26T00:00:45Z","abstract_excerpt":"The advent of Large Language Models (LLMs) and Generative AI has revolutionized natural language applications across various domains. However, high-stakes decision-making tasks in fields such as medical, legal and finance require a level of precision, comprehensiveness, and logical consistency that pure LLM or Retrieval-Augmented-Generation (RAG) approaches often fail to deliver. At Elemental Cognition (EC), we have developed a neuro-symbolic AI platform to tackle these problems. The platform integrates fine-tuned LLMs for knowledge extraction and alignment with a robust symbolic reasoning eng"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17987","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/2406.17987/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":"2406.17987","created_at":"2026-07-05T08:48:15.261709+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.17987v4","created_at":"2026-07-05T08:48:15.261709+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17987","created_at":"2026-07-05T08:48:15.261709+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q7OREAUEQ7PN","created_at":"2026-07-05T08:48:15.261709+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q7OREAUEQ7PNMPVP","created_at":"2026-07-05T08:48:15.261709+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q7OREAUE","created_at":"2026-07-05T08:48:15.261709+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/Q7OREAUEQ7PNMPVPCVGQWL5E6M","json":"https://pith.science/pith/Q7OREAUEQ7PNMPVPCVGQWL5E6M.json","graph_json":"https://pith.science/api/pith-number/Q7OREAUEQ7PNMPVPCVGQWL5E6M/graph.json","events_json":"https://pith.science/api/pith-number/Q7OREAUEQ7PNMPVPCVGQWL5E6M/events.json","paper":"https://pith.science/paper/Q7OREAUE"},"agent_actions":{"view_html":"https://pith.science/pith/Q7OREAUEQ7PNMPVPCVGQWL5E6M","download_json":"https://pith.science/pith/Q7OREAUEQ7PNMPVPCVGQWL5E6M.json","view_paper":"https://pith.science/paper/Q7OREAUE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.17987&json=true","fetch_graph":"https://pith.science/api/pith-number/Q7OREAUEQ7PNMPVPCVGQWL5E6M/graph.json","fetch_events":"https://pith.science/api/pith-number/Q7OREAUEQ7PNMPVPCVGQWL5E6M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q7OREAUEQ7PNMPVPCVGQWL5E6M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q7OREAUEQ7PNMPVPCVGQWL5E6M/action/storage_attestation","attest_author":"https://pith.science/pith/Q7OREAUEQ7PNMPVPCVGQWL5E6M/action/author_attestation","sign_citation":"https://pith.science/pith/Q7OREAUEQ7PNMPVPCVGQWL5E6M/action/citation_signature","submit_replication":"https://pith.science/pith/Q7OREAUEQ7PNMPVPCVGQWL5E6M/action/replication_record"}},"created_at":"2026-07-05T08:48:15.261709+00:00","updated_at":"2026-07-05T08:48:15.261709+00:00"}