{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PJGDHFNRIQISL5YI7QYV5VZI6T","short_pith_number":"pith:PJGDHFNR","schema_version":"1.0","canonical_sha256":"7a4c3395b1441125f708fc315ed728f4e94e50cfd48268c0d567b8fd0a29058a","source":{"kind":"arxiv","id":"2312.07559","version":2},"attestation_state":"computed","paper":{"title":"PaperQA: Retrieval-Augmented Generative Agent for Scientific Research","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aleksandar Shtedritski, Andrew D. White, Jakub L\\'ala, Odhran O'Donoghue, Sam Cox, Samuel G. Rodriques","submitted_at":"2023-12-08T18:50:20Z","abstract_excerpt":"Large Language Models (LLMs) generalize well across language tasks, but suffer from hallucinations and uninterpretability, making it difficult to assess their accuracy without ground-truth. Retrieval-Augmented Generation (RAG) models have been proposed to reduce hallucinations and provide provenance for how an answer was generated. Applying such models to the scientific literature may enable large-scale, systematic processing of scientific knowledge. We present PaperQA, a RAG agent for answering questions over the scientific literature. PaperQA is an agent that performs information retrieval a"},"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":"2312.07559","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-08T18:50:20Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"45d07f674e15f65b5c44cbaa12ff9a6048b7369a641cd2c63a878a3af446b72b","abstract_canon_sha256":"cea0c9e1473eeee1342045196780aba1451259254ccae7950651216bf2969029"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:21.970089Z","signature_b64":"ClK3Vub/F09dUXWLOXP7tSEUk/hbf2Nmn4k4jsDj0miiLPHVMoTKfKb3jf4jwDCt4yjLOHEaMriFK+TV71xYCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a4c3395b1441125f708fc315ed728f4e94e50cfd48268c0d567b8fd0a29058a","last_reissued_at":"2026-07-05T07:24:21.969606Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:21.969606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PaperQA: Retrieval-Augmented Generative Agent for Scientific Research","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aleksandar Shtedritski, Andrew D. White, Jakub L\\'ala, Odhran O'Donoghue, Sam Cox, Samuel G. Rodriques","submitted_at":"2023-12-08T18:50:20Z","abstract_excerpt":"Large Language Models (LLMs) generalize well across language tasks, but suffer from hallucinations and uninterpretability, making it difficult to assess their accuracy without ground-truth. Retrieval-Augmented Generation (RAG) models have been proposed to reduce hallucinations and provide provenance for how an answer was generated. Applying such models to the scientific literature may enable large-scale, systematic processing of scientific knowledge. We present PaperQA, a RAG agent for answering questions over the scientific literature. PaperQA is an agent that performs information retrieval a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.07559","kind":"arxiv","version":2},"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/2312.07559/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":"2312.07559","created_at":"2026-07-05T07:24:21.969660+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.07559v2","created_at":"2026-07-05T07:24:21.969660+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.07559","created_at":"2026-07-05T07:24:21.969660+00:00"},{"alias_kind":"pith_short_12","alias_value":"PJGDHFNRIQIS","created_at":"2026-07-05T07:24:21.969660+00:00"},{"alias_kind":"pith_short_16","alias_value":"PJGDHFNRIQISL5YI","created_at":"2026-07-05T07:24:21.969660+00:00"},{"alias_kind":"pith_short_8","alias_value":"PJGDHFNR","created_at":"2026-07-05T07:24:21.969660+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":30,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24530","citing_title":"NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers?","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26246","citing_title":"Lacuna: A Research Map for Machine Learning","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19135","citing_title":"A Technical Taxonomy of LLM Agent Communication Protocols","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18356","citing_title":"SafeClawBench: Separating Semantic, Audit-Evidence, and Sandbox Harm in Tool-Using LLM Agents","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01588","citing_title":"OrchestrXR: A Multi-Agent System for Idea-to-Prototype XR Study Authoring","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07936","citing_title":"Illusions of the Gold Standard: A Large-scale Analysis of Human Evaluation Protocols for Long-form Text Generation","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07022","citing_title":"Self-Driving Datasets: From 20 Million Papers to Nuanced Biomedical Knowledge at Scale","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27610","citing_title":"Eliot: Interactively $\\underline{E}$xploring Fast-Changing Scientific $\\underline{Li}$terature Trends with $\\underline{O}$nline Da$\\underline{t}$a and Learning","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29966","citing_title":"Compass: Navigating Global Marine Lead Data Integration through Expert-Guided LLM Agent","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00644","citing_title":"ForeSci: Evaluating LLM Agents for Forward-Looking AI Research Judgment","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2312.10997","citing_title":"Retrieval-Augmented Generation for Large Language Models: A Survey","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2410.17448","citing_title":"In Context Learning and Reasoning for Symbolic Regression with Large Language Models","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"2502.02871","citing_title":"Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2502.13957","citing_title":"Supervising the search process produces reliable and generalizable information-seeking agents","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2505.11336","citing_title":"XtraGPT: Context-Aware and Controllable Academic Paper Revision via Human-AI Collaboration","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21168","citing_title":"Diverse LLMs or Diverse Question Interpretations? That is the Ensembling Question","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04375","citing_title":"Experiment-as-Code Labs: A Declarative Stack for AI-Driven Scientific Discovery","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07022","citing_title":"Self-Driving Datasets: From 20 Million Papers to Nuanced Biomedical Knowledge at Scale","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18144","citing_title":"Evidence-Grounded Frontier Mapping and Agentic Hypothesis Generation in Nanomedicine","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18661","citing_title":"AI for Auto-Research: Roadmap & User Guide","ref_index":128,"is_internal_anchor":false},{"citing_arxiv_id":"2601.15170","citing_title":"Multi-Dimensional Knowledge Profiling with Large-Scale Literature Database and Hierarchical Retrieval","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04074","citing_title":"FactReview: Evidence-Grounded Reviews with Literature Positioning and Execution-Based Claim Verification","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10813","citing_title":"NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09012","citing_title":"Re$^2$Math: Benchmarking Theorem Retrieval in Research-Level Mathematics","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03344","citing_title":"RAG over Thinking Traces Can Improve Reasoning Tasks","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PJGDHFNRIQISL5YI7QYV5VZI6T","json":"https://pith.science/pith/PJGDHFNRIQISL5YI7QYV5VZI6T.json","graph_json":"https://pith.science/api/pith-number/PJGDHFNRIQISL5YI7QYV5VZI6T/graph.json","events_json":"https://pith.science/api/pith-number/PJGDHFNRIQISL5YI7QYV5VZI6T/events.json","paper":"https://pith.science/paper/PJGDHFNR"},"agent_actions":{"view_html":"https://pith.science/pith/PJGDHFNRIQISL5YI7QYV5VZI6T","download_json":"https://pith.science/pith/PJGDHFNRIQISL5YI7QYV5VZI6T.json","view_paper":"https://pith.science/paper/PJGDHFNR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.07559&json=true","fetch_graph":"https://pith.science/api/pith-number/PJGDHFNRIQISL5YI7QYV5VZI6T/graph.json","fetch_events":"https://pith.science/api/pith-number/PJGDHFNRIQISL5YI7QYV5VZI6T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PJGDHFNRIQISL5YI7QYV5VZI6T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PJGDHFNRIQISL5YI7QYV5VZI6T/action/storage_attestation","attest_author":"https://pith.science/pith/PJGDHFNRIQISL5YI7QYV5VZI6T/action/author_attestation","sign_citation":"https://pith.science/pith/PJGDHFNRIQISL5YI7QYV5VZI6T/action/citation_signature","submit_replication":"https://pith.science/pith/PJGDHFNRIQISL5YI7QYV5VZI6T/action/replication_record"}},"created_at":"2026-07-05T07:24:21.969660+00:00","updated_at":"2026-07-05T07:24:21.969660+00:00"}