{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5VKMMTNGJ5PD2WMSELN4TA2DIS","short_pith_number":"pith:5VKMMTNG","schema_version":"1.0","canonical_sha256":"ed54c64da64f5e3d599222dbc9834344857f58b5a1013a2d9b291386963f97f9","source":{"kind":"arxiv","id":"2411.14199","version":1},"attestation_state":"computed","paper":{"title":"OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DL","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Akari Asai, Amanpreet Singh, Bohao Wu, Dan Weld, David Wadden, Doug Downey, Graham Neubig, Hannaneh Hajishirzi, Hao Tong, Jacqueline He, Joseph Chee Chang, Kyle Lo, Luca Soldaini, Luke Zettlemoyer, Matt Latzke, Mike D'Arcy, Minyang Tian, Pang Wei Koh, Pan Ji, Rulin Shao, Sergey Feldman, Shengyan Liu, Weijia Shi, Wen-tau Yih, Yanyu Xiong","submitted_at":"2024-11-21T15:07:42Z","abstract_excerpt":"Scientific progress depends on researchers' ability to synthesize the growing body of literature. Can large language models (LMs) assist scientists in this task? We introduce OpenScholar, a specialized retrieval-augmented LM that answers scientific queries by identifying relevant passages from 45 million open-access papers and synthesizing citation-backed responses. To evaluate OpenScholar, we develop ScholarQABench, the first large-scale multi-domain benchmark for literature search, comprising 2,967 expert-written queries and 208 long-form answers across computer science, physics, neuroscienc"},"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":"2411.14199","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-21T15:07:42Z","cross_cats_sorted":["cs.AI","cs.DL","cs.IR","cs.LG"],"title_canon_sha256":"7f78669d33e4ab53a3b64652f2a9680c0d4e0a0f6312c35d29057aba5bd40665","abstract_canon_sha256":"80e4e9fee16fccb1dc7b570d7dba221405ee6689e9e9df3fbdef80d7653b8b7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:43.190650Z","signature_b64":"kHqflfo7SIVl4g5K8/EBVudFzQjakeqA2owMwPXp9TQW/Ii/N7YG5Eq+6Lo17w+uf5359MgbQ6xZcUYOIFWDCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed54c64da64f5e3d599222dbc9834344857f58b5a1013a2d9b291386963f97f9","last_reissued_at":"2026-07-05T09:38:43.190207Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:43.190207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DL","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Akari Asai, Amanpreet Singh, Bohao Wu, Dan Weld, David Wadden, Doug Downey, Graham Neubig, Hannaneh Hajishirzi, Hao Tong, Jacqueline He, Joseph Chee Chang, Kyle Lo, Luca Soldaini, Luke Zettlemoyer, Matt Latzke, Mike D'Arcy, Minyang Tian, Pang Wei Koh, Pan Ji, Rulin Shao, Sergey Feldman, Shengyan Liu, Weijia Shi, Wen-tau Yih, Yanyu Xiong","submitted_at":"2024-11-21T15:07:42Z","abstract_excerpt":"Scientific progress depends on researchers' ability to synthesize the growing body of literature. Can large language models (LMs) assist scientists in this task? We introduce OpenScholar, a specialized retrieval-augmented LM that answers scientific queries by identifying relevant passages from 45 million open-access papers and synthesizing citation-backed responses. To evaluate OpenScholar, we develop ScholarQABench, the first large-scale multi-domain benchmark for literature search, comprising 2,967 expert-written queries and 208 long-form answers across computer science, physics, neuroscienc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14199","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/2411.14199/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":"2411.14199","created_at":"2026-07-05T09:38:43.190268+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.14199v1","created_at":"2026-07-05T09:38:43.190268+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14199","created_at":"2026-07-05T09:38:43.190268+00:00"},{"alias_kind":"pith_short_12","alias_value":"5VKMMTNGJ5PD","created_at":"2026-07-05T09:38:43.190268+00:00"},{"alias_kind":"pith_short_16","alias_value":"5VKMMTNGJ5PD2WMS","created_at":"2026-07-05T09:38:43.190268+00:00"},{"alias_kind":"pith_short_8","alias_value":"5VKMMTNG","created_at":"2026-07-05T09:38:43.190268+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":23,"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":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11337","citing_title":"Can AI Agents Synthesize Scientific Conclusions?","ref_index":15,"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":28,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00597","citing_title":"Multi-Turn Agentic Scientific Literature Search via Workflow Induction","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31651","citing_title":"FARS: A Fully Automated Research System Deployed at Scale","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29645","citing_title":"Metadata, Structure, or Strategy? A Decomposition of RAG Context Enrichment","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27361","citing_title":"Natural Language Query to Configuration for Retrieval Agents","ref_index":3,"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":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30824","citing_title":"Planner-Centric Reinforcement Learning for Deep Research with Structure-Aware Reward","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30947","citing_title":"Extending AI for Research to the Humanities: A Multi-Agent Framework for Evidence-Grounded Scholarship","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12191","citing_title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22878","citing_title":"SciAtlas: A Large-Scale Knowledge Graph for Automated Scientific Research","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23590","citing_title":"Co-ReAct: Rubrics as Step-Level Collaborators for ReAct Agents","ref_index":25,"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":3,"is_internal_anchor":false},{"citing_arxiv_id":"2505.14838","citing_title":"In-depth Research Impact Summarization through Fine-Grained Temporal Citation Analysis","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2509.23986","citing_title":"TusoAI: Agentic Optimization for Scientific Methods","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2603.05308","citing_title":"Med-V1: Small Language Models for Zero-shot and Scalable Biomedical Evidence Attribution","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2509.26574","citing_title":"Probing the Critical Point (CritPt) of AI Reasoning: a Frontier Physics Research Benchmark","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2510.00361","citing_title":"Attribution Gradients: Incrementally Unfolding Citations for Critical Examination of Attributed AI Answers","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2511.07689","citing_title":"Stress Testing Factual Consistency Metrics for Long-Document Summarization","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02988","citing_title":"Self-Optimizing Multi-Agent Systems for Deep Research","ref_index":2,"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":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09012","citing_title":"Re$^2$Math: Benchmarking Theorem Retrieval in Research-Level Mathematics","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5VKMMTNGJ5PD2WMSELN4TA2DIS","json":"https://pith.science/pith/5VKMMTNGJ5PD2WMSELN4TA2DIS.json","graph_json":"https://pith.science/api/pith-number/5VKMMTNGJ5PD2WMSELN4TA2DIS/graph.json","events_json":"https://pith.science/api/pith-number/5VKMMTNGJ5PD2WMSELN4TA2DIS/events.json","paper":"https://pith.science/paper/5VKMMTNG"},"agent_actions":{"view_html":"https://pith.science/pith/5VKMMTNGJ5PD2WMSELN4TA2DIS","download_json":"https://pith.science/pith/5VKMMTNGJ5PD2WMSELN4TA2DIS.json","view_paper":"https://pith.science/paper/5VKMMTNG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.14199&json=true","fetch_graph":"https://pith.science/api/pith-number/5VKMMTNGJ5PD2WMSELN4TA2DIS/graph.json","fetch_events":"https://pith.science/api/pith-number/5VKMMTNGJ5PD2WMSELN4TA2DIS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5VKMMTNGJ5PD2WMSELN4TA2DIS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5VKMMTNGJ5PD2WMSELN4TA2DIS/action/storage_attestation","attest_author":"https://pith.science/pith/5VKMMTNGJ5PD2WMSELN4TA2DIS/action/author_attestation","sign_citation":"https://pith.science/pith/5VKMMTNGJ5PD2WMSELN4TA2DIS/action/citation_signature","submit_replication":"https://pith.science/pith/5VKMMTNGJ5PD2WMSELN4TA2DIS/action/replication_record"}},"created_at":"2026-07-05T09:38:43.190268+00:00","updated_at":"2026-07-05T09:38:43.190268+00:00"}