{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7JXV5FMBYHKA7T2M63HUMNLPRG","short_pith_number":"pith:7JXV5FMB","schema_version":"1.0","canonical_sha256":"fa6f5e9581c1d40fcf4cf6cf46356f89ab800dea66d5e2d7cbeacaec26768fee","source":{"kind":"arxiv","id":"2501.10120","version":2},"attestation_state":"computed","paper":{"title":"PaSa: An LLM Agent for Comprehensive Academic Paper Search","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Guanhua Huang, Hang Li, Peiyuan Feng, Weinan E, Yichen He, Yuan Lin, Yuchen Zhang","submitted_at":"2025-01-17T11:12:28Z","abstract_excerpt":"We introduce PaSa, an advanced Paper Search agent powered by large language models. PaSa can autonomously make a series of decisions, including invoking search tools, reading papers, and selecting relevant references, to ultimately obtain comprehensive and accurate results for complex scholar queries. We optimize PaSa using reinforcement learning with a synthetic dataset, AutoScholarQuery, which includes 35k fine-grained academic queries and corresponding papers sourced from top-tier AI conference publications. Additionally, we develop RealScholarQuery, a benchmark collecting real-world academ"},"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":"2501.10120","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2025-01-17T11:12:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"272c7dc39b6ae8aa356e97d45a200eb406db0a04349896192136474d7d4dd912","abstract_canon_sha256":"7c87879a3a18c08f3bff9a5a0de0a7d8dfa0c5ce3d2b91dab626fa4b64b3dc94"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:04.076066Z","signature_b64":"mkrw+XRJPODszvzHOtTmhZfR1FP1bN0avQD+PbqvqSDP7005Ey5zxH837ivz6d/50XmR4IY1nrTQJpz5ec3pBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa6f5e9581c1d40fcf4cf6cf46356f89ab800dea66d5e2d7cbeacaec26768fee","last_reissued_at":"2026-07-05T11:10:04.075563Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:04.075563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PaSa: An LLM Agent for Comprehensive Academic Paper Search","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Guanhua Huang, Hang Li, Peiyuan Feng, Weinan E, Yichen He, Yuan Lin, Yuchen Zhang","submitted_at":"2025-01-17T11:12:28Z","abstract_excerpt":"We introduce PaSa, an advanced Paper Search agent powered by large language models. PaSa can autonomously make a series of decisions, including invoking search tools, reading papers, and selecting relevant references, to ultimately obtain comprehensive and accurate results for complex scholar queries. We optimize PaSa using reinforcement learning with a synthetic dataset, AutoScholarQuery, which includes 35k fine-grained academic queries and corresponding papers sourced from top-tier AI conference publications. Additionally, we develop RealScholarQuery, a benchmark collecting real-world academ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.10120","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/2501.10120/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":"2501.10120","created_at":"2026-07-05T11:10:04.075619+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.10120v2","created_at":"2026-07-05T11:10:04.075619+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.10120","created_at":"2026-07-05T11:10:04.075619+00:00"},{"alias_kind":"pith_short_12","alias_value":"7JXV5FMBYHKA","created_at":"2026-07-05T11:10:04.075619+00:00"},{"alias_kind":"pith_short_16","alias_value":"7JXV5FMBYHKA7T2M","created_at":"2026-07-05T11:10:04.075619+00:00"},{"alias_kind":"pith_short_8","alias_value":"7JXV5FMB","created_at":"2026-07-05T11:10:04.075619+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20235","citing_title":"ScholarQuest: A Taxonomy-Guided Benchmark for Agentic Academic Paper Search in Open Literature Environments","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18661","citing_title":"AI for Auto-Research: Roadmap & User Guide","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04562","citing_title":"Paper Espresso: From Paper Overload to Research Insight","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7JXV5FMBYHKA7T2M63HUMNLPRG","json":"https://pith.science/pith/7JXV5FMBYHKA7T2M63HUMNLPRG.json","graph_json":"https://pith.science/api/pith-number/7JXV5FMBYHKA7T2M63HUMNLPRG/graph.json","events_json":"https://pith.science/api/pith-number/7JXV5FMBYHKA7T2M63HUMNLPRG/events.json","paper":"https://pith.science/paper/7JXV5FMB"},"agent_actions":{"view_html":"https://pith.science/pith/7JXV5FMBYHKA7T2M63HUMNLPRG","download_json":"https://pith.science/pith/7JXV5FMBYHKA7T2M63HUMNLPRG.json","view_paper":"https://pith.science/paper/7JXV5FMB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.10120&json=true","fetch_graph":"https://pith.science/api/pith-number/7JXV5FMBYHKA7T2M63HUMNLPRG/graph.json","fetch_events":"https://pith.science/api/pith-number/7JXV5FMBYHKA7T2M63HUMNLPRG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7JXV5FMBYHKA7T2M63HUMNLPRG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7JXV5FMBYHKA7T2M63HUMNLPRG/action/storage_attestation","attest_author":"https://pith.science/pith/7JXV5FMBYHKA7T2M63HUMNLPRG/action/author_attestation","sign_citation":"https://pith.science/pith/7JXV5FMBYHKA7T2M63HUMNLPRG/action/citation_signature","submit_replication":"https://pith.science/pith/7JXV5FMBYHKA7T2M63HUMNLPRG/action/replication_record"}},"created_at":"2026-07-05T11:10:04.075619+00:00","updated_at":"2026-07-05T11:10:04.075619+00:00"}