{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FTGKTRDTUM7OLGLCNUDC2ZA3OM","short_pith_number":"pith:FTGKTRDT","schema_version":"1.0","canonical_sha256":"2ccca9c473a33ee599626d062d641b732f7a0de5302c4e06711cbe301b417d41","source":{"kind":"arxiv","id":"2407.18940","version":2},"attestation_state":"computed","paper":{"title":"LitSearch: A Retrieval Benchmark for Scientific Literature Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.DL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Alexis Chevalier, Anirudh Ajith, Danqi Chen, Mengzhou Xia, Tanya Goyal, Tianyu Gao","submitted_at":"2024-07-10T18:00:03Z","abstract_excerpt":"Literature search questions, such as \"Where can I find research on the evaluation of consistency in generated summaries?\" pose significant challenges for modern search engines and retrieval systems. These questions often require a deep understanding of research concepts and the ability to reason across entire articles. In this work, we introduce LitSearch, a retrieval benchmark comprising 597 realistic literature search queries about recent ML and NLP papers. LitSearch is constructed using a combination of (1) questions generated by GPT-4 based on paragraphs containing inline citations from re"},"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":"2407.18940","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-07-10T18:00:03Z","cross_cats_sorted":["cs.AI","cs.CL","cs.DL","cs.LG"],"title_canon_sha256":"c533bd7e0d0b7268a79e91b76b2e827d3a3a1640f8684d9f00821dccb46233ff","abstract_canon_sha256":"0b8264913d8373716c998d0e6ff733a9c9250a289b682bb64784521422f726d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:47.361648Z","signature_b64":"BzLXEnlrQjnKmeh5laNF/++VuBpw6OrRUvH1TrGPS3gVZunbMT1s9jEOvkaGisvgqlS/Ukiu9x8GO5A0+j8mAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ccca9c473a33ee599626d062d641b732f7a0de5302c4e06711cbe301b417d41","last_reissued_at":"2026-07-05T09:21:47.361104Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:47.361104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LitSearch: A Retrieval Benchmark for Scientific Literature Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.DL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Alexis Chevalier, Anirudh Ajith, Danqi Chen, Mengzhou Xia, Tanya Goyal, Tianyu Gao","submitted_at":"2024-07-10T18:00:03Z","abstract_excerpt":"Literature search questions, such as \"Where can I find research on the evaluation of consistency in generated summaries?\" pose significant challenges for modern search engines and retrieval systems. These questions often require a deep understanding of research concepts and the ability to reason across entire articles. In this work, we introduce LitSearch, a retrieval benchmark comprising 597 realistic literature search queries about recent ML and NLP papers. LitSearch is constructed using a combination of (1) questions generated by GPT-4 based on paragraphs containing inline citations from re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18940","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/2407.18940/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":"2407.18940","created_at":"2026-07-05T09:21:47.361172+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.18940v2","created_at":"2026-07-05T09:21:47.361172+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18940","created_at":"2026-07-05T09:21:47.361172+00:00"},{"alias_kind":"pith_short_12","alias_value":"FTGKTRDTUM7O","created_at":"2026-07-05T09:21:47.361172+00:00"},{"alias_kind":"pith_short_16","alias_value":"FTGKTRDTUM7OLGLC","created_at":"2026-07-05T09:21:47.361172+00:00"},{"alias_kind":"pith_short_8","alias_value":"FTGKTRDT","created_at":"2026-07-05T09:21:47.361172+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26246","citing_title":"Lacuna: A Research Map for Machine Learning","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2504.19678","citing_title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10097","citing_title":"H-MAPS: Hierarchical Memory-Augmented Proactive Search Assistant for Scientific Literature","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04018","citing_title":"Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FTGKTRDTUM7OLGLCNUDC2ZA3OM","json":"https://pith.science/pith/FTGKTRDTUM7OLGLCNUDC2ZA3OM.json","graph_json":"https://pith.science/api/pith-number/FTGKTRDTUM7OLGLCNUDC2ZA3OM/graph.json","events_json":"https://pith.science/api/pith-number/FTGKTRDTUM7OLGLCNUDC2ZA3OM/events.json","paper":"https://pith.science/paper/FTGKTRDT"},"agent_actions":{"view_html":"https://pith.science/pith/FTGKTRDTUM7OLGLCNUDC2ZA3OM","download_json":"https://pith.science/pith/FTGKTRDTUM7OLGLCNUDC2ZA3OM.json","view_paper":"https://pith.science/paper/FTGKTRDT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.18940&json=true","fetch_graph":"https://pith.science/api/pith-number/FTGKTRDTUM7OLGLCNUDC2ZA3OM/graph.json","fetch_events":"https://pith.science/api/pith-number/FTGKTRDTUM7OLGLCNUDC2ZA3OM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FTGKTRDTUM7OLGLCNUDC2ZA3OM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FTGKTRDTUM7OLGLCNUDC2ZA3OM/action/storage_attestation","attest_author":"https://pith.science/pith/FTGKTRDTUM7OLGLCNUDC2ZA3OM/action/author_attestation","sign_citation":"https://pith.science/pith/FTGKTRDTUM7OLGLCNUDC2ZA3OM/action/citation_signature","submit_replication":"https://pith.science/pith/FTGKTRDTUM7OLGLCNUDC2ZA3OM/action/replication_record"}},"created_at":"2026-07-05T09:21:47.361172+00:00","updated_at":"2026-07-05T09:21:47.361172+00:00"}