{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PL75D4CXWZPIMIGNEEHMXYRZCE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d749fa2f1435eea53d076f83dff9f0b22a21a63ab3c8031c62a7ae3b7ccb7665","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-03-14T07:27:30Z","title_canon_sha256":"00b1b4b0ec849edf4dd5ae857edb432e0b8ea26751734e48651142e25a68bfd9"},"schema_version":"1.0","source":{"id":"2303.07678","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.07678","created_at":"2026-07-05T06:59:30Z"},{"alias_kind":"arxiv_version","alias_value":"2303.07678v2","created_at":"2026-07-05T06:59:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.07678","created_at":"2026-07-05T06:59:30Z"},{"alias_kind":"pith_short_12","alias_value":"PL75D4CXWZPI","created_at":"2026-07-05T06:59:30Z"},{"alias_kind":"pith_short_16","alias_value":"PL75D4CXWZPIMIGN","created_at":"2026-07-05T06:59:30Z"},{"alias_kind":"pith_short_8","alias_value":"PL75D4CX","created_at":"2026-07-05T06:59:30Z"}],"graph_snapshots":[{"event_id":"sha256:294ab54c15e361cc6c7d4e09d8a95b63bf91c31b267496166e699e9bd9f12f1a","target":"graph","created_at":"2026-07-05T06:59:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2303.07678/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces a simple yet effective query expansion approach, denoted as query2doc, to improve both sparse and dense retrieval systems. The proposed method first generates pseudo-documents by few-shot prompting large language models (LLMs), and then expands the query with generated pseudo-documents. LLMs are trained on web-scale text corpora and are adept at knowledge memorization. The pseudo-documents from LLMs often contain highly relevant information that can aid in query disambiguation and guide the retrievers. Experimental results demonstrate that query2doc boosts the performance","authors_text":"Furu Wei, Liang Wang, Nan Yang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-03-14T07:27:30Z","title":"Query2doc: Query Expansion with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.07678","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8ef7e831355746981603595f2ea9fea9c389beacc335be9125d1c1a010753fa6","target":"record","created_at":"2026-07-05T06:59:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d749fa2f1435eea53d076f83dff9f0b22a21a63ab3c8031c62a7ae3b7ccb7665","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-03-14T07:27:30Z","title_canon_sha256":"00b1b4b0ec849edf4dd5ae857edb432e0b8ea26751734e48651142e25a68bfd9"},"schema_version":"1.0","source":{"id":"2303.07678","kind":"arxiv","version":2}},"canonical_sha256":"7affd1f057b65e8620cd210ecbe239111e1956f6e24fe50f4dadcb283a8a69e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7affd1f057b65e8620cd210ecbe239111e1956f6e24fe50f4dadcb283a8a69e3","first_computed_at":"2026-07-05T06:59:30.380949Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:59:30.380949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0/tfbgYuvs/vlQJTu83SYUw2udw1SsdV5Hr7LbOv0I8vTgCndDdT+DctBz13i0qsoN8ySMQCf+NZGRzCmeenBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:59:30.381311Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.07678","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ef7e831355746981603595f2ea9fea9c389beacc335be9125d1c1a010753fa6","sha256:294ab54c15e361cc6c7d4e09d8a95b63bf91c31b267496166e699e9bd9f12f1a"],"state_sha256":"7251f4099795cd53984f6fc7541f2bbb9618c1602bbac1085c3e3bd9dda70689"}