{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2AI3B6MIPWANR5YODQUKCDJEAX","short_pith_number":"pith:2AI3B6MI","schema_version":"1.0","canonical_sha256":"d011b0f9887d80d8f70e1c28a10d2405f943c06f89265ef9e45c798e103f2b1e","source":{"kind":"arxiv","id":"2303.00807","version":3},"attestation_state":"computed","paper":{"title":"UDAPDR: Unsupervised Domain Adaptation via LLM Prompting and Distillation of Rerankers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Avirup Sil, Christopher Potts, Jon Saad-Falcon, Keshav Santhanam, Martin Franz, Md Arafat Sultan, Omar Khattab, Radu Florian, Salim Roukos","submitted_at":"2023-03-01T20:21:23Z","abstract_excerpt":"Many information retrieval tasks require large labeled datasets for fine-tuning. However, such datasets are often unavailable, and their utility for real-world applications can diminish quickly due to domain shifts. To address this challenge, we develop and motivate a method for using large language models (LLMs) to generate large numbers of synthetic queries cheaply. The method begins by generating a small number of synthetic queries using an expensive LLM. After that, a much less expensive one is used to create large numbers of synthetic queries, which are used to fine-tune a family of reran"},"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":"2303.00807","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-03-01T20:21:23Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"19921f468d9e905172fa449d012868350dec8f870d5dd1d646501e225f5e748b","abstract_canon_sha256":"700f34b52d5b99637d688f095dee2039f06852c0bb1f51ab68c4bf202ae2138d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:21.646509Z","signature_b64":"LGEz7+pEulWA5WWtr4YDHigZ+0FTyY7GJ6achOMLqHhsDOozdvOJULpQbKksJfJItL6XRrDSHN7LGui3QG+KDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d011b0f9887d80d8f70e1c28a10d2405f943c06f89265ef9e45c798e103f2b1e","last_reissued_at":"2026-07-05T07:00:21.646039Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:21.646039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UDAPDR: Unsupervised Domain Adaptation via LLM Prompting and Distillation of Rerankers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Avirup Sil, Christopher Potts, Jon Saad-Falcon, Keshav Santhanam, Martin Franz, Md Arafat Sultan, Omar Khattab, Radu Florian, Salim Roukos","submitted_at":"2023-03-01T20:21:23Z","abstract_excerpt":"Many information retrieval tasks require large labeled datasets for fine-tuning. However, such datasets are often unavailable, and their utility for real-world applications can diminish quickly due to domain shifts. To address this challenge, we develop and motivate a method for using large language models (LLMs) to generate large numbers of synthetic queries cheaply. The method begins by generating a small number of synthetic queries using an expensive LLM. After that, a much less expensive one is used to create large numbers of synthetic queries, which are used to fine-tune a family of reran"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.00807","kind":"arxiv","version":3},"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/2303.00807/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":"2303.00807","created_at":"2026-07-05T07:00:21.646100+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.00807v3","created_at":"2026-07-05T07:00:21.646100+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.00807","created_at":"2026-07-05T07:00:21.646100+00:00"},{"alias_kind":"pith_short_12","alias_value":"2AI3B6MIPWAN","created_at":"2026-07-05T07:00:21.646100+00:00"},{"alias_kind":"pith_short_16","alias_value":"2AI3B6MIPWANR5YO","created_at":"2026-07-05T07:00:21.646100+00:00"},{"alias_kind":"pith_short_8","alias_value":"2AI3B6MI","created_at":"2026-07-05T07:00:21.646100+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2AI3B6MIPWANR5YODQUKCDJEAX","json":"https://pith.science/pith/2AI3B6MIPWANR5YODQUKCDJEAX.json","graph_json":"https://pith.science/api/pith-number/2AI3B6MIPWANR5YODQUKCDJEAX/graph.json","events_json":"https://pith.science/api/pith-number/2AI3B6MIPWANR5YODQUKCDJEAX/events.json","paper":"https://pith.science/paper/2AI3B6MI"},"agent_actions":{"view_html":"https://pith.science/pith/2AI3B6MIPWANR5YODQUKCDJEAX","download_json":"https://pith.science/pith/2AI3B6MIPWANR5YODQUKCDJEAX.json","view_paper":"https://pith.science/paper/2AI3B6MI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.00807&json=true","fetch_graph":"https://pith.science/api/pith-number/2AI3B6MIPWANR5YODQUKCDJEAX/graph.json","fetch_events":"https://pith.science/api/pith-number/2AI3B6MIPWANR5YODQUKCDJEAX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2AI3B6MIPWANR5YODQUKCDJEAX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2AI3B6MIPWANR5YODQUKCDJEAX/action/storage_attestation","attest_author":"https://pith.science/pith/2AI3B6MIPWANR5YODQUKCDJEAX/action/author_attestation","sign_citation":"https://pith.science/pith/2AI3B6MIPWANR5YODQUKCDJEAX/action/citation_signature","submit_replication":"https://pith.science/pith/2AI3B6MIPWANR5YODQUKCDJEAX/action/replication_record"}},"created_at":"2026-07-05T07:00:21.646100+00:00","updated_at":"2026-07-05T07:00:21.646100+00:00"}