{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:T2QKZ2GM2QB5U3BVK5X4YZDRFZ","short_pith_number":"pith:T2QKZ2GM","schema_version":"1.0","canonical_sha256":"9ea0ace8ccd403da6c35576fcc64712e73ded7e53e013e68383c42269820e8fd","source":{"kind":"arxiv","id":"2305.15225","version":2},"attestation_state":"computed","paper":{"title":"SAIL: Search-Augmented Instruction Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Danny Fox, Helen Meng, Hongyin Luo, James Glass, Tianhua Zhang, Xixin Wu, Yoon Kim, Yuan Gong, Yung-Sung Chuang","submitted_at":"2023-05-24T15:07:30Z","abstract_excerpt":"Large language models (LLMs) have been significantly improved by instruction fine-tuning, but still lack transparency and the ability to utilize up-to-date knowledge and information. In this work, we propose search-augmented instruction learning (SAIL), which grounds the language generation and instruction following abilities on complex search results generated by in-house and external search engines. With an instruction tuning corpus, we collect search results for each training case from different search APIs and domains, and construct a new search-grounded training set containing \\textit{(in"},"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":"2305.15225","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T15:07:30Z","cross_cats_sorted":[],"title_canon_sha256":"69f3fa5094b8e62ef33988021844fe3a16510a985e51958352e4507c78b650ee","abstract_canon_sha256":"60251bd2a2bbf645a48b3f15a804822fa32d9b68c0c8ce89be9aaed16b4773db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:30.039547Z","signature_b64":"d84+WsuJLpXT3O0VDQ271Msavc2cVLmTstQoI0d7AVV5FkwT+/btEjfEMh8fpGLZaMt88ZKH8/sGWYNbI1mZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ea0ace8ccd403da6c35576fcc64712e73ded7e53e013e68383c42269820e8fd","last_reissued_at":"2026-07-05T06:24:30.039071Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:30.039071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAIL: Search-Augmented Instruction Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Danny Fox, Helen Meng, Hongyin Luo, James Glass, Tianhua Zhang, Xixin Wu, Yoon Kim, Yuan Gong, Yung-Sung Chuang","submitted_at":"2023-05-24T15:07:30Z","abstract_excerpt":"Large language models (LLMs) have been significantly improved by instruction fine-tuning, but still lack transparency and the ability to utilize up-to-date knowledge and information. In this work, we propose search-augmented instruction learning (SAIL), which grounds the language generation and instruction following abilities on complex search results generated by in-house and external search engines. With an instruction tuning corpus, we collect search results for each training case from different search APIs and domains, and construct a new search-grounded training set containing \\textit{(in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15225","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/2305.15225/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":"2305.15225","created_at":"2026-07-05T06:24:30.039126+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.15225v2","created_at":"2026-07-05T06:24:30.039126+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15225","created_at":"2026-07-05T06:24:30.039126+00:00"},{"alias_kind":"pith_short_12","alias_value":"T2QKZ2GM2QB5","created_at":"2026-07-05T06:24:30.039126+00:00"},{"alias_kind":"pith_short_16","alias_value":"T2QKZ2GM2QB5U3BV","created_at":"2026-07-05T06:24:30.039126+00:00"},{"alias_kind":"pith_short_8","alias_value":"T2QKZ2GM","created_at":"2026-07-05T06:24:30.039126+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2409.10102","citing_title":"Trustworthiness in Retrieval-Augmented Generation Systems: A Survey","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2506.04565","citing_title":"From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems","ref_index":110,"is_internal_anchor":false},{"citing_arxiv_id":"2402.13116","citing_title":"A Survey on Knowledge Distillation of Large Language Models","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2310.11511","citing_title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","ref_index":140,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20146","citing_title":"SAKE: Self-aware Knowledge Exploitation-Exploration for Grounded Multimodal Named Entity Recognition","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T2QKZ2GM2QB5U3BVK5X4YZDRFZ","json":"https://pith.science/pith/T2QKZ2GM2QB5U3BVK5X4YZDRFZ.json","graph_json":"https://pith.science/api/pith-number/T2QKZ2GM2QB5U3BVK5X4YZDRFZ/graph.json","events_json":"https://pith.science/api/pith-number/T2QKZ2GM2QB5U3BVK5X4YZDRFZ/events.json","paper":"https://pith.science/paper/T2QKZ2GM"},"agent_actions":{"view_html":"https://pith.science/pith/T2QKZ2GM2QB5U3BVK5X4YZDRFZ","download_json":"https://pith.science/pith/T2QKZ2GM2QB5U3BVK5X4YZDRFZ.json","view_paper":"https://pith.science/paper/T2QKZ2GM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.15225&json=true","fetch_graph":"https://pith.science/api/pith-number/T2QKZ2GM2QB5U3BVK5X4YZDRFZ/graph.json","fetch_events":"https://pith.science/api/pith-number/T2QKZ2GM2QB5U3BVK5X4YZDRFZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T2QKZ2GM2QB5U3BVK5X4YZDRFZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T2QKZ2GM2QB5U3BVK5X4YZDRFZ/action/storage_attestation","attest_author":"https://pith.science/pith/T2QKZ2GM2QB5U3BVK5X4YZDRFZ/action/author_attestation","sign_citation":"https://pith.science/pith/T2QKZ2GM2QB5U3BVK5X4YZDRFZ/action/citation_signature","submit_replication":"https://pith.science/pith/T2QKZ2GM2QB5U3BVK5X4YZDRFZ/action/replication_record"}},"created_at":"2026-07-05T06:24:30.039126+00:00","updated_at":"2026-07-05T06:24:30.039126+00:00"}