{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Y5TGWAMU5PB3RVLQMSMI5XFDHD","short_pith_number":"pith:Y5TGWAMU","schema_version":"1.0","canonical_sha256":"c7666b0194ebc3b8d57064988edca338f43eeaf9080d0e6950299097d07c5480","source":{"kind":"arxiv","id":"2402.17355","version":1},"attestation_state":"computed","paper":{"title":"RECOST: External Knowledge Guided Data-efficient Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haobo Wang, Junbo Zhao, Qi Zhang, Yiming Zhang","submitted_at":"2024-02-27T09:47:36Z","abstract_excerpt":"In the current landscape of large language models (LLMs), the process of instruction tuning serves as an essential step. Considering the high computing power overhead, data-efficient instruction tuning was proposed to reduce the training data size in this process, aiming at selecting high-quality instructional data. Nevertheless, we argue that most current data-efficient instruction-tuning methods are highly dependent on the quality of the original instruction-tuning dataset. When it comes to datasets synthesized by LLMs, a common scenario in this field, dirty samples will even be selected wit"},"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":"2402.17355","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-27T09:47:36Z","cross_cats_sorted":[],"title_canon_sha256":"a576fec7dd7045adf6a12867b8b2eb9ea8ea34731a2ff1b27007b96c08492249","abstract_canon_sha256":"916d126b4aaa6dbad443f967450de666348507eb661ceb13fc89391a2342fb1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:20.846401Z","signature_b64":"a5QLUhTM/9ZMlmp7xgamIS1JFVFxUfeoG0UsJq0pKiqPV/EDJij4xYIX2grINtIJ34e9D3Q/mcRcHORjEWUvBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7666b0194ebc3b8d57064988edca338f43eeaf9080d0e6950299097d07c5480","last_reissued_at":"2026-07-05T09:56:20.845968Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:20.845968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RECOST: External Knowledge Guided Data-efficient Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haobo Wang, Junbo Zhao, Qi Zhang, Yiming Zhang","submitted_at":"2024-02-27T09:47:36Z","abstract_excerpt":"In the current landscape of large language models (LLMs), the process of instruction tuning serves as an essential step. Considering the high computing power overhead, data-efficient instruction tuning was proposed to reduce the training data size in this process, aiming at selecting high-quality instructional data. Nevertheless, we argue that most current data-efficient instruction-tuning methods are highly dependent on the quality of the original instruction-tuning dataset. When it comes to datasets synthesized by LLMs, a common scenario in this field, dirty samples will even be selected wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17355","kind":"arxiv","version":1},"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/2402.17355/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":"2402.17355","created_at":"2026-07-05T09:56:20.846028+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.17355v1","created_at":"2026-07-05T09:56:20.846028+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17355","created_at":"2026-07-05T09:56:20.846028+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y5TGWAMU5PB3","created_at":"2026-07-05T09:56:20.846028+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y5TGWAMU5PB3RVLQ","created_at":"2026-07-05T09:56:20.846028+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y5TGWAMU","created_at":"2026-07-05T09:56:20.846028+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.05327","citing_title":"RICo: Refined In-Context Contribution for Automatic Instruction-Tuning Data Selection","ref_index":85,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y5TGWAMU5PB3RVLQMSMI5XFDHD","json":"https://pith.science/pith/Y5TGWAMU5PB3RVLQMSMI5XFDHD.json","graph_json":"https://pith.science/api/pith-number/Y5TGWAMU5PB3RVLQMSMI5XFDHD/graph.json","events_json":"https://pith.science/api/pith-number/Y5TGWAMU5PB3RVLQMSMI5XFDHD/events.json","paper":"https://pith.science/paper/Y5TGWAMU"},"agent_actions":{"view_html":"https://pith.science/pith/Y5TGWAMU5PB3RVLQMSMI5XFDHD","download_json":"https://pith.science/pith/Y5TGWAMU5PB3RVLQMSMI5XFDHD.json","view_paper":"https://pith.science/paper/Y5TGWAMU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.17355&json=true","fetch_graph":"https://pith.science/api/pith-number/Y5TGWAMU5PB3RVLQMSMI5XFDHD/graph.json","fetch_events":"https://pith.science/api/pith-number/Y5TGWAMU5PB3RVLQMSMI5XFDHD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y5TGWAMU5PB3RVLQMSMI5XFDHD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y5TGWAMU5PB3RVLQMSMI5XFDHD/action/storage_attestation","attest_author":"https://pith.science/pith/Y5TGWAMU5PB3RVLQMSMI5XFDHD/action/author_attestation","sign_citation":"https://pith.science/pith/Y5TGWAMU5PB3RVLQMSMI5XFDHD/action/citation_signature","submit_replication":"https://pith.science/pith/Y5TGWAMU5PB3RVLQMSMI5XFDHD/action/replication_record"}},"created_at":"2026-07-05T09:56:20.846028+00:00","updated_at":"2026-07-05T09:56:20.846028+00:00"}