{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SVXHQJTP434HUPHECUWJEO5M5F","short_pith_number":"pith:SVXHQJTP","schema_version":"1.0","canonical_sha256":"956e78266fe6f87a3ce4152c923bace950b81d258545f4e8d99b40952c65b963","source":{"kind":"arxiv","id":"2308.12032","version":5},"attestation_state":"computed","paper":{"title":"From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jianzong Wang, Jing Xiao, Jiuhai Chen, Lichang Chen, Ming Li, Ning Cheng, Tianyi Zhou, Yong Zhang, Zhitao Li","submitted_at":"2023-08-23T09:45:29Z","abstract_excerpt":"In the realm of Large Language Models (LLMs), the balance between instruction data quality and quantity is a focal point. Recognizing this, we introduce a self-guided methodology for LLMs to autonomously discern and select cherry samples from open-source datasets, effectively minimizing manual curation and potential cost for instruction tuning an LLM. Our key innovation, the Instruction-Following Difficulty (IFD) metric, emerges as a pivotal metric to identify discrepancies between a model's expected responses and its intrinsic generation capability. Through the application of IFD, cherry samp"},"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":"2308.12032","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-23T09:45:29Z","cross_cats_sorted":[],"title_canon_sha256":"1dba7979ed42b6cddc3135b0ebe0b7893b96bb39ccbae9c80e86f767749b66f1","abstract_canon_sha256":"047395a3d3647f754811dcccaa9d1e964ed3ffd0e429210fbf0b1af396282971"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:01.294580Z","signature_b64":"fIrYsWlteE6TFiyed0vx/zYk8xXOqBgvsceWe2bqSdJ/sKuTa9HtC2WoEH2+3+oEL3/Vso4JfwNpwZ3FTvTFBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"956e78266fe6f87a3ce4152c923bace950b81d258545f4e8d99b40952c65b963","last_reissued_at":"2026-07-05T08:05:01.294065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:01.294065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jianzong Wang, Jing Xiao, Jiuhai Chen, Lichang Chen, Ming Li, Ning Cheng, Tianyi Zhou, Yong Zhang, Zhitao Li","submitted_at":"2023-08-23T09:45:29Z","abstract_excerpt":"In the realm of Large Language Models (LLMs), the balance between instruction data quality and quantity is a focal point. Recognizing this, we introduce a self-guided methodology for LLMs to autonomously discern and select cherry samples from open-source datasets, effectively minimizing manual curation and potential cost for instruction tuning an LLM. Our key innovation, the Instruction-Following Difficulty (IFD) metric, emerges as a pivotal metric to identify discrepancies between a model's expected responses and its intrinsic generation capability. Through the application of IFD, cherry samp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.12032","kind":"arxiv","version":5},"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/2308.12032/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":"2308.12032","created_at":"2026-07-05T08:05:01.294133+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.12032v5","created_at":"2026-07-05T08:05:01.294133+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.12032","created_at":"2026-07-05T08:05:01.294133+00:00"},{"alias_kind":"pith_short_12","alias_value":"SVXHQJTP434H","created_at":"2026-07-05T08:05:01.294133+00:00"},{"alias_kind":"pith_short_16","alias_value":"SVXHQJTP434HUPHE","created_at":"2026-07-05T08:05:01.294133+00:00"},{"alias_kind":"pith_short_8","alias_value":"SVXHQJTP","created_at":"2026-07-05T08:05:01.294133+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26761","citing_title":"Once-For-All: A Train-Once and Select-Anytime Framework for Multimodal Instruction Tuning","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2502.10248","citing_title":"Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model","ref_index":100,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21166","citing_title":"The Ratchet Effect in Silico: How Interaction Drives Cumulative Intelligence in Large Language Models","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2502.16982","citing_title":"Muon is Scalable for LLM Training","ref_index":75,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SVXHQJTP434HUPHECUWJEO5M5F","json":"https://pith.science/pith/SVXHQJTP434HUPHECUWJEO5M5F.json","graph_json":"https://pith.science/api/pith-number/SVXHQJTP434HUPHECUWJEO5M5F/graph.json","events_json":"https://pith.science/api/pith-number/SVXHQJTP434HUPHECUWJEO5M5F/events.json","paper":"https://pith.science/paper/SVXHQJTP"},"agent_actions":{"view_html":"https://pith.science/pith/SVXHQJTP434HUPHECUWJEO5M5F","download_json":"https://pith.science/pith/SVXHQJTP434HUPHECUWJEO5M5F.json","view_paper":"https://pith.science/paper/SVXHQJTP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.12032&json=true","fetch_graph":"https://pith.science/api/pith-number/SVXHQJTP434HUPHECUWJEO5M5F/graph.json","fetch_events":"https://pith.science/api/pith-number/SVXHQJTP434HUPHECUWJEO5M5F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SVXHQJTP434HUPHECUWJEO5M5F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SVXHQJTP434HUPHECUWJEO5M5F/action/storage_attestation","attest_author":"https://pith.science/pith/SVXHQJTP434HUPHECUWJEO5M5F/action/author_attestation","sign_citation":"https://pith.science/pith/SVXHQJTP434HUPHECUWJEO5M5F/action/citation_signature","submit_replication":"https://pith.science/pith/SVXHQJTP434HUPHECUWJEO5M5F/action/replication_record"}},"created_at":"2026-07-05T08:05:01.294133+00:00","updated_at":"2026-07-05T08:05:01.294133+00:00"}