{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:C3VURN3KYQYV4RIHPY7GQOPNJS","short_pith_number":"pith:C3VURN3K","schema_version":"1.0","canonical_sha256":"16eb48b76ac4315e45077e3e6839ed4ca46222bcd3dec54a052354650ba086ca","source":{"kind":"arxiv","id":"2311.08182","version":1},"attestation_state":"computed","paper":{"title":"Self-Evolved Diverse Data Sampling for Efficient Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Benfeng Xu, Chang Zhou, Junyang Lin, Keming Lu, Qi Su, Shengguang Wu","submitted_at":"2023-11-14T14:10:40Z","abstract_excerpt":"Enhancing the instruction-following ability of Large Language Models (LLMs) primarily demands substantial instruction-tuning datasets. However, the sheer volume of these imposes a considerable computational burden and annotation cost. To investigate a label-efficient instruction tuning method that allows the model itself to actively sample subsets that are equally or even more effective, we introduce a self-evolving mechanism DiverseEvol. In this process, a model iteratively augments its training subset to refine its own performance, without requiring any intervention from humans or more advan"},"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":"2311.08182","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-14T14:10:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ee25c20575b1cf36e0a6c78d4fd41d4d69d0ae1d85e06f085364bccf42c8cdaa","abstract_canon_sha256":"67a8a4895d635cd50d72a252a2a7106fc587fcace830e2ac555ea4a44ee634b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:41.336490Z","signature_b64":"TRVyjG7DupmAgrHR/ztB66IWuaSU+mmEyXhF7qzrebpdAE0Z1vRWo6npOkwfkFBczKoVjtEg/8HrhgfK17eJCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16eb48b76ac4315e45077e3e6839ed4ca46222bcd3dec54a052354650ba086ca","last_reissued_at":"2026-07-05T07:12:41.336060Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:41.336060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Evolved Diverse Data Sampling for Efficient Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Benfeng Xu, Chang Zhou, Junyang Lin, Keming Lu, Qi Su, Shengguang Wu","submitted_at":"2023-11-14T14:10:40Z","abstract_excerpt":"Enhancing the instruction-following ability of Large Language Models (LLMs) primarily demands substantial instruction-tuning datasets. However, the sheer volume of these imposes a considerable computational burden and annotation cost. To investigate a label-efficient instruction tuning method that allows the model itself to actively sample subsets that are equally or even more effective, we introduce a self-evolving mechanism DiverseEvol. In this process, a model iteratively augments its training subset to refine its own performance, without requiring any intervention from humans or more advan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.08182","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/2311.08182/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":"2311.08182","created_at":"2026-07-05T07:12:41.336116+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.08182v1","created_at":"2026-07-05T07:12:41.336116+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.08182","created_at":"2026-07-05T07:12:41.336116+00:00"},{"alias_kind":"pith_short_12","alias_value":"C3VURN3KYQYV","created_at":"2026-07-05T07:12:41.336116+00:00"},{"alias_kind":"pith_short_16","alias_value":"C3VURN3KYQYV4RIH","created_at":"2026-07-05T07:12:41.336116+00:00"},{"alias_kind":"pith_short_8","alias_value":"C3VURN3K","created_at":"2026-07-05T07:12:41.336116+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07690","citing_title":"HARP: Efficient Data Selection for Finetuning Large Language Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2503.21460","citing_title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22564","citing_title":"SynAE: A Framework for Measuring the Quality of Synthetic Data for Tool-Calling Agent Evaluations","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2508.04149","citing_title":"Difficulty-Based Preference Data Selection by DPO Implicit Reward Gap","ref_index":36,"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":102,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C3VURN3KYQYV4RIHPY7GQOPNJS","json":"https://pith.science/pith/C3VURN3KYQYV4RIHPY7GQOPNJS.json","graph_json":"https://pith.science/api/pith-number/C3VURN3KYQYV4RIHPY7GQOPNJS/graph.json","events_json":"https://pith.science/api/pith-number/C3VURN3KYQYV4RIHPY7GQOPNJS/events.json","paper":"https://pith.science/paper/C3VURN3K"},"agent_actions":{"view_html":"https://pith.science/pith/C3VURN3KYQYV4RIHPY7GQOPNJS","download_json":"https://pith.science/pith/C3VURN3KYQYV4RIHPY7GQOPNJS.json","view_paper":"https://pith.science/paper/C3VURN3K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.08182&json=true","fetch_graph":"https://pith.science/api/pith-number/C3VURN3KYQYV4RIHPY7GQOPNJS/graph.json","fetch_events":"https://pith.science/api/pith-number/C3VURN3KYQYV4RIHPY7GQOPNJS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C3VURN3KYQYV4RIHPY7GQOPNJS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C3VURN3KYQYV4RIHPY7GQOPNJS/action/storage_attestation","attest_author":"https://pith.science/pith/C3VURN3KYQYV4RIHPY7GQOPNJS/action/author_attestation","sign_citation":"https://pith.science/pith/C3VURN3KYQYV4RIHPY7GQOPNJS/action/citation_signature","submit_replication":"https://pith.science/pith/C3VURN3KYQYV4RIHPY7GQOPNJS/action/replication_record"}},"created_at":"2026-07-05T07:12:41.336116+00:00","updated_at":"2026-07-05T07:12:41.336116+00:00"}