{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F4SWDZF77MV6NPUJRDIVZHAZXL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"02527972a9653184e50f320f93f3115d19f5cb7472d48d96039f104fa4b78947","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-20T08:58:58Z","title_canon_sha256":"033a85d6c670e4424eb01a44ddc5ee5b034c8b0a6a6a7dad7b2d798cc8f9ecc0"},"schema_version":"1.0","source":{"id":"2406.14115","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.14115","created_at":"2026-07-05T10:18:38Z"},{"alias_kind":"arxiv_version","alias_value":"2406.14115v2","created_at":"2026-07-05T10:18:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14115","created_at":"2026-07-05T10:18:38Z"},{"alias_kind":"pith_short_12","alias_value":"F4SWDZF77MV6","created_at":"2026-07-05T10:18:38Z"},{"alias_kind":"pith_short_16","alias_value":"F4SWDZF77MV6NPUJ","created_at":"2026-07-05T10:18:38Z"},{"alias_kind":"pith_short_8","alias_value":"F4SWDZF7","created_at":"2026-07-05T10:18:38Z"}],"graph_snapshots":[{"event_id":"sha256:435729e0a7986b711ac66efa180d7168755bcd3712d8be82ea2203f95dc42366","target":"graph","created_at":"2026-07-05T10:18:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2406.14115/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data selection for fine-tuning large language models (LLMs) aims to choose a high-quality subset from existing datasets, allowing the trained model to outperform baselines trained on the full dataset. However, the expanding body of research lacks a clear, unified framework, and the variability in experimental settings complicates systematic comparisons. While existing surveys comprehensively overview the stages and methods of data selection, they often overlook an in-depth exploration of the fine-tuning phase. In this paper, we conduct a focused review of recent data selection techniques for f","authors_text":"Feng Jiang, Haizhou Li, Rui Ke, Yajiao Liu, Ziche Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-20T08:58:58Z","title":"Take the essence and discard the dross: A Rethinking on Data Selection for Fine-Tuning Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14115","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:24625ebf93efc55963c81e7992755d854b5b43832dfcce56213169217e8af811","target":"record","created_at":"2026-07-05T10:18:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"02527972a9653184e50f320f93f3115d19f5cb7472d48d96039f104fa4b78947","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-20T08:58:58Z","title_canon_sha256":"033a85d6c670e4424eb01a44ddc5ee5b034c8b0a6a6a7dad7b2d798cc8f9ecc0"},"schema_version":"1.0","source":{"id":"2406.14115","kind":"arxiv","version":2}},"canonical_sha256":"2f2561e4bffb2be6be8988d15c9c19bafa276e496072c464ef4cc875bc769ffb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f2561e4bffb2be6be8988d15c9c19bafa276e496072c464ef4cc875bc769ffb","first_computed_at":"2026-07-05T10:18:38.419938Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:18:38.419938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4rFFZl9j1Mdn3KAd77uj86FjoYLnC+SwiCWwbVFx5sXW35JzsR4vFujUo/JCJ7kX7rnGAebP5k/hFEDB77i0Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:18:38.420439Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.14115","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:24625ebf93efc55963c81e7992755d854b5b43832dfcce56213169217e8af811","sha256:435729e0a7986b711ac66efa180d7168755bcd3712d8be82ea2203f95dc42366"],"state_sha256":"d0831e076535542ddd8089131f72af80a22fe208111e32cc79454dd02c4a4a6b"}