{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WZYRFJ5G2XVW5FRBIL3JF3RA43","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":"ee8c74e34083331359e04241b823525d86a73111269251f0a12b4332dbcebc30","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-12T07:45:33Z","title_canon_sha256":"1a2a426d71df32a6cda846629802277754416fc3c67d64c722f4c64d7175af8e"},"schema_version":"1.0","source":{"id":"2403.07384","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.07384","created_at":"2026-07-05T09:44:49Z"},{"alias_kind":"arxiv_version","alias_value":"2403.07384v2","created_at":"2026-07-05T09:44:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.07384","created_at":"2026-07-05T09:44:49Z"},{"alias_kind":"pith_short_12","alias_value":"WZYRFJ5G2XVW","created_at":"2026-07-05T09:44:49Z"},{"alias_kind":"pith_short_16","alias_value":"WZYRFJ5G2XVW5FRB","created_at":"2026-07-05T09:44:49Z"},{"alias_kind":"pith_short_8","alias_value":"WZYRFJ5G","created_at":"2026-07-05T09:44:49Z"}],"graph_snapshots":[{"event_id":"sha256:8f30e7d8707b22bf0e581e3556fb1bdcfb23db0f40f15daab6a5aed5b0687984","target":"graph","created_at":"2026-07-05T09:44:49Z","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/2403.07384/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the effectiveness of data selection for large language models (LLMs) during pretraining and instruction fine-tuning phases, improving data efficiency in supervised fine-tuning (SFT) for specialized domains poses significant challenges due to the complexity of fine-tuning data. To bridge this gap, we introduce an effective and scalable data selection method for SFT, SmallToLarge (S2L), which leverages training trajectories from small models to guide the data selection for larger models. We demonstrate through extensive experiments that S2L significantly improves data efficiency in SFT f","authors_text":"Baharan Mirzasoleiman, Jeffrey N Chiang, Siddhartha Mishra, Yu Yang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-12T07:45:33Z","title":"SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.07384","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":"sha256:0a21afbb2c5439af75d1f7c43ccd0e7634cf5926e3466e95161f95de7bcca94e","target":"record","created_at":"2026-07-05T09:44:49Z","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":"ee8c74e34083331359e04241b823525d86a73111269251f0a12b4332dbcebc30","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-12T07:45:33Z","title_canon_sha256":"1a2a426d71df32a6cda846629802277754416fc3c67d64c722f4c64d7175af8e"},"schema_version":"1.0","source":{"id":"2403.07384","kind":"arxiv","version":2}},"canonical_sha256":"b67112a7a6d5eb6e962142f692ee20e6e8749c5218dc1b13162d8b3d6c1573fb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b67112a7a6d5eb6e962142f692ee20e6e8749c5218dc1b13162d8b3d6c1573fb","first_computed_at":"2026-07-05T09:44:49.865742Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:44:49.865742Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RhocFznpUFV2fX23ht+eEED8hiCaLz6V9xoXhXiFaRFS/5AcZgVWRtWX0K1mYgZdjOhS3kFQropUaVX5xipTAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:44:49.866305Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.07384","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a21afbb2c5439af75d1f7c43ccd0e7634cf5926e3466e95161f95de7bcca94e","sha256:8f30e7d8707b22bf0e581e3556fb1bdcfb23db0f40f15daab6a5aed5b0687984"],"state_sha256":"2e47578ffd254ffab4b55715bddc11aae39d6201ab4e74a61a26cb13cbafb898"}