{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NJPUXRYRF65RGE236L6G7YLY2G","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":"b2b091433ca5315bdf940b7c025d8d988301582400259a0d93748f6367547baa","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T21:36:00Z","title_canon_sha256":"902076e8b79ba57fd8457588baa84cd3bd64699d47b883426e9d426057b2bbb1"},"schema_version":"1.0","source":{"id":"2407.13906","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.13906","created_at":"2026-07-05T08:45:55Z"},{"alias_kind":"arxiv_version","alias_value":"2407.13906v1","created_at":"2026-07-05T08:45:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13906","created_at":"2026-07-05T08:45:55Z"},{"alias_kind":"pith_short_12","alias_value":"NJPUXRYRF65R","created_at":"2026-07-05T08:45:55Z"},{"alias_kind":"pith_short_16","alias_value":"NJPUXRYRF65RGE23","created_at":"2026-07-05T08:45:55Z"},{"alias_kind":"pith_short_8","alias_value":"NJPUXRYR","created_at":"2026-07-05T08:45:55Z"}],"graph_snapshots":[{"event_id":"sha256:346dadcdd8a367db6d642c7da6bb69be0d9f03bb823ea5678d569c4bc9a7fb25","target":"graph","created_at":"2026-07-05T08:45:55Z","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/2407.13906/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper addresses the challenges of efficiently fine-tuning large language models (LLMs) by exploring data efficiency and hyperparameter optimization. We investigate the minimum data required for effective fine-tuning and propose a novel hyperparameter optimization method that leverages early-stage model performance. Our experiments demonstrate that fine-tuning with as few as 200 samples can improve model accuracy from 70\\% to 88\\% in a product attribute extraction task. We identify a saturation point of approximately 6,500 samples, beyond which additional data yields diminishing returns. O","authors_text":"Guan Wang, Michael Oliver","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T21:36:00Z","title":"Crafting Efficient Fine-Tuning Strategies for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13906","kind":"arxiv","version":1},"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:af6f10397bcc8da77736f1b6a235a812e478d7554db4d6514d74aeeba018ff16","target":"record","created_at":"2026-07-05T08:45:55Z","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":"b2b091433ca5315bdf940b7c025d8d988301582400259a0d93748f6367547baa","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T21:36:00Z","title_canon_sha256":"902076e8b79ba57fd8457588baa84cd3bd64699d47b883426e9d426057b2bbb1"},"schema_version":"1.0","source":{"id":"2407.13906","kind":"arxiv","version":1}},"canonical_sha256":"6a5f4bc7112fbb13135bf2fc6fe178d1bf9590398d188a6fc6485743dfbfe540","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a5f4bc7112fbb13135bf2fc6fe178d1bf9590398d188a6fc6485743dfbfe540","first_computed_at":"2026-07-05T08:45:55.312841Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:55.312841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dTv3JWkEmOTKyfTLNon4+KOSB0TgcPGb8YfMc5thYX59+r3yyv1ksj48bKU35OD3aPcxDqr7lerOOb9SwuFaCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:55.313339Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.13906","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:af6f10397bcc8da77736f1b6a235a812e478d7554db4d6514d74aeeba018ff16","sha256:346dadcdd8a367db6d642c7da6bb69be0d9f03bb823ea5678d569c4bc9a7fb25"],"state_sha256":"eb07f0bf1d151f2ae200ede30c0fe652522e5276fa5f7b25b238bc34cfb0c785"}