{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QTJGAUGHWPJF7TS6AO4IIBA3RP","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":"9bd95205037c05b650e01702bd7142f2c651cd1f7ca8dbe9aac2b602f5e56778","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-09T16:02:23Z","title_canon_sha256":"05ac7fb5cd4da151cfb073a70370c9c2d698939591d5493cd8f040819911cc64"},"schema_version":"1.0","source":{"id":"2505.06150","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.06150","created_at":"2026-07-05T11:14:28Z"},{"alias_kind":"arxiv_version","alias_value":"2505.06150v2","created_at":"2026-07-05T11:14:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06150","created_at":"2026-07-05T11:14:28Z"},{"alias_kind":"pith_short_12","alias_value":"QTJGAUGHWPJF","created_at":"2026-07-05T11:14:28Z"},{"alias_kind":"pith_short_16","alias_value":"QTJGAUGHWPJF7TS6","created_at":"2026-07-05T11:14:28Z"},{"alias_kind":"pith_short_8","alias_value":"QTJGAUGH","created_at":"2026-07-05T11:14:28Z"}],"graph_snapshots":[{"event_id":"sha256:dce11f14ddbe18fff1a54e04ee204d1d09fd4191b6d805d2e139e22ffc4cfcfa","target":"graph","created_at":"2026-07-05T11:14:28Z","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/2505.06150/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a scaling law for fine-tuning large language models (LLMs) under fixed compute budgets that explicitly accounts for data composition. Conventional approaches measure training data solely by total tokens, yet the number of examples and their average token length -- what we term \\emph{dataset volume} -- play a decisive role in model performance. Our formulation is tuned following established procedures. Experiments on the BRICC dataset \\cite{salavati2024reducing} and subsets of the MMLU dataset \\cite{hendrycks2021measuringmassivemultitasklanguage}, evaluated under multiple subsampli","authors_text":"Aidan Kierans, Avijit Ghosh, Ryan Lagasse, Shiri Dori-Hacohen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-09T16:02:23Z","title":"A Scaling Law for Token Efficiency in LLM Fine-Tuning Under Fixed Compute Budgets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06150","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":"sha256:5fa46d06f7d0cb38c5d688bbb84ce5fe26b435d0627029a008faf00639415e13","target":"record","created_at":"2026-07-05T11:14:28Z","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":"9bd95205037c05b650e01702bd7142f2c651cd1f7ca8dbe9aac2b602f5e56778","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-09T16:02:23Z","title_canon_sha256":"05ac7fb5cd4da151cfb073a70370c9c2d698939591d5493cd8f040819911cc64"},"schema_version":"1.0","source":{"id":"2505.06150","kind":"arxiv","version":2}},"canonical_sha256":"84d26050c7b3d25fce5e03b884041b8bd814e1fe582a64501429c030261335ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"84d26050c7b3d25fce5e03b884041b8bd814e1fe582a64501429c030261335ca","first_computed_at":"2026-07-05T11:14:28.919373Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:28.919373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z26b7CGb7eiU3/DNIK2Dx2nfwESEgs7f9uFcdIFdBUEuesQkS06owWj6GsU4vGszjENgi/uYm4fm50gLUsOjDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:28.919851Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.06150","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5fa46d06f7d0cb38c5d688bbb84ce5fe26b435d0627029a008faf00639415e13","sha256:dce11f14ddbe18fff1a54e04ee204d1d09fd4191b6d805d2e139e22ffc4cfcfa"],"state_sha256":"fea141fa29a211c1da509ae55ca507418c46b687c1bc4fe8311876857629dd36"}