{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EB6HDFZLFDIAXPE4FZV6PTOP4Q","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":"d64ca422ca91c0cfed8032c35334dc558451f8699f9a16bdb7fd93dad62b453e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T10:56:45Z","title_canon_sha256":"c5eaeda72321e8ef2ae354aa23b70f8c1d835a23b9ce81319e5016db7c4d645c"},"schema_version":"1.0","source":{"id":"2605.25698","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.25698","created_at":"2026-05-26T02:04:51Z"},{"alias_kind":"arxiv_version","alias_value":"2605.25698v1","created_at":"2026-05-26T02:04:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25698","created_at":"2026-05-26T02:04:51Z"},{"alias_kind":"pith_short_12","alias_value":"EB6HDFZLFDIA","created_at":"2026-05-26T02:04:51Z"},{"alias_kind":"pith_short_16","alias_value":"EB6HDFZLFDIAXPE4","created_at":"2026-05-26T02:04:51Z"},{"alias_kind":"pith_short_8","alias_value":"EB6HDFZL","created_at":"2026-05-26T02:04:51Z"}],"graph_snapshots":[{"event_id":"sha256:50c4a8e3a4e4ee0b51055f6a8ca57e301998a79c3ec0a8626731e5ed4b93b2ba","target":"graph","created_at":"2026-05-26T02:04:51Z","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/2605.25698/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"High-quality data is scarce in large language model (LLM) training, yet how to schedule its use jointly with training dynamics lacks theoretical guidance. We extend functional scaling laws by incorporating a data-quality dimension, and solve the joint data-quality and batch-size scheduling problem in asymptotic closed form. The solution reveals two regimes and a dual role of high-quality data. In the noise-limited regime, high-quality data should be used as a signal amplifier: lowering the batch size converts cleaner data into more signal without amplifying noise. In the signal-limited regime,","authors_text":"Jiawei Fu, Shizhe Wu, Xiaoqing Liu, Xili Wang, Zhitao Zhu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T10:56:45Z","title":"How Should LLMs Consume High-Quality Data? Optimal Data Scheduling via Quality-Aware Functional Scaling Laws"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25698","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":"sha256:596ab2c0fec82da639331c3a5887d8098e22a6ad57e7971485f3f5eef291be15","target":"record","created_at":"2026-05-26T02:04:51Z","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":"d64ca422ca91c0cfed8032c35334dc558451f8699f9a16bdb7fd93dad62b453e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T10:56:45Z","title_canon_sha256":"c5eaeda72321e8ef2ae354aa23b70f8c1d835a23b9ce81319e5016db7c4d645c"},"schema_version":"1.0","source":{"id":"2605.25698","kind":"arxiv","version":1}},"canonical_sha256":"207c71972b28d00bbc9c2e6be7cdcfe419501ba4a5ef6225c2e9a0ac2a18d323","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"207c71972b28d00bbc9c2e6be7cdcfe419501ba4a5ef6225c2e9a0ac2a18d323","first_computed_at":"2026-05-26T02:04:51.107202Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:04:51.107202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KmuZ8oLDiOGQCK2J6bWif31aqeiN70xr/wiC+wzznzEB5vFzKt7p9zzG8aWRHhqMeN7hhUaXi36YHrsViR4iAQ==","signature_status":"signed_v1","signed_at":"2026-05-26T02:04:51.107924Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.25698","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:596ab2c0fec82da639331c3a5887d8098e22a6ad57e7971485f3f5eef291be15","sha256:50c4a8e3a4e4ee0b51055f6a8ca57e301998a79c3ec0a8626731e5ed4b93b2ba"],"state_sha256":"90b55088c061db3c49d80b356f0a0e2723e8cebfb6f2039117db83e288b892a6"}