{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:U37PKMTP3YRYGYOYWJXIJD3XYK","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":"056a4dbc0c63fd648fe77b68342ba0f1c1b18ae15bef87928f05992ec048d57a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T03:54:58Z","title_canon_sha256":"60766570892eba5bb490a9e1569100798a3fea5f8bdf8ed63d85e15200f7ea9d"},"schema_version":"1.0","source":{"id":"2607.22769","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22769","created_at":"2026-07-28T00:21:53Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22769v1","created_at":"2026-07-28T00:21:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22769","created_at":"2026-07-28T00:21:53Z"},{"alias_kind":"pith_short_12","alias_value":"U37PKMTP3YRY","created_at":"2026-07-28T00:21:53Z"},{"alias_kind":"pith_short_16","alias_value":"U37PKMTP3YRYGYOY","created_at":"2026-07-28T00:21:53Z"},{"alias_kind":"pith_short_8","alias_value":"U37PKMTP","created_at":"2026-07-28T00:21:53Z"}],"graph_snapshots":[{"event_id":"sha256:b1686a93b7515d50b544942ade48d4eddff240de5ec2ad318d997d17325de036","target":"graph","created_at":"2026-07-28T00:21:53Z","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/2607.22769/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The training efficacy of large language models (LLMs) is fundamentally constrained by the quality and composition of training data. Existing dynamic data scheduling methods face critical limitations in industrial-scale pretraining and supervised fine-tuning (SFT): data selection incurs prohibitive O(N) costs on terabyte-scale corpora, mixture optimization schemes introduce severe I/O bottlenecks or require training auxiliary reference models, and sample-level reweighting strategies rely on loss signals that conflate noise, difficulty, and novelty.\n  We present DomainPilot, a domain-level loss-","authors_text":"He Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T03:54:58Z","title":"DomainPilot: Domain-Level Loss-Guided Two-Stage Data Mixture Optimization for Efficient Language Model Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22769","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:f7b359956333270e1e3e36033181af6f2c6d111ddc69a9d77fd29603117339a0","target":"record","created_at":"2026-07-28T00:21:53Z","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":"056a4dbc0c63fd648fe77b68342ba0f1c1b18ae15bef87928f05992ec048d57a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T03:54:58Z","title_canon_sha256":"60766570892eba5bb490a9e1569100798a3fea5f8bdf8ed63d85e15200f7ea9d"},"schema_version":"1.0","source":{"id":"2607.22769","kind":"arxiv","version":1}},"canonical_sha256":"a6fef5326fde238361d8b26e848f77c2be8ad650f6fb962893c017d9558fc5b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a6fef5326fde238361d8b26e848f77c2be8ad650f6fb962893c017d9558fc5b1","first_computed_at":"2026-07-28T00:21:53.440102Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T00:21:53.440102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ueVvDl+VLXd/5qjUCfDTum6ToFcV2zmNMGa47NAkLZLLeX8+BHr4UFZCJfG1GI/pu8GMX6KbMpfbR6h1giWUCQ==","signature_status":"signed_v1","signed_at":"2026-07-28T00:21:53.440906Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.22769","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f7b359956333270e1e3e36033181af6f2c6d111ddc69a9d77fd29603117339a0","sha256:b1686a93b7515d50b544942ade48d4eddff240de5ec2ad318d997d17325de036"],"state_sha256":"613726c467d593751b4c7e76a2a0869aa0611322d248c75f5b485eb88cf1a948"}