{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:U6DBM6LRRPIVFWEE43FCZXGU3P","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":"8e7320a461d6a4e1e4d76b3fb28ad250df48f31b537f77f76e7c1c90ed629e64","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-29T21:56:45Z","title_canon_sha256":"71e0bcdc1c7abbc9fe3d171c26493ae0b1c07fcfd68862fbff47f5ab4d6b467b"},"schema_version":"1.0","source":{"id":"2507.22250","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.22250","created_at":"2026-07-05T11:45:19Z"},{"alias_kind":"arxiv_version","alias_value":"2507.22250v1","created_at":"2026-07-05T11:45:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22250","created_at":"2026-07-05T11:45:19Z"},{"alias_kind":"pith_short_12","alias_value":"U6DBM6LRRPIV","created_at":"2026-07-05T11:45:19Z"},{"alias_kind":"pith_short_16","alias_value":"U6DBM6LRRPIVFWEE","created_at":"2026-07-05T11:45:19Z"},{"alias_kind":"pith_short_8","alias_value":"U6DBM6LR","created_at":"2026-07-05T11:45:19Z"}],"graph_snapshots":[{"event_id":"sha256:1d6811678b739307534db177c57d6d79b01e442419b61a1ce5e7259bf32016d6","target":"graph","created_at":"2026-07-05T11:45:19Z","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/2507.22250/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a framework for optimizing domain-specific dataset construction in foundation model training. Specifically, we seek a cost-efficient way to estimate the quality of data sources (e.g. synthetically generated or filtered web data, etc.) in order to make optimal decisions about resource allocation for data sourcing from these sources for the stage two pre-training phase, aka annealing, with the goal of specializing a generalist pre-trained model to specific domains. Our approach extends the usual point estimate approaches, aka micro-annealing, to estimating scaling laws by performing","authors_text":"Charles Guille-Escuret, Denis Kocetkov, Gopeshh Subbaraj, Joel Lamy-Poirier, Luke Kumar, Max Tian, Oleksiy Ostapenko, Raymond Li, Sebastien Paquet, Torsten Scholak","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-29T21:56:45Z","title":"Using Scaling Laws for Data Source Utility Estimation in Domain-Specific Pre-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22250","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:fb0ebe72c3fbeba089f7e0a53481c98fc7940bf1e8100d3ecb570c52b222df42","target":"record","created_at":"2026-07-05T11:45:19Z","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":"8e7320a461d6a4e1e4d76b3fb28ad250df48f31b537f77f76e7c1c90ed629e64","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-29T21:56:45Z","title_canon_sha256":"71e0bcdc1c7abbc9fe3d171c26493ae0b1c07fcfd68862fbff47f5ab4d6b467b"},"schema_version":"1.0","source":{"id":"2507.22250","kind":"arxiv","version":1}},"canonical_sha256":"a7861679718bd152d884e6ca2cdcd4dbc752e79ca5fcd0973405baaca19bfe83","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a7861679718bd152d884e6ca2cdcd4dbc752e79ca5fcd0973405baaca19bfe83","first_computed_at":"2026-07-05T11:45:19.204014Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:45:19.204014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dB68Ike7gUI7ORZboRkE1Rd4jfrktpEruJH8m4L+ddZy5IdVI8k4HB54HLbGkU8pwy06v1TDIIcSjUEl6hEqBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:45:19.204566Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.22250","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb0ebe72c3fbeba089f7e0a53481c98fc7940bf1e8100d3ecb570c52b222df42","sha256:1d6811678b739307534db177c57d6d79b01e442419b61a1ce5e7259bf32016d6"],"state_sha256":"ebc107a0193ba625f2cc0eeb84d19dc75c9cd11e469699fd6527df04efaf1272"}