{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TY6IWVMNTACLDREOKGQLN3QFXH","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":"f1c490f07a00338794ab20ed84009d8a613bfd5b6eac09aa78ccbda1730980ec","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T06:08:57Z","title_canon_sha256":"b4127ebf0ad45b3ffb3275b3ac4da3222ee4c7dd6fd81ad4273e3108e8eaed72"},"schema_version":"1.0","source":{"id":"2606.07597","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07597","created_at":"2026-06-09T00:04:44Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07597v1","created_at":"2026-06-09T00:04:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07597","created_at":"2026-06-09T00:04:44Z"},{"alias_kind":"pith_short_12","alias_value":"TY6IWVMNTACL","created_at":"2026-06-09T00:04:44Z"},{"alias_kind":"pith_short_16","alias_value":"TY6IWVMNTACLDREO","created_at":"2026-06-09T00:04:44Z"},{"alias_kind":"pith_short_8","alias_value":"TY6IWVMN","created_at":"2026-06-09T00:04:44Z"}],"graph_snapshots":[{"event_id":"sha256:8429ee8d7ceb5f58d94426c11375a3b275e9ff35bb8c80a3a06744b881ee034d","target":"graph","created_at":"2026-06-09T00:04:44Z","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/2606.07597/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-training data mixtures are commonly tuned by running small-scale experiments and extrapolating to the target training budget. When high-quality data is scarce and must be repeated, this extrapolation frequently fails, but the source of the failure has not been isolated. We show that a primary culprit is a repetition mismatch: because high-quality datasets are small, their repetition rate changes as the training budget grows, shifting the optimal mixture in ways that small-scale proxy experiments do not anticipate. A subsampling procedure that matches the target repetition rate controls for","authors_text":"Kevin Zhou, Kris Cao, Lisa Alazraki, Marek Rei","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T06:08:57Z","title":"Repetition Mismatch: Why Data Mixture Experiments Don't Scale and How to Fix Them"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07597","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":"sha256:6fc7e9deb70477f67c65a0c3fc47951b2388f6af9c16e8bf720177080e668107","target":"record","created_at":"2026-06-09T00:04:44Z","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":"f1c490f07a00338794ab20ed84009d8a613bfd5b6eac09aa78ccbda1730980ec","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T06:08:57Z","title_canon_sha256":"b4127ebf0ad45b3ffb3275b3ac4da3222ee4c7dd6fd81ad4273e3108e8eaed72"},"schema_version":"1.0","source":{"id":"2606.07597","kind":"arxiv","version":1}},"canonical_sha256":"9e3c8b558d9804b1c48e51a0b6ee05b9c29e609c7168f590ccdc559b63263044","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e3c8b558d9804b1c48e51a0b6ee05b9c29e609c7168f590ccdc559b63263044","first_computed_at":"2026-06-09T00:04:44.416823Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T00:04:44.416823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xHgFlrn4Zwk8Vxj1kPh+bGC/wrpcwn3swVb9LAOEtzVMyDMWfMDvuZo3iNKtlD6WTdTisNyvTjclwdHnGM/qAQ==","signature_status":"signed_v1","signed_at":"2026-06-09T00:04:44.417221Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.07597","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6fc7e9deb70477f67c65a0c3fc47951b2388f6af9c16e8bf720177080e668107","sha256:8429ee8d7ceb5f58d94426c11375a3b275e9ff35bb8c80a3a06744b881ee034d"],"state_sha256":"bb798728cfa7a5b4d652c5c90d18f1731780b7843fe1046a8c49e553846613bb"}