{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7LY3HRXZKNLHQR4VALA5AFXK7P","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":"3ef618b32d03211fc4c417661e7e5ece3fc71c9ad537e461da74851beae6528c","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-15T05:48:57Z","title_canon_sha256":"4ff4490126be0156d7c57edfbc0e4c948f418f131e317057ddbed034275c9c19"},"schema_version":"1.0","source":{"id":"2606.16246","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.16246","created_at":"2026-06-23T01:13:06Z"},{"alias_kind":"arxiv_version","alias_value":"2606.16246v2","created_at":"2026-06-23T01:13:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.16246","created_at":"2026-06-23T01:13:06Z"},{"alias_kind":"pith_short_12","alias_value":"7LY3HRXZKNLH","created_at":"2026-06-23T01:13:06Z"},{"alias_kind":"pith_short_16","alias_value":"7LY3HRXZKNLHQR4V","created_at":"2026-06-23T01:13:06Z"},{"alias_kind":"pith_short_8","alias_value":"7LY3HRXZ","created_at":"2026-06-23T01:13:06Z"}],"graph_snapshots":[{"event_id":"sha256:45ce52cbd3bbb4fda72da4f230b12aeec90e90c31409539f1978a81017a0ab4f","target":"graph","created_at":"2026-06-23T01:13:06Z","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/2606.16246/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As AI labs approach a data ceiling where compute capacity outpaces the rate of new high-quality text generation, language model pretraining is shifting toward a data-constrained, compute-abundant regime that demands productive multi-epoch training on fixed corpora. Standard autoregressive (AR) pretraining overfits severely in this setting, reaching its optimum early and then continuously deteriorating. We investigate training-time data augmentation as a regularizer to mitigate this overfitting and enable productive training for hundreds of epochs on the same data. We introduce three orthogonal","authors_text":"Fan Bai, Michael K. Chen, Xikun Zhang, Zhengding Hu, Zhen Wang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-15T05:48:57Z","title":"Demystifying Training-Time Augmentation for Data-Constrained Language Model Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.16246","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:efe381e122f0c51949e091efbadf23857d31d6ae3d1c59a96cece528bac27d03","target":"record","created_at":"2026-06-23T01:13:06Z","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":"3ef618b32d03211fc4c417661e7e5ece3fc71c9ad537e461da74851beae6528c","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-15T05:48:57Z","title_canon_sha256":"4ff4490126be0156d7c57edfbc0e4c948f418f131e317057ddbed034275c9c19"},"schema_version":"1.0","source":{"id":"2606.16246","kind":"arxiv","version":2}},"canonical_sha256":"faf1b3c6f9535678479502c1d016eafbca43730b0d672fff26c0a2cd9515b645","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"faf1b3c6f9535678479502c1d016eafbca43730b0d672fff26c0a2cd9515b645","first_computed_at":"2026-06-23T01:13:06.826929Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T01:13:06.826929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wUfSl0jZ1/sEjmydz/UOOWWcxnwMLJWvbJSzzXYGzUhZJY+4lSttqhet1iVpUVL49yJ/r0fTeZBD9v5PTtplDA==","signature_status":"signed_v1","signed_at":"2026-06-23T01:13:06.827542Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.16246","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:efe381e122f0c51949e091efbadf23857d31d6ae3d1c59a96cece528bac27d03","sha256:45ce52cbd3bbb4fda72da4f230b12aeec90e90c31409539f1978a81017a0ab4f"],"state_sha256":"1e454d7d9ceb85a32290f289b1e6ad55fd385c2421c90801968d261ebd98cc92"}