{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QQNJULOQ6SRGGHG3OC4CHMWNV6","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":"33293a16bcd9c12a236b15758895bf83096da825e9e46a9512d902e643eec350","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T04:10:09Z","title_canon_sha256":"84ef3f5230565c2879248e56407818db6e66a3eeb50e933c6fb707d833ee8b9b"},"schema_version":"1.0","source":{"id":"2606.06888","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.06888","created_at":"2026-06-08T01:04:34Z"},{"alias_kind":"arxiv_version","alias_value":"2606.06888v1","created_at":"2026-06-08T01:04:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06888","created_at":"2026-06-08T01:04:34Z"},{"alias_kind":"pith_short_12","alias_value":"QQNJULOQ6SRG","created_at":"2026-06-08T01:04:34Z"},{"alias_kind":"pith_short_16","alias_value":"QQNJULOQ6SRGGHG3","created_at":"2026-06-08T01:04:34Z"},{"alias_kind":"pith_short_8","alias_value":"QQNJULOQ","created_at":"2026-06-08T01:04:34Z"}],"graph_snapshots":[{"event_id":"sha256:7122188c7f7e35857b5bc17a31e0e8e03bd43de642d11468c42978b824744136","target":"graph","created_at":"2026-06-08T01:04:34Z","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/2606.06888/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Classical scaling laws for language model pretraining balance model size against training dataset size under a fixed compute budget, assuming abundant data and a single pass over the corpus. As training compute grows faster than the supply of natural language data, pretraining is likely to enter a data-constrained, compute-rich regime where models train for multiple epochs over a finite dataset. We study data-constrained pretraining along two axes, regularization and scaling. For regularization, we study masked-input regularization (MIR), an auxiliary next-token prediction loss on randomly mas","authors_text":"Hanseul Cho, Shihao Wu, Wei Hu, Yixin Wang, Zhiwei Xu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T04:10:09Z","title":"Data-Constrained Language Model Pretraining: Improved Regularization and Scaling Laws"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06888","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":"sha256:262226ce5db46bcb3c82a2d324af677f50601afbc1e68b2c956ec2646761707b","target":"record","created_at":"2026-06-08T01:04:34Z","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":"33293a16bcd9c12a236b15758895bf83096da825e9e46a9512d902e643eec350","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T04:10:09Z","title_canon_sha256":"84ef3f5230565c2879248e56407818db6e66a3eeb50e933c6fb707d833ee8b9b"},"schema_version":"1.0","source":{"id":"2606.06888","kind":"arxiv","version":1}},"canonical_sha256":"841a9a2dd0f4a2631cdb70b823b2cdaf90af562eaf55da5c8346634e259006d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"841a9a2dd0f4a2631cdb70b823b2cdaf90af562eaf55da5c8346634e259006d0","first_computed_at":"2026-06-08T01:04:34.093532Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:04:34.093532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B4lnD7+0CuIo6Ln2L60d3N3iCSIK7iykW7m6yrmBuuG6Fr0vwUczW8x+xxF16AdclFEyMrpKtAVDC2U9tShlCw==","signature_status":"signed_v1","signed_at":"2026-06-08T01:04:34.094486Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.06888","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:262226ce5db46bcb3c82a2d324af677f50601afbc1e68b2c956ec2646761707b","sha256:7122188c7f7e35857b5bc17a31e0e8e03bd43de642d11468c42978b824744136"],"state_sha256":"b9cf2345266844860f5de698fd0cd3b2691591ff95ce026ba8569c868b4f0134"}