{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MSJIFRNDPPUJ5TID3VLSEXIVWA","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":"fa06807c9275c821d2c0192738f510bf2774fe46b5eba992a45681e59d0c87a7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-25T07:18:29Z","title_canon_sha256":"51682390674333ae16623107a031446085c2f6e8eed55ff79b2a911b34bb47a6"},"schema_version":"1.0","source":{"id":"2502.17910","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.17910","created_at":"2026-07-05T10:19:45Z"},{"alias_kind":"arxiv_version","alias_value":"2502.17910v1","created_at":"2026-07-05T10:19:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17910","created_at":"2026-07-05T10:19:45Z"},{"alias_kind":"pith_short_12","alias_value":"MSJIFRNDPPUJ","created_at":"2026-07-05T10:19:45Z"},{"alias_kind":"pith_short_16","alias_value":"MSJIFRNDPPUJ5TID","created_at":"2026-07-05T10:19:45Z"},{"alias_kind":"pith_short_8","alias_value":"MSJIFRND","created_at":"2026-07-05T10:19:45Z"}],"graph_snapshots":[{"event_id":"sha256:d11e0bbe63e4547a1582a181177a6987c6b51ba84abdda4f529c0594475165dd","target":"graph","created_at":"2026-07-05T10:19:45Z","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/2502.17910/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern language models rely on static vocabularies, fixed before pretraining, in contrast to the adaptive vocabulary acquisition observed in human language learning. To bridge this gap, we introduce vocabulary curriculum learning, an approach that improves pretraining efficiency with log-linear scaling gains relative to vocabulary size. Our method alternates between entropy-guided vocabulary expansion and model optimization, enabling models to learn transferable representations across diverse tokenization granularities. This approach naturally gives rise to an optimal computation allocation pa","authors_text":"Fangyuan Yu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-25T07:18:29Z","title":"Scaling LLM Pre-training with Vocabulary Curriculum"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17910","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:f8635c201ad2f12afcfd26941c3528bb9fb491c8c17458a2604cba1e6e4e8c6c","target":"record","created_at":"2026-07-05T10:19:45Z","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":"fa06807c9275c821d2c0192738f510bf2774fe46b5eba992a45681e59d0c87a7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-25T07:18:29Z","title_canon_sha256":"51682390674333ae16623107a031446085c2f6e8eed55ff79b2a911b34bb47a6"},"schema_version":"1.0","source":{"id":"2502.17910","kind":"arxiv","version":1}},"canonical_sha256":"649282c5a37be89ecd03dd57225d15b03e58a27b43995e34cd3baa5626ad150a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"649282c5a37be89ecd03dd57225d15b03e58a27b43995e34cd3baa5626ad150a","first_computed_at":"2026-07-05T10:19:45.997787Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:19:45.997787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+grAvfY+5/35iBEaP2VTtcNKb3Vs1mXtTJ7742aklL9N6DopNDCjljkCuihsatsGuuTExXNuFhHmHJbHPavwDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:19:45.998202Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.17910","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8635c201ad2f12afcfd26941c3528bb9fb491c8c17458a2604cba1e6e4e8c6c","sha256:d11e0bbe63e4547a1582a181177a6987c6b51ba84abdda4f529c0594475165dd"],"state_sha256":"32cbffe838588a97c971d10fe19c5a9287b548b39ab03525d18b899b331bfdb5"}