{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3HCPPE6O2R3GH2WYL7C23QZEA3","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":"8643ea5cab66084329573e4c5802d76837a6b22ba0f6f2f7719c76ebd9baab13","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T07:45:56Z","title_canon_sha256":"cf2068258588c0d2b6df1264d7718a19384457e422a7f0563e0e76734c373fc5"},"schema_version":"1.0","source":{"id":"2410.12325","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12325","created_at":"2026-06-02T02:04:45Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12325v2","created_at":"2026-06-02T02:04:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12325","created_at":"2026-06-02T02:04:45Z"},{"alias_kind":"pith_short_12","alias_value":"3HCPPE6O2R3G","created_at":"2026-06-02T02:04:45Z"},{"alias_kind":"pith_short_16","alias_value":"3HCPPE6O2R3GH2WY","created_at":"2026-06-02T02:04:45Z"},{"alias_kind":"pith_short_8","alias_value":"3HCPPE6O","created_at":"2026-06-02T02:04:45Z"}],"graph_snapshots":[{"event_id":"sha256:ae39c5dcc9ac767d7ebf725f69363a6a338970c229ead3bfe9c27c8bd94f3b24","target":"graph","created_at":"2026-06-02T02:04:45Z","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/2410.12325/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we study a fundamental design problem in pretraining Large Language Models (LLMs) for low-resource language regimes. Existing works adopt multi-epoch, multi-lingual, and multi-stage training to utilize the limited target-language corpus efficiently, but no prior scaling law can compare recipes spanning these approaches under the same compute budget $C$ and target-language corpus size $D_T$, leaving the optimal training setup unclear. To address this gap, we propose the $M^3$ Scaling Law, a unified predictive model parameterized by the model scale, the number of target-corpus epo","authors_text":"Kosuke Akimoto, Masafumi Oyamada, Taiki Miyagawa","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T07:45:56Z","title":"$M^3$ Scaling Law: Optimizing Multi-Epoch, Multi-Lingual, and Multi-Stage Training for Low-Resource Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12325","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:fd0871595c21c03a527788fd15b74bf1965a8a22245846a2c0dd51ea269362cb","target":"record","created_at":"2026-06-02T02:04:45Z","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":"8643ea5cab66084329573e4c5802d76837a6b22ba0f6f2f7719c76ebd9baab13","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T07:45:56Z","title_canon_sha256":"cf2068258588c0d2b6df1264d7718a19384457e422a7f0563e0e76734c373fc5"},"schema_version":"1.0","source":{"id":"2410.12325","kind":"arxiv","version":2}},"canonical_sha256":"d9c4f793ced47663ead85fc5adc32406ce0d82793b62a510cd2e3a79efc62d01","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d9c4f793ced47663ead85fc5adc32406ce0d82793b62a510cd2e3a79efc62d01","first_computed_at":"2026-06-02T02:04:45.137190Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:45.137190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qpg6WZic20UY4HkEz/NYd3J4sSz5ashgMCKlMvM6IhZTN0/1GE6qt0lFzDIzb7yN6O9VAlE3YFT6hZH/9WSNAQ==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:45.137642Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.12325","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd0871595c21c03a527788fd15b74bf1965a8a22245846a2c0dd51ea269362cb","sha256:ae39c5dcc9ac767d7ebf725f69363a6a338970c229ead3bfe9c27c8bd94f3b24"],"state_sha256":"b4c75df2a138a9b372b869c93a3cc992d58bc73db5962c6f90ba7f18cf46a528"}