{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XPEQR4F5ZI6LXFRWNNKK47VW32","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":"ced7ada17b545eadb50253a253ef920c82394c77f35a083e1bbdd068392de60c","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-15T20:29:38Z","title_canon_sha256":"bb93e407977b58be9301f0166f828c8bc8c85fa95a0f0fdfc8798d8bff9087d1"},"schema_version":"1.0","source":{"id":"2410.12883","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12883","created_at":"2026-07-05T09:44:15Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12883v2","created_at":"2026-07-05T09:44:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12883","created_at":"2026-07-05T09:44:15Z"},{"alias_kind":"pith_short_12","alias_value":"XPEQR4F5ZI6L","created_at":"2026-07-05T09:44:15Z"},{"alias_kind":"pith_short_16","alias_value":"XPEQR4F5ZI6LXFRW","created_at":"2026-07-05T09:44:15Z"},{"alias_kind":"pith_short_8","alias_value":"XPEQR4F5","created_at":"2026-07-05T09:44:15Z"}],"graph_snapshots":[{"event_id":"sha256:736515629f2b556b348ac9e1d11ded4f7add2d4a9e5753fe93f4103e2490c99c","target":"graph","created_at":"2026-07-05T09:44:15Z","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/2410.12883/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a novel scaling law for general-purpose decoder-only language models (LMs) trained on multilingual data, tackling the problem of balancing languages during multilingual pretraining. A primary challenge in studying multilingual scaling is the difficulty of analyzing individual language performance due to cross-lingual transfer. To address this, we shift the focus from individual languages to language families. We introduce and validate a hypothesis that the test cross-entropy loss for each language family is determined solely by its own sampling ratio, independent of other languages ","authors_text":"Alon Benhaim, Barun Patra, Han Zhao, Parul Chopra, Praneetha Vaddamanu, Sanchit Ahuja, Vishrav Chaudhary, Xia Song, Yifei He","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-15T20:29:38Z","title":"Scaling Laws for Multilingual Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12883","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":"sha256:034f5777ae7cd65551c4d1678511ed71f4b3da491744dbe69375f2c618fd0921","target":"record","created_at":"2026-07-05T09:44:15Z","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":"ced7ada17b545eadb50253a253ef920c82394c77f35a083e1bbdd068392de60c","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-15T20:29:38Z","title_canon_sha256":"bb93e407977b58be9301f0166f828c8bc8c85fa95a0f0fdfc8798d8bff9087d1"},"schema_version":"1.0","source":{"id":"2410.12883","kind":"arxiv","version":2}},"canonical_sha256":"bbc908f0bdca3cbb96366b54ae7eb6de90eddc9dfdfdc9c49e0fa15cf8e16346","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bbc908f0bdca3cbb96366b54ae7eb6de90eddc9dfdfdc9c49e0fa15cf8e16346","first_computed_at":"2026-07-05T09:44:15.618931Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:44:15.618931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zSr88iQhDL1H+pEAOH3Dh6HkO7+vE0//OV/mFooiQdDTYNmwYrCrpei8WmmhR4MtTf3k2NNeiQMuEXrSMWTqBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:44:15.619418Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.12883","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:034f5777ae7cd65551c4d1678511ed71f4b3da491744dbe69375f2c618fd0921","sha256:736515629f2b556b348ac9e1d11ded4f7add2d4a9e5753fe93f4103e2490c99c"],"state_sha256":"3494d6a76add65060fb08edb629c810cc844ce9cb8f7b2198b8bf36d04a9febc"}