{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VL73RD4AMNPZQMHDZTPOWZHXQT","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":"d5d1cab7aefb5d538935f8f207313d90790ed08ca8bc05415b4332b99238a6e4","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T09:44:02Z","title_canon_sha256":"4e7d3f014467cdac7d07aa20d6c3c9fdc182d37bc04174203824edf3a41bf684"},"schema_version":"1.0","source":{"id":"2405.14908","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.14908","created_at":"2026-07-05T10:05:42Z"},{"alias_kind":"arxiv_version","alias_value":"2405.14908v4","created_at":"2026-07-05T10:05:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14908","created_at":"2026-07-05T10:05:42Z"},{"alias_kind":"pith_short_12","alias_value":"VL73RD4AMNPZ","created_at":"2026-07-05T10:05:42Z"},{"alias_kind":"pith_short_16","alias_value":"VL73RD4AMNPZQMHD","created_at":"2026-07-05T10:05:42Z"},{"alias_kind":"pith_short_8","alias_value":"VL73RD4A","created_at":"2026-07-05T10:05:42Z"}],"graph_snapshots":[{"event_id":"sha256:77162258bb8b8ceb920fad44eef9ac1407a5372d85738d2e61e2b2a5762e55ef","target":"graph","created_at":"2026-07-05T10:05:42Z","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/2405.14908/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models have demonstrated remarkable capabilities across various tasks, primarily attributed to the utilization of diversely sourced data. However, the impact of pretraining data composition on model performance remains poorly understood. This paper introduces $\\textbf{BiMix}$, a novel bivariate data mixing law that models the joint scaling behavior of domain proportions and data volume in LLM pretraining. $\\textbf{BiMix}$ provides a systematic framework for understanding and optimizing data mixtures across diverse domains. Through extensive experiments on two large-scale dataset","authors_text":"Bolin Ding, Ce Ge, Daoyuan Chen, Yaliang Li, Zhijian Ma","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T09:44:02Z","title":"BiMix: A Bivariate Data Mixing Law for Language Model Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14908","kind":"arxiv","version":4},"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":"sha256:33f4fb9b5496ef72690df8f22a26a8b1a8922e8d673b64e01336199afad89344","target":"record","created_at":"2026-07-05T10:05:42Z","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":"d5d1cab7aefb5d538935f8f207313d90790ed08ca8bc05415b4332b99238a6e4","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T09:44:02Z","title_canon_sha256":"4e7d3f014467cdac7d07aa20d6c3c9fdc182d37bc04174203824edf3a41bf684"},"schema_version":"1.0","source":{"id":"2405.14908","kind":"arxiv","version":4}},"canonical_sha256":"aaffb88f80635f9830e3ccdeeb64f784cdb0fd39122736134b34e0f88fc3f127","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aaffb88f80635f9830e3ccdeeb64f784cdb0fd39122736134b34e0f88fc3f127","first_computed_at":"2026-07-05T10:05:42.980201Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:42.980201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N9SAuPm6zsaPTovmTh2gj6OJN/FgIU4Ecx1J8k5QwS7XwtMjOJOplneQuMYzg3iipN24gZMUrlpffRPnLEG+CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:42.980687Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.14908","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:33f4fb9b5496ef72690df8f22a26a8b1a8922e8d673b64e01336199afad89344","sha256:77162258bb8b8ceb920fad44eef9ac1407a5372d85738d2e61e2b2a5762e55ef"],"state_sha256":"218c59d4b5acec792f30b155813cae15b3832afdb657b0b0b97b8f1ec549d5bb"}