{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:D7TYCXARY27J4GKM72TIWLMSLU","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":"ed41be3cfb55f9e3c3ff431710d7ea4e0bfad9c6a978b552bd0cea4486c5d0c0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T16:56:54Z","title_canon_sha256":"d2d379c9093de8de6fb104f45396cd8bc04163030bdb5641d34e76f46be8045f"},"schema_version":"1.0","source":{"id":"2505.21598","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.21598","created_at":"2026-07-05T11:11:00Z"},{"alias_kind":"arxiv_version","alias_value":"2505.21598v1","created_at":"2026-07-05T11:11:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21598","created_at":"2026-07-05T11:11:00Z"},{"alias_kind":"pith_short_12","alias_value":"D7TYCXARY27J","created_at":"2026-07-05T11:11:00Z"},{"alias_kind":"pith_short_16","alias_value":"D7TYCXARY27J4GKM","created_at":"2026-07-05T11:11:00Z"},{"alias_kind":"pith_short_8","alias_value":"D7TYCXAR","created_at":"2026-07-05T11:11:00Z"}],"graph_snapshots":[{"event_id":"sha256:b679d3cb072d292e2df1dd655f40d483cba4c1c99d1dc32a6ce2b6c3c4cd6145","target":"graph","created_at":"2026-07-05T11:11:00Z","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/2505.21598/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training large language models with data collected from various domains can improve their performance on downstream tasks. However, given a fixed training budget, the sampling proportions of these different domains significantly impact the model's performance. How can we determine the domain weights across different data domains to train the best-performing model within constrained computational resources? In this paper, we provide a comprehensive overview of existing data mixture methods. First, we propose a fine-grained categorization of existing methods, extending beyond the previous offlin","authors_text":"Congliang Chen, Junchi Yang, Ruoyu Sun, Yajiao Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T16:56:54Z","title":"Rethinking Data Mixture for Large Language Models: A Comprehensive Survey and New Perspectives"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21598","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":"sha256:27476eeaa8e6c984e191dd01b14d5fe3423901b45d03274e225d6b7c4d99a28e","target":"record","created_at":"2026-07-05T11:11:00Z","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":"ed41be3cfb55f9e3c3ff431710d7ea4e0bfad9c6a978b552bd0cea4486c5d0c0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T16:56:54Z","title_canon_sha256":"d2d379c9093de8de6fb104f45396cd8bc04163030bdb5641d34e76f46be8045f"},"schema_version":"1.0","source":{"id":"2505.21598","kind":"arxiv","version":1}},"canonical_sha256":"1fe7815c11c6be9e194cfea68b2d925d0e72b5a3a9f4f590ba53d9656372dd19","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1fe7815c11c6be9e194cfea68b2d925d0e72b5a3a9f4f590ba53d9656372dd19","first_computed_at":"2026-07-05T11:11:00.806662Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:00.806662Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mxrD74hNhQCZxzC9lqIkWO8NxjOHem+0ML18H2b0Klyh4uOlPsE0lPzm5UvsmrF+yIBZVcFSOQehhM5SyRV1BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:00.807141Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.21598","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27476eeaa8e6c984e191dd01b14d5fe3423901b45d03274e225d6b7c4d99a28e","sha256:b679d3cb072d292e2df1dd655f40d483cba4c1c99d1dc32a6ce2b6c3c4cd6145"],"state_sha256":"b71101d9f035f6e1b91f0fac404017be7961f1e2abc7aa9a385836900ef38917"}