{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DK47IDJKC2LBURTL6YT63SBXMZ","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":"94c2c644906bf2109a8c1da856e077bbd8795144c9d05a02f87cff1c9d7a8afb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-03T13:22:11Z","title_canon_sha256":"1157d5194accfe86556ebeff04eb632c8fa691596a2fa3de91b775f7a14da1de"},"schema_version":"1.0","source":{"id":"2503.01506","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.01506","created_at":"2026-07-05T10:23:08Z"},{"alias_kind":"arxiv_version","alias_value":"2503.01506v1","created_at":"2026-07-05T10:23:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01506","created_at":"2026-07-05T10:23:08Z"},{"alias_kind":"pith_short_12","alias_value":"DK47IDJKC2LB","created_at":"2026-07-05T10:23:08Z"},{"alias_kind":"pith_short_16","alias_value":"DK47IDJKC2LBURTL","created_at":"2026-07-05T10:23:08Z"},{"alias_kind":"pith_short_8","alias_value":"DK47IDJK","created_at":"2026-07-05T10:23:08Z"}],"graph_snapshots":[{"event_id":"sha256:a5c5ea153f758eff892996db378e755b232ba18a0e5508cff6c5eed9374f3d58","target":"graph","created_at":"2026-07-05T10:23:08Z","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/2503.01506/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing pretraining data mixing methods for large language models (LLMs) typically follow a domain-wise methodology, a top-down process that first determines domain weights and then performs uniform data sampling across each domain. However, these approaches neglect significant inter-domain overlaps and commonalities, failing to control the global diversity of the constructed training dataset. Further, uniform sampling within domains ignores fine-grained sample-specific features, potentially leading to suboptimal data distribution. To address these shortcomings, we propose a novel sample-wise","authors_text":"Deyang Kong, Jian Yang, Jiawei Yang, Jingang Wang, Shikun Zhang, Wei Wang, Wei Ye, Xiangyu Xi, Xunliang Cai, Zhengyu Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-03T13:22:11Z","title":"SampleMix: A Sample-wise Pre-training Data Mixing Strategey by Coordinating Data Quality and Diversity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01506","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":"sha256:10e5365bc2bd899c7979bed55cae88da65f214542bfed9ced0924247bc465429","target":"record","created_at":"2026-07-05T10:23:08Z","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":"94c2c644906bf2109a8c1da856e077bbd8795144c9d05a02f87cff1c9d7a8afb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-03T13:22:11Z","title_canon_sha256":"1157d5194accfe86556ebeff04eb632c8fa691596a2fa3de91b775f7a14da1de"},"schema_version":"1.0","source":{"id":"2503.01506","kind":"arxiv","version":1}},"canonical_sha256":"1ab9f40d2a16961a466bf627edc837664bbce3a4f0c179af0e7f39ea3fae9cd2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ab9f40d2a16961a466bf627edc837664bbce3a4f0c179af0e7f39ea3fae9cd2","first_computed_at":"2026-07-05T10:23:08.703383Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:23:08.703383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fIXnpzkQXjmWiAtr7HHtqdsEolHBcvn4cQWzB7W1i50rj6HUdpHJQUmshMoPOb7fT0Z6o0k+FKWGR0w1ml4GCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:23:08.703934Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.01506","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:10e5365bc2bd899c7979bed55cae88da65f214542bfed9ced0924247bc465429","sha256:a5c5ea153f758eff892996db378e755b232ba18a0e5508cff6c5eed9374f3d58"],"state_sha256":"e5bd1af49e24226ab69aff81a7952ea71d9110a884f1968a3a729428694857f9"}