{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TY65AJV7E7JKZAF66BBVENOWF5","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":"0b02d3d1739818c791ec903df6e7aa1e41a141642d37211d8fb6ed0232be97db","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-26T04:30:32Z","title_canon_sha256":"671c15612c46fcf369d01735febaff5c02cc3c2b94690ce297e7847c785864ae"},"schema_version":"1.0","source":{"id":"2409.17527","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.17527","created_at":"2026-07-05T09:12:11Z"},{"alias_kind":"arxiv_version","alias_value":"2409.17527v1","created_at":"2026-07-05T09:12:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.17527","created_at":"2026-07-05T09:12:11Z"},{"alias_kind":"pith_short_12","alias_value":"TY65AJV7E7JK","created_at":"2026-07-05T09:12:11Z"},{"alias_kind":"pith_short_16","alias_value":"TY65AJV7E7JKZAF6","created_at":"2026-07-05T09:12:11Z"},{"alias_kind":"pith_short_8","alias_value":"TY65AJV7","created_at":"2026-07-05T09:12:11Z"}],"graph_snapshots":[{"event_id":"sha256:1bba62921d7b907aaf6b836907a08842b1f51feb905b237c7967c497743eed22","target":"graph","created_at":"2026-07-05T09:12:11Z","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/2409.17527/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have demonstrated exceptional performance across a wide range of tasks and domains, with data preparation playing a critical role in achieving these results. Pre-training data typically combines information from multiple domains. To maximize performance when integrating data from various domains, determining the optimal data proportion is essential. However, state-of-the-art (SOTA) LLMs rarely disclose details about their pre-training data, making it difficult for researchers to identify ideal data proportions. In this paper, we introduce a new topic, \\textit{data ","authors_text":"Bin Cui, Guosheng Dong, Hao Liang, Keshi Zhao, Wentao Zhang, Yajie Yang, Zenan Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-26T04:30:32Z","title":"Data Proportion Detection for Optimized Data Management for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.17527","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":"sha256:73c240555c4d49ef0d9bd3ca1034e2d6beedc4b15521aabfbaf68230693db617","target":"record","created_at":"2026-07-05T09:12:11Z","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":"0b02d3d1739818c791ec903df6e7aa1e41a141642d37211d8fb6ed0232be97db","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-26T04:30:32Z","title_canon_sha256":"671c15612c46fcf369d01735febaff5c02cc3c2b94690ce297e7847c785864ae"},"schema_version":"1.0","source":{"id":"2409.17527","kind":"arxiv","version":1}},"canonical_sha256":"9e3dd026bf27d2ac80bef0435235d62f7e0a5fe47ebcba5a136f741b4cabcbe5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e3dd026bf27d2ac80bef0435235d62f7e0a5fe47ebcba5a136f741b4cabcbe5","first_computed_at":"2026-07-05T09:12:11.468774Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:12:11.468774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zKBSDowMk5rjZsFe/UweCdZbZgUkke9n/i199MWSv3OS8/MJzX3EHJr4t0doGqlUElcZS2wM1g86j2WcrIvvAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:12:11.469323Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.17527","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73c240555c4d49ef0d9bd3ca1034e2d6beedc4b15521aabfbaf68230693db617","sha256:1bba62921d7b907aaf6b836907a08842b1f51feb905b237c7967c497743eed22"],"state_sha256":"e4e1cde8fd7e0004dd698c79e7d64f595ab44eb2f5ee944729e2c1b40d5d611b"}