{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SFG5RHGGENOKXRKGYVHVGBULNT","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":"1b63ea8256dad22e5d291426c8b5b209cf2f32740f8d9f3c625885d3cdc6fd82","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-19T06:12:33Z","title_canon_sha256":"ec11ce82fcec3c6b1856d8070ef629b7a9dfd1213f52baa15b20b6b9846d4668"},"schema_version":"1.0","source":{"id":"2504.14194","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.14194","created_at":"2026-07-05T11:49:33Z"},{"alias_kind":"arxiv_version","alias_value":"2504.14194v4","created_at":"2026-07-05T11:49:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14194","created_at":"2026-07-05T11:49:33Z"},{"alias_kind":"pith_short_12","alias_value":"SFG5RHGGENOK","created_at":"2026-07-05T11:49:33Z"},{"alias_kind":"pith_short_16","alias_value":"SFG5RHGGENOKXRKG","created_at":"2026-07-05T11:49:33Z"},{"alias_kind":"pith_short_8","alias_value":"SFG5RHGG","created_at":"2026-07-05T11:49:33Z"}],"graph_snapshots":[{"event_id":"sha256:85194affdbb46d61dc71d7cdc4233280d7f0d5c691158394b9df419854c23d39","target":"graph","created_at":"2026-07-05T11:49:33Z","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/2504.14194/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The composition of pre-training datasets for large language models (LLMs) remains largely undisclosed, hindering transparency and efforts to optimize data quality, a critical driver of model performance. Current data selection methods, such as natural language quality assessments, diversity-based filters, and classifier-based approaches, are limited by single-dimensional evaluation or redundancy-focused strategies. To address these gaps, we propose four dimensions to evaluate data quality: professionalism, readability, reasoning, and cleanliness. We further introduce Meta-rater,a multi-dimensi","authors_text":"Chi Zhang, Conghui He, Jiahui Peng, Jiantao Qiu, Ren Ma, Tianyi Bai, Xingjian Wei, Xinlin Zhuang, Yinfan Wang, Ying Qian","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-19T06:12:33Z","title":"Meta-rater: A Multi-dimensional Data Selection Method for Pre-training Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14194","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":"sha256:0af96f5ec18208614fae2eb45b7d284d1446e8d749c035c0dc610f62e56989d2","target":"record","created_at":"2026-07-05T11:49:33Z","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":"1b63ea8256dad22e5d291426c8b5b209cf2f32740f8d9f3c625885d3cdc6fd82","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-19T06:12:33Z","title_canon_sha256":"ec11ce82fcec3c6b1856d8070ef629b7a9dfd1213f52baa15b20b6b9846d4668"},"schema_version":"1.0","source":{"id":"2504.14194","kind":"arxiv","version":4}},"canonical_sha256":"914dd89cc6235cabc546c54f53068b6ccf687172074af5646701d9f181bbad47","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"914dd89cc6235cabc546c54f53068b6ccf687172074af5646701d9f181bbad47","first_computed_at":"2026-07-05T11:49:33.103971Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:33.103971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NH/TA2wf0Sd7OUJ0b2d05gbobm9qBFN34oA8kxEeEBPcaktFxNHDK2GqFemOMt4EqhABznHdq3J1UtrZjB7YBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:49:33.104529Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.14194","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0af96f5ec18208614fae2eb45b7d284d1446e8d749c035c0dc610f62e56989d2","sha256:85194affdbb46d61dc71d7cdc4233280d7f0d5c691158394b9df419854c23d39"],"state_sha256":"d03ef3da8baecaa1a49191644ee4749aec1b990690098764fcb2cf915a2a4b66"}