{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SFG5RHGGENOKXRKGYVHVGBULNT","short_pith_number":"pith:SFG5RHGG","canonical_record":{"source":{"id":"2504.14194","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-19T06:12:33Z","cross_cats_sorted":[],"title_canon_sha256":"ec11ce82fcec3c6b1856d8070ef629b7a9dfd1213f52baa15b20b6b9846d4668","abstract_canon_sha256":"1b63ea8256dad22e5d291426c8b5b209cf2f32740f8d9f3c625885d3cdc6fd82"},"schema_version":"1.0"},"canonical_sha256":"914dd89cc6235cabc546c54f53068b6ccf687172074af5646701d9f181bbad47","source":{"kind":"arxiv","id":"2504.14194","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SFG5RHGGENOKXRKGYVHVGBULNT","target":"record","payload":{"canonical_record":{"source":{"id":"2504.14194","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-19T06:12:33Z","cross_cats_sorted":[],"title_canon_sha256":"ec11ce82fcec3c6b1856d8070ef629b7a9dfd1213f52baa15b20b6b9846d4668","abstract_canon_sha256":"1b63ea8256dad22e5d291426c8b5b209cf2f32740f8d9f3c625885d3cdc6fd82"},"schema_version":"1.0"},"canonical_sha256":"914dd89cc6235cabc546c54f53068b6ccf687172074af5646701d9f181bbad47","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:33.104529Z","signature_b64":"NH/TA2wf0Sd7OUJ0b2d05gbobm9qBFN34oA8kxEeEBPcaktFxNHDK2GqFemOMt4EqhABznHdq3J1UtrZjB7YBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"914dd89cc6235cabc546c54f53068b6ccf687172074af5646701d9f181bbad47","last_reissued_at":"2026-07-05T11:49:33.103971Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:33.103971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.14194","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:49:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xNJRs9jCAlox7wz4D8SeNJ/dA41uiuRYTdBistQutVicbYrccqebMjTMnpbd1cwecURlehzCD2b42oRiv43HCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:16:33.196042Z"},"content_sha256":"0af96f5ec18208614fae2eb45b7d284d1446e8d749c035c0dc610f62e56989d2","schema_version":"1.0","event_id":"sha256:0af96f5ec18208614fae2eb45b7d284d1446e8d749c035c0dc610f62e56989d2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SFG5RHGGENOKXRKGYVHVGBULNT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Meta-rater: A Multi-dimensional Data Selection Method for Pre-training Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chi Zhang, Conghui He, Jiahui Peng, Jiantao Qiu, Ren Ma, Tianyi Bai, Xingjian Wei, Xinlin Zhuang, Yinfan Wang, Ying Qian","submitted_at":"2025-04-19T06:12:33Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14194","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2504.14194/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:49:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7IiHJ+W56HD5T8ej86o1xhDUmVbp8vRm5xaOukJvkKwEFYvcvPjLHMnHrlQf22D2ymk06p8T4HM6urWdbdOKBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:16:33.196739Z"},"content_sha256":"85194affdbb46d61dc71d7cdc4233280d7f0d5c691158394b9df419854c23d39","schema_version":"1.0","event_id":"sha256:85194affdbb46d61dc71d7cdc4233280d7f0d5c691158394b9df419854c23d39"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SFG5RHGGENOKXRKGYVHVGBULNT/bundle.json","state_url":"https://pith.science/pith/SFG5RHGGENOKXRKGYVHVGBULNT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SFG5RHGGENOKXRKGYVHVGBULNT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T10:16:33Z","links":{"resolver":"https://pith.science/pith/SFG5RHGGENOKXRKGYVHVGBULNT","bundle":"https://pith.science/pith/SFG5RHGGENOKXRKGYVHVGBULNT/bundle.json","state":"https://pith.science/pith/SFG5RHGGENOKXRKGYVHVGBULNT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SFG5RHGGENOKXRKGYVHVGBULNT/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XNWkxplupIPhpWvyR1v7YnANKMh3CyPAZ3jUknRY9yDvIg8FYW5MSa7Qr38RESlBbisSziSmFEUd4X1rGk+WAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T10:16:33.203961Z","bundle_sha256":"98abfc8688d4221b523bfb784a2fcc10a5c4f8ef80ca9cc9f305cebbfabaf795"}}