{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:O4EDCQDFFKL6GFTSSY4MB3WGZC","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":"e135486f95de15d62ee27427f8b53120a51e9b6a962d3fa7b2545c084a1ada0a","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-03T17:58:29Z","title_canon_sha256":"1638c4ee87534aa2700ed1bcfab06d3b2a6afd83d9dc7edd1d8a612050ca4f6c"},"schema_version":"1.0","source":{"id":"2410.02755","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.02755","created_at":"2026-07-05T10:07:45Z"},{"alias_kind":"arxiv_version","alias_value":"2410.02755v3","created_at":"2026-07-05T10:07:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02755","created_at":"2026-07-05T10:07:45Z"},{"alias_kind":"pith_short_12","alias_value":"O4EDCQDFFKL6","created_at":"2026-07-05T10:07:45Z"},{"alias_kind":"pith_short_16","alias_value":"O4EDCQDFFKL6GFTS","created_at":"2026-07-05T10:07:45Z"},{"alias_kind":"pith_short_8","alias_value":"O4EDCQDF","created_at":"2026-07-05T10:07:45Z"}],"graph_snapshots":[{"event_id":"sha256:73c83ca5624d85e535ee910f818d5352ac14fe6730d93a1ebd71da7cdddb85e6","target":"graph","created_at":"2026-07-05T10:07:45Z","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/2410.02755/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models require vast amounts of high-quality training data, but effective filtering of web-scale datasets remains a significant challenge. This paper demonstrates that GPT-4o is remarkably effective at identifying high-quality training data, but its prohibitive cost makes it impractical at web-scale. We propose SIEVE, a lightweight alternative that matches GPT-4o accuracy at less than 1\\% of the cost. SIEVE can perform up to 500 filtering operations for the cost of one GPT-4o filtering call. The key to SIEVE is a seamless integration of GPT-4o and lightweight text classification ","authors_text":"Jia Liu, Jifan Zhang, Ness Shroff, Robert Nowak, Ziyue Luo","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-03T17:58:29Z","title":"GPT-4o as the Gold Standard: A Scalable and General Purpose Approach to Filter Language Model Pretraining Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02755","kind":"arxiv","version":3},"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":"sha256:3d56ce6c839d56a6c61fa579122910b514dde1a1476fe5a03d09a659ed5c45a1","target":"record","created_at":"2026-07-05T10:07:45Z","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":"e135486f95de15d62ee27427f8b53120a51e9b6a962d3fa7b2545c084a1ada0a","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-03T17:58:29Z","title_canon_sha256":"1638c4ee87534aa2700ed1bcfab06d3b2a6afd83d9dc7edd1d8a612050ca4f6c"},"schema_version":"1.0","source":{"id":"2410.02755","kind":"arxiv","version":3}},"canonical_sha256":"77083140652a97e316729638c0eec6c88ad64914e45facfe8f56f359f8a33b59","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77083140652a97e316729638c0eec6c88ad64914e45facfe8f56f359f8a33b59","first_computed_at":"2026-07-05T10:07:45.087305Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:07:45.087305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zv+cO/oyyWJHYj6CiMNmiIinq0Xtl4FbPi+yrVxoOGOVvvnqcAShDbTDgaHoOjBZcxgJrFhPBaQiuPH0aeGnAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:07:45.087806Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.02755","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d56ce6c839d56a6c61fa579122910b514dde1a1476fe5a03d09a659ed5c45a1","sha256:73c83ca5624d85e535ee910f818d5352ac14fe6730d93a1ebd71da7cdddb85e6"],"state_sha256":"7c7b3eb3d6051c6dd1fe5f2d76aa5c47fa93f2e2d4dc6468613b54a2b225e450"}