{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H6NDB6V2ZJYWXIS3ACHKERT4KT","short_pith_number":"pith:H6NDB6V2","schema_version":"1.0","canonical_sha256":"3f9a30fabaca716ba25b008ea2467c54fa9d7f476f14c86dd74a67af47e9475c","source":{"kind":"arxiv","id":"2406.04638","version":1},"attestation_state":"computed","paper":{"title":"Large Language Model-guided Document Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ruoming Pang, Tom Gunter, Xiang Kong","submitted_at":"2024-06-07T04:52:46Z","abstract_excerpt":"Large Language Model (LLM) pre-training exhausts an ever growing compute budget, yet recent research has demonstrated that careful document selection enables comparable model quality with only a fraction of the FLOPs. Inspired by efforts suggesting that domain-specific training document selection is in fact an interpretable process [Gunasekar et al., 2023], as well as research showing that instruction-finetuned LLMs are adept zero-shot data labelers [Gilardi et al.,2023], we explore a promising direction for scalable general-domain document selection; employing a prompted LLM as a document gra"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.04638","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-07T04:52:46Z","cross_cats_sorted":[],"title_canon_sha256":"6da0f4cd40b0469118422e7a0abec2c95aebb6626a25c7ad1b6ebd6c9382dc76","abstract_canon_sha256":"bb38192f9a68a52f0d462c7b9fb897423579abb54f0fd2b1a131d9681d6a74ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:46.858983Z","signature_b64":"U0CWt6iHSUaOwYCExgJUHF3zGZJgoD7gSffL3jQFQB60Cn7TbdgSx+QeLDx9zoHqTr1X71O8UBTzFklbMk2SBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f9a30fabaca716ba25b008ea2467c54fa9d7f476f14c86dd74a67af47e9475c","last_reissued_at":"2026-07-05T08:28:46.858599Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:46.858599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Model-guided Document Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ruoming Pang, Tom Gunter, Xiang Kong","submitted_at":"2024-06-07T04:52:46Z","abstract_excerpt":"Large Language Model (LLM) pre-training exhausts an ever growing compute budget, yet recent research has demonstrated that careful document selection enables comparable model quality with only a fraction of the FLOPs. Inspired by efforts suggesting that domain-specific training document selection is in fact an interpretable process [Gunasekar et al., 2023], as well as research showing that instruction-finetuned LLMs are adept zero-shot data labelers [Gilardi et al.,2023], we explore a promising direction for scalable general-domain document selection; employing a prompted LLM as a document gra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04638","kind":"arxiv","version":1},"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/2406.04638/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.04638","created_at":"2026-07-05T08:28:46.858656+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.04638v1","created_at":"2026-07-05T08:28:46.858656+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04638","created_at":"2026-07-05T08:28:46.858656+00:00"},{"alias_kind":"pith_short_12","alias_value":"H6NDB6V2ZJYW","created_at":"2026-07-05T08:28:46.858656+00:00"},{"alias_kind":"pith_short_16","alias_value":"H6NDB6V2ZJYWXIS3","created_at":"2026-07-05T08:28:46.858656+00:00"},{"alias_kind":"pith_short_8","alias_value":"H6NDB6V2","created_at":"2026-07-05T08:28:46.858656+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.02737","citing_title":"SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model","ref_index":188,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19394","citing_title":"Can Continual Pre-training Bridge the Performance Gap between General-purpose and Specialized Language Models in the Medical Domain?","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H6NDB6V2ZJYWXIS3ACHKERT4KT","json":"https://pith.science/pith/H6NDB6V2ZJYWXIS3ACHKERT4KT.json","graph_json":"https://pith.science/api/pith-number/H6NDB6V2ZJYWXIS3ACHKERT4KT/graph.json","events_json":"https://pith.science/api/pith-number/H6NDB6V2ZJYWXIS3ACHKERT4KT/events.json","paper":"https://pith.science/paper/H6NDB6V2"},"agent_actions":{"view_html":"https://pith.science/pith/H6NDB6V2ZJYWXIS3ACHKERT4KT","download_json":"https://pith.science/pith/H6NDB6V2ZJYWXIS3ACHKERT4KT.json","view_paper":"https://pith.science/paper/H6NDB6V2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.04638&json=true","fetch_graph":"https://pith.science/api/pith-number/H6NDB6V2ZJYWXIS3ACHKERT4KT/graph.json","fetch_events":"https://pith.science/api/pith-number/H6NDB6V2ZJYWXIS3ACHKERT4KT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H6NDB6V2ZJYWXIS3ACHKERT4KT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H6NDB6V2ZJYWXIS3ACHKERT4KT/action/storage_attestation","attest_author":"https://pith.science/pith/H6NDB6V2ZJYWXIS3ACHKERT4KT/action/author_attestation","sign_citation":"https://pith.science/pith/H6NDB6V2ZJYWXIS3ACHKERT4KT/action/citation_signature","submit_replication":"https://pith.science/pith/H6NDB6V2ZJYWXIS3ACHKERT4KT/action/replication_record"}},"created_at":"2026-07-05T08:28:46.858656+00:00","updated_at":"2026-07-05T08:28:46.858656+00:00"}