{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KPZ6XFZV4TEAC7GQRJJ5337CKJ","short_pith_number":"pith:KPZ6XFZV","schema_version":"1.0","canonical_sha256":"53f3eb9735e4c8017cd08a53ddefe252667f34def744ffa0432613b2a7dac0ac","source":{"kind":"arxiv","id":"2411.11289","version":1},"attestation_state":"computed","paper":{"title":"LP Data Pipeline: Lightweight, Purpose-driven Data Pipeline for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chanjun Park, Hyunsoo Ha, Jihoo Kim, Seonghoon Yang, Sukyung Lee, Yungi Kim","submitted_at":"2024-11-18T05:17:27Z","abstract_excerpt":"Creating high-quality, large-scale datasets for large language models (LLMs) often relies on resource-intensive, GPU-accelerated models for quality filtering, making the process time-consuming and costly. This dependence on GPUs limits accessibility for organizations lacking significant computational infrastructure. To address this issue, we introduce the Lightweight, Purpose-driven (LP) Data Pipeline, a framework that operates entirely on CPUs to streamline the processes of dataset extraction, filtering, and curation. Based on our four core principles, the LP Data Pipeline significantly reduc"},"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":"2411.11289","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-18T05:17:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b7a6fceac7f407f51bdd1ace57d3f8f17ece867f9ba49f2f443b6ceafd591040","abstract_canon_sha256":"3bb850241e19e9f05d51d4ee4c4eb4aa220671df9011748a3b57a4d0f6ad3a1b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:54.032664Z","signature_b64":"nMVwuGtmU2aY7MM6LwyTXzrfcKhHR6uz85a3wr/6Msa4+RAYCFlkbuS6du9HEwKrIiwsARFK0TTSYPddS+ZpDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53f3eb9735e4c8017cd08a53ddefe252667f34def744ffa0432613b2a7dac0ac","last_reissued_at":"2026-07-05T09:36:54.032230Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:54.032230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LP Data Pipeline: Lightweight, Purpose-driven Data Pipeline for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chanjun Park, Hyunsoo Ha, Jihoo Kim, Seonghoon Yang, Sukyung Lee, Yungi Kim","submitted_at":"2024-11-18T05:17:27Z","abstract_excerpt":"Creating high-quality, large-scale datasets for large language models (LLMs) often relies on resource-intensive, GPU-accelerated models for quality filtering, making the process time-consuming and costly. This dependence on GPUs limits accessibility for organizations lacking significant computational infrastructure. To address this issue, we introduce the Lightweight, Purpose-driven (LP) Data Pipeline, a framework that operates entirely on CPUs to streamline the processes of dataset extraction, filtering, and curation. Based on our four core principles, the LP Data Pipeline significantly reduc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11289","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/2411.11289/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":"2411.11289","created_at":"2026-07-05T09:36:54.032281+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.11289v1","created_at":"2026-07-05T09:36:54.032281+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11289","created_at":"2026-07-05T09:36:54.032281+00:00"},{"alias_kind":"pith_short_12","alias_value":"KPZ6XFZV4TEA","created_at":"2026-07-05T09:36:54.032281+00:00"},{"alias_kind":"pith_short_16","alias_value":"KPZ6XFZV4TEAC7GQ","created_at":"2026-07-05T09:36:54.032281+00:00"},{"alias_kind":"pith_short_8","alias_value":"KPZ6XFZV","created_at":"2026-07-05T09:36:54.032281+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KPZ6XFZV4TEAC7GQRJJ5337CKJ","json":"https://pith.science/pith/KPZ6XFZV4TEAC7GQRJJ5337CKJ.json","graph_json":"https://pith.science/api/pith-number/KPZ6XFZV4TEAC7GQRJJ5337CKJ/graph.json","events_json":"https://pith.science/api/pith-number/KPZ6XFZV4TEAC7GQRJJ5337CKJ/events.json","paper":"https://pith.science/paper/KPZ6XFZV"},"agent_actions":{"view_html":"https://pith.science/pith/KPZ6XFZV4TEAC7GQRJJ5337CKJ","download_json":"https://pith.science/pith/KPZ6XFZV4TEAC7GQRJJ5337CKJ.json","view_paper":"https://pith.science/paper/KPZ6XFZV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.11289&json=true","fetch_graph":"https://pith.science/api/pith-number/KPZ6XFZV4TEAC7GQRJJ5337CKJ/graph.json","fetch_events":"https://pith.science/api/pith-number/KPZ6XFZV4TEAC7GQRJJ5337CKJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KPZ6XFZV4TEAC7GQRJJ5337CKJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KPZ6XFZV4TEAC7GQRJJ5337CKJ/action/storage_attestation","attest_author":"https://pith.science/pith/KPZ6XFZV4TEAC7GQRJJ5337CKJ/action/author_attestation","sign_citation":"https://pith.science/pith/KPZ6XFZV4TEAC7GQRJJ5337CKJ/action/citation_signature","submit_replication":"https://pith.science/pith/KPZ6XFZV4TEAC7GQRJJ5337CKJ/action/replication_record"}},"created_at":"2026-07-05T09:36:54.032281+00:00","updated_at":"2026-07-05T09:36:54.032281+00:00"}