{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KPZ6XFZV4TEAC7GQRJJ5337CKJ","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":"3bb850241e19e9f05d51d4ee4c4eb4aa220671df9011748a3b57a4d0f6ad3a1b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-18T05:17:27Z","title_canon_sha256":"b7a6fceac7f407f51bdd1ace57d3f8f17ece867f9ba49f2f443b6ceafd591040"},"schema_version":"1.0","source":{"id":"2411.11289","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.11289","created_at":"2026-07-05T09:36:54Z"},{"alias_kind":"arxiv_version","alias_value":"2411.11289v1","created_at":"2026-07-05T09:36:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11289","created_at":"2026-07-05T09:36:54Z"},{"alias_kind":"pith_short_12","alias_value":"KPZ6XFZV4TEA","created_at":"2026-07-05T09:36:54Z"},{"alias_kind":"pith_short_16","alias_value":"KPZ6XFZV4TEAC7GQ","created_at":"2026-07-05T09:36:54Z"},{"alias_kind":"pith_short_8","alias_value":"KPZ6XFZV","created_at":"2026-07-05T09:36:54Z"}],"graph_snapshots":[{"event_id":"sha256:87ddba4ec69d82faea3a8632b496094a622a9e83587faa0c69ff5076fa8b2be1","target":"graph","created_at":"2026-07-05T09:36:54Z","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/2411.11289/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chanjun Park, Hyunsoo Ha, Jihoo Kim, Seonghoon Yang, Sukyung Lee, Yungi Kim","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-18T05:17:27Z","title":"LP Data Pipeline: Lightweight, Purpose-driven Data Pipeline for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11289","kind":"arxiv","version":1},"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":"sha256:264f43dc96de9d874d6a36d62c9fe012140c1e00756ee22b892e0f3259c26a6e","target":"record","created_at":"2026-07-05T09:36:54Z","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":"3bb850241e19e9f05d51d4ee4c4eb4aa220671df9011748a3b57a4d0f6ad3a1b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-18T05:17:27Z","title_canon_sha256":"b7a6fceac7f407f51bdd1ace57d3f8f17ece867f9ba49f2f443b6ceafd591040"},"schema_version":"1.0","source":{"id":"2411.11289","kind":"arxiv","version":1}},"canonical_sha256":"53f3eb9735e4c8017cd08a53ddefe252667f34def744ffa0432613b2a7dac0ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53f3eb9735e4c8017cd08a53ddefe252667f34def744ffa0432613b2a7dac0ac","first_computed_at":"2026-07-05T09:36:54.032230Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:36:54.032230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nMVwuGtmU2aY7MM6LwyTXzrfcKhHR6uz85a3wr/6Msa4+RAYCFlkbuS6du9HEwKrIiwsARFK0TTSYPddS+ZpDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:36:54.032664Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.11289","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:264f43dc96de9d874d6a36d62c9fe012140c1e00756ee22b892e0f3259c26a6e","sha256:87ddba4ec69d82faea3a8632b496094a622a9e83587faa0c69ff5076fa8b2be1"],"state_sha256":"290b462ecb799b3693c649efc34be1dc087d9eaa50596696d0aa2f0e7da19fec"}