{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KPZ6XFZV4TEAC7GQRJJ5337CKJ","short_pith_number":"pith:KPZ6XFZV","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"},"canonical_sha256":"53f3eb9735e4c8017cd08a53ddefe252667f34def744ffa0432613b2a7dac0ac","source":{"kind":"arxiv","id":"2411.11289","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KPZ6XFZV4TEAC7GQRJJ5337CKJ","target":"record","payload":{"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"},"canonical_sha256":"53f3eb9735e4c8017cd08a53ddefe252667f34def744ffa0432613b2a7dac0ac","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"},"source_kind":"arxiv","source_id":"2411.11289","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:36:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JZDNKVmzDqji8oi3FuLCcHkC6aWBvSr2KhJueP+S5Uu0PIrHEtWJRKQq7YnpGloeYSmfVmPw3wsV9z892KzfCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T18:59:17.050434Z"},"content_sha256":"264f43dc96de9d874d6a36d62c9fe012140c1e00756ee22b892e0f3259c26a6e","schema_version":"1.0","event_id":"sha256:264f43dc96de9d874d6a36d62c9fe012140c1e00756ee22b892e0f3259c26a6e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KPZ6XFZV4TEAC7GQRJJ5337CKJ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:36:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eB+QxED9/79UGSaO2XjBfo4junWczrUcgNmLj/QugeveuFII5otkqhD8Y8Gs+5v+W5bnMyAM05kQIkucbsspCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T18:59:17.050927Z"},"content_sha256":"87ddba4ec69d82faea3a8632b496094a622a9e83587faa0c69ff5076fa8b2be1","schema_version":"1.0","event_id":"sha256:87ddba4ec69d82faea3a8632b496094a622a9e83587faa0c69ff5076fa8b2be1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KPZ6XFZV4TEAC7GQRJJ5337CKJ/bundle.json","state_url":"https://pith.science/pith/KPZ6XFZV4TEAC7GQRJJ5337CKJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KPZ6XFZV4TEAC7GQRJJ5337CKJ/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":"2026-08-13T18:59:17Z","links":{"resolver":"https://pith.science/pith/KPZ6XFZV4TEAC7GQRJJ5337CKJ","bundle":"https://pith.science/pith/KPZ6XFZV4TEAC7GQRJJ5337CKJ/bundle.json","state":"https://pith.science/pith/KPZ6XFZV4TEAC7GQRJJ5337CKJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KPZ6XFZV4TEAC7GQRJJ5337CKJ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"if52g3P71DacFf3ArqHayTznVfMYNtSKWagVUmXxvg4bzIhZAfHP9tRB/TA2J379acADCrdskzGXLczL3YdrDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T18:59:17.072099Z","bundle_sha256":"e285bca14cf09eea6e57ce1903b19262168c63c9b193e990dafaf5a04e67396f"}}