{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SHF4WAYY6MMGJQUKKZRWTERCNB","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":"feb17b0a2c5c50c1b00c8047274bf250cbd7bb593a36fcf8ae874e729d403918","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-28T11:57:08Z","title_canon_sha256":"282a312711c2d68db143db5eb4637f66172f1cb00514a2b2253b760227fb7417"},"schema_version":"1.0","source":{"id":"2403.19340","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.19340","created_at":"2026-07-05T10:23:19Z"},{"alias_kind":"arxiv_version","alias_value":"2403.19340v2","created_at":"2026-07-05T10:23:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.19340","created_at":"2026-07-05T10:23:19Z"},{"alias_kind":"pith_short_12","alias_value":"SHF4WAYY6MMG","created_at":"2026-07-05T10:23:19Z"},{"alias_kind":"pith_short_16","alias_value":"SHF4WAYY6MMGJQUK","created_at":"2026-07-05T10:23:19Z"},{"alias_kind":"pith_short_8","alias_value":"SHF4WAYY","created_at":"2026-07-05T10:23:19Z"}],"graph_snapshots":[{"event_id":"sha256:f9165c63cad9e7d13b22c01b6b24718a0e3c098f01ba9b87a670e0c2950355c7","target":"graph","created_at":"2026-07-05T10:23:19Z","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/2403.19340/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To address the challenges associated with data processing at scale, we propose Dataverse, a unified open-source Extract-Transform-Load (ETL) pipeline for large language models (LLMs) with a user-friendly design at its core. Easy addition of custom processors with block-based interface in Dataverse allows users to readily and efficiently use Dataverse to build their own ETL pipeline. We hope that Dataverse will serve as a vital tool for LLM development and open source the entire library to welcome community contribution. Additionally, we provide a concise, two-minute video demonstration of our ","authors_text":"Chanjun Park, Dahyun Kim, Gyoungjin Gim, Hyunbyung Park, Sukyung Lee, Yungi Kim","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-28T11:57:08Z","title":"Dataverse: Open-Source ETL (Extract, Transform, Load) Pipeline for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.19340","kind":"arxiv","version":2},"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":"sha256:8f72aabee5b8c4c7d5b9c9ee14d3d5b8808882514c0c45783f59bb03bfe7b7c6","target":"record","created_at":"2026-07-05T10:23:19Z","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":"feb17b0a2c5c50c1b00c8047274bf250cbd7bb593a36fcf8ae874e729d403918","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-28T11:57:08Z","title_canon_sha256":"282a312711c2d68db143db5eb4637f66172f1cb00514a2b2253b760227fb7417"},"schema_version":"1.0","source":{"id":"2403.19340","kind":"arxiv","version":2}},"canonical_sha256":"91cbcb0318f31864c28a5663699222685c97fc54fc04b25e83974cb111207b2c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"91cbcb0318f31864c28a5663699222685c97fc54fc04b25e83974cb111207b2c","first_computed_at":"2026-07-05T10:23:19.024824Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:23:19.024824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D9XW5MKgXkUaZpruatIfnwncjtbqswctCJzINJdlei03ThW3l2N2EaQ+dje6vPY1hRIQKmFBbDfUe0FgdCo3DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:23:19.025652Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.19340","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f72aabee5b8c4c7d5b9c9ee14d3d5b8808882514c0c45783f59bb03bfe7b7c6","sha256:f9165c63cad9e7d13b22c01b6b24718a0e3c098f01ba9b87a670e0c2950355c7"],"state_sha256":"2c5f4f18464189755a39b8a20d7ddaba3f2e218a511457c3cd87c2b324fa9d3d"}