{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SHF4WAYY6MMGJQUKKZRWTERCNB","short_pith_number":"pith:SHF4WAYY","schema_version":"1.0","canonical_sha256":"91cbcb0318f31864c28a5663699222685c97fc54fc04b25e83974cb111207b2c","source":{"kind":"arxiv","id":"2403.19340","version":2},"attestation_state":"computed","paper":{"title":"Dataverse: Open-Source ETL (Extract, Transform, Load) 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, Dahyun Kim, Gyoungjin Gim, Hyunbyung Park, Sukyung Lee, Yungi Kim","submitted_at":"2024-03-28T11:57:08Z","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 "},"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":"2403.19340","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-28T11:57:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"282a312711c2d68db143db5eb4637f66172f1cb00514a2b2253b760227fb7417","abstract_canon_sha256":"feb17b0a2c5c50c1b00c8047274bf250cbd7bb593a36fcf8ae874e729d403918"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:23:19.025652Z","signature_b64":"D9XW5MKgXkUaZpruatIfnwncjtbqswctCJzINJdlei03ThW3l2N2EaQ+dje6vPY1hRIQKmFBbDfUe0FgdCo3DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91cbcb0318f31864c28a5663699222685c97fc54fc04b25e83974cb111207b2c","last_reissued_at":"2026-07-05T10:23:19.024824Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:23:19.024824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dataverse: Open-Source ETL (Extract, Transform, Load) 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, Dahyun Kim, Gyoungjin Gim, Hyunbyung Park, Sukyung Lee, Yungi Kim","submitted_at":"2024-03-28T11:57:08Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.19340","kind":"arxiv","version":2},"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/2403.19340/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":"2403.19340","created_at":"2026-07-05T10:23:19.024950+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.19340v2","created_at":"2026-07-05T10:23:19.024950+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.19340","created_at":"2026-07-05T10:23:19.024950+00:00"},{"alias_kind":"pith_short_12","alias_value":"SHF4WAYY6MMG","created_at":"2026-07-05T10:23:19.024950+00:00"},{"alias_kind":"pith_short_16","alias_value":"SHF4WAYY6MMGJQUK","created_at":"2026-07-05T10:23:19.024950+00:00"},{"alias_kind":"pith_short_8","alias_value":"SHF4WAYY","created_at":"2026-07-05T10:23:19.024950+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.18458","citing_title":"A Survey of LLM $\\times$ DATA","ref_index":305,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SHF4WAYY6MMGJQUKKZRWTERCNB","json":"https://pith.science/pith/SHF4WAYY6MMGJQUKKZRWTERCNB.json","graph_json":"https://pith.science/api/pith-number/SHF4WAYY6MMGJQUKKZRWTERCNB/graph.json","events_json":"https://pith.science/api/pith-number/SHF4WAYY6MMGJQUKKZRWTERCNB/events.json","paper":"https://pith.science/paper/SHF4WAYY"},"agent_actions":{"view_html":"https://pith.science/pith/SHF4WAYY6MMGJQUKKZRWTERCNB","download_json":"https://pith.science/pith/SHF4WAYY6MMGJQUKKZRWTERCNB.json","view_paper":"https://pith.science/paper/SHF4WAYY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.19340&json=true","fetch_graph":"https://pith.science/api/pith-number/SHF4WAYY6MMGJQUKKZRWTERCNB/graph.json","fetch_events":"https://pith.science/api/pith-number/SHF4WAYY6MMGJQUKKZRWTERCNB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SHF4WAYY6MMGJQUKKZRWTERCNB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SHF4WAYY6MMGJQUKKZRWTERCNB/action/storage_attestation","attest_author":"https://pith.science/pith/SHF4WAYY6MMGJQUKKZRWTERCNB/action/author_attestation","sign_citation":"https://pith.science/pith/SHF4WAYY6MMGJQUKKZRWTERCNB/action/citation_signature","submit_replication":"https://pith.science/pith/SHF4WAYY6MMGJQUKKZRWTERCNB/action/replication_record"}},"created_at":"2026-07-05T10:23:19.024950+00:00","updated_at":"2026-07-05T10:23:19.024950+00:00"}