{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SHF4WAYY6MMGJQUKKZRWTERCNB","short_pith_number":"pith:SHF4WAYY","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"},"canonical_sha256":"91cbcb0318f31864c28a5663699222685c97fc54fc04b25e83974cb111207b2c","source":{"kind":"arxiv","id":"2403.19340","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SHF4WAYY6MMGJQUKKZRWTERCNB","target":"record","payload":{"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"},"canonical_sha256":"91cbcb0318f31864c28a5663699222685c97fc54fc04b25e83974cb111207b2c","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"},"source_kind":"arxiv","source_id":"2403.19340","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:23:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CYCKCwyyVc1+D87IcLDU9gz27015CBtUG/cPePoJgtGvjr3lmWkiA6G8Tcs+OtTqz7fg96bcFRaSEougoaoIBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T11:15:35.507996Z"},"content_sha256":"8f72aabee5b8c4c7d5b9c9ee14d3d5b8808882514c0c45783f59bb03bfe7b7c6","schema_version":"1.0","event_id":"sha256:8f72aabee5b8c4c7d5b9c9ee14d3d5b8808882514c0c45783f59bb03bfe7b7c6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SHF4WAYY6MMGJQUKKZRWTERCNB","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:23:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bTvXftUxCnq6ubM78/dX4niqYwjZd7TFXqNUgFmxcMoCWUHTSRbhrbfGOq60eFhToLNalh1zlCNk0J/I9byiDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T11:15:35.509379Z"},"content_sha256":"f9165c63cad9e7d13b22c01b6b24718a0e3c098f01ba9b87a670e0c2950355c7","schema_version":"1.0","event_id":"sha256:f9165c63cad9e7d13b22c01b6b24718a0e3c098f01ba9b87a670e0c2950355c7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SHF4WAYY6MMGJQUKKZRWTERCNB/bundle.json","state_url":"https://pith.science/pith/SHF4WAYY6MMGJQUKKZRWTERCNB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SHF4WAYY6MMGJQUKKZRWTERCNB/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":"2026-08-16T11:15:35Z","links":{"resolver":"https://pith.science/pith/SHF4WAYY6MMGJQUKKZRWTERCNB","bundle":"https://pith.science/pith/SHF4WAYY6MMGJQUKKZRWTERCNB/bundle.json","state":"https://pith.science/pith/SHF4WAYY6MMGJQUKKZRWTERCNB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SHF4WAYY6MMGJQUKKZRWTERCNB/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9VHXvssDBcrEfDX+3WxCOQF0+PgRLhtjWUVkuZG5StwRfTMIftgyvtckG8UoU8ynyKaqRlSVhI4UiDB8Zzb2Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T11:15:35.514606Z","bundle_sha256":"609dea1fba9e788d37c887a2f2700926854be1155a03a71add7221adfe91eee7"}}