{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:CJJ6KBFDBWWTPSLGSZEOHKIPEK","short_pith_number":"pith:CJJ6KBFD","schema_version":"1.0","canonical_sha256":"1253e504a30dad37c9669648e3a90f22b1f6515d2038c91a4a723f2d7d891fbb","source":{"kind":"arxiv","id":"1409.0798","version":1},"attestation_state":"computed","paper":{"title":"DataHub: Collaborative Data Science & Dataset Version Management at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Aaron J. Elmore, Aditya G. Parameswaran, Amit Chavan, Amol Deshpande, Anant Bhardwaj, Samuel Madden, Souvik Bhattacherjee","submitted_at":"2014-09-02T17:16:47Z","abstract_excerpt":"Relational databases have limited support for data collaboration, where teams collaboratively curate and analyze large datasets. Inspired by software version control systems like git, we propose (a) a dataset version control system, giving users the ability to create, branch, merge, difference and search large, divergent collections of datasets, and (b) a platform, DataHub, that gives users the ability to perform collaborative data analysis building on this version control system. We outline the challenges in providing dataset version control at scale."},"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":"1409.0798","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2014-09-02T17:16:47Z","cross_cats_sorted":[],"title_canon_sha256":"eac6bb013203fd343afbc70ecb4d987f475d2e9f704c55b1be718321cf084f44","abstract_canon_sha256":"698a463ba307ee5debf8883da2c5152289653fa060558559b3737ba2a1ad50a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:43:46.098714Z","signature_b64":"kdEEBQZBN+zS9glOvkk3wy0etgbR3djLnRIzaIOgfj5SpzzUxDxmzyZR/UiCihB8cFuNkn53IiUJg5xB5Bu0Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1253e504a30dad37c9669648e3a90f22b1f6515d2038c91a4a723f2d7d891fbb","last_reissued_at":"2026-05-18T02:43:46.098260Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:43:46.098260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DataHub: Collaborative Data Science & Dataset Version Management at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Aaron J. Elmore, Aditya G. Parameswaran, Amit Chavan, Amol Deshpande, Anant Bhardwaj, Samuel Madden, Souvik Bhattacherjee","submitted_at":"2014-09-02T17:16:47Z","abstract_excerpt":"Relational databases have limited support for data collaboration, where teams collaboratively curate and analyze large datasets. Inspired by software version control systems like git, we propose (a) a dataset version control system, giving users the ability to create, branch, merge, difference and search large, divergent collections of datasets, and (b) a platform, DataHub, that gives users the ability to perform collaborative data analysis building on this version control system. We outline the challenges in providing dataset version control at scale."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1409.0798","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":""},"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":"1409.0798","created_at":"2026-05-18T02:43:46.098334+00:00"},{"alias_kind":"arxiv_version","alias_value":"1409.0798v1","created_at":"2026-05-18T02:43:46.098334+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1409.0798","created_at":"2026-05-18T02:43:46.098334+00:00"},{"alias_kind":"pith_short_12","alias_value":"CJJ6KBFDBWWT","created_at":"2026-05-18T12:28:22.404517+00:00"},{"alias_kind":"pith_short_16","alias_value":"CJJ6KBFDBWWTPSLG","created_at":"2026-05-18T12:28:22.404517+00:00"},{"alias_kind":"pith_short_8","alias_value":"CJJ6KBFD","created_at":"2026-05-18T12:28:22.404517+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CJJ6KBFDBWWTPSLGSZEOHKIPEK","json":"https://pith.science/pith/CJJ6KBFDBWWTPSLGSZEOHKIPEK.json","graph_json":"https://pith.science/api/pith-number/CJJ6KBFDBWWTPSLGSZEOHKIPEK/graph.json","events_json":"https://pith.science/api/pith-number/CJJ6KBFDBWWTPSLGSZEOHKIPEK/events.json","paper":"https://pith.science/paper/CJJ6KBFD"},"agent_actions":{"view_html":"https://pith.science/pith/CJJ6KBFDBWWTPSLGSZEOHKIPEK","download_json":"https://pith.science/pith/CJJ6KBFDBWWTPSLGSZEOHKIPEK.json","view_paper":"https://pith.science/paper/CJJ6KBFD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1409.0798&json=true","fetch_graph":"https://pith.science/api/pith-number/CJJ6KBFDBWWTPSLGSZEOHKIPEK/graph.json","fetch_events":"https://pith.science/api/pith-number/CJJ6KBFDBWWTPSLGSZEOHKIPEK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CJJ6KBFDBWWTPSLGSZEOHKIPEK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CJJ6KBFDBWWTPSLGSZEOHKIPEK/action/storage_attestation","attest_author":"https://pith.science/pith/CJJ6KBFDBWWTPSLGSZEOHKIPEK/action/author_attestation","sign_citation":"https://pith.science/pith/CJJ6KBFDBWWTPSLGSZEOHKIPEK/action/citation_signature","submit_replication":"https://pith.science/pith/CJJ6KBFDBWWTPSLGSZEOHKIPEK/action/replication_record"}},"created_at":"2026-05-18T02:43:46.098334+00:00","updated_at":"2026-05-18T02:43:46.098334+00:00"}