{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:CJJ6KBFDBWWTPSLGSZEOHKIPEK","short_pith_number":"pith:CJJ6KBFD","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"},"canonical_sha256":"1253e504a30dad37c9669648e3a90f22b1f6515d2038c91a4a723f2d7d891fbb","source":{"kind":"arxiv","id":"1409.0798","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1409.0798","created_at":"2026-05-18T02:43:46Z"},{"alias_kind":"arxiv_version","alias_value":"1409.0798v1","created_at":"2026-05-18T02:43:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1409.0798","created_at":"2026-05-18T02:43:46Z"},{"alias_kind":"pith_short_12","alias_value":"CJJ6KBFDBWWT","created_at":"2026-05-18T12:28:22Z"},{"alias_kind":"pith_short_16","alias_value":"CJJ6KBFDBWWTPSLG","created_at":"2026-05-18T12:28:22Z"},{"alias_kind":"pith_short_8","alias_value":"CJJ6KBFD","created_at":"2026-05-18T12:28:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:CJJ6KBFDBWWTPSLGSZEOHKIPEK","target":"record","payload":{"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"},"canonical_sha256":"1253e504a30dad37c9669648e3a90f22b1f6515d2038c91a4a723f2d7d891fbb","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"},"source_kind":"arxiv","source_id":"1409.0798","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":"2026-05-18T02:43:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+jVOCIBS1AFlyvHkhyXCyBMiBF5VS7Ike1Y4tz4jYTlqGR1qRh6fX/aq5DUOGHgNc0mZFHHfKyyKx7c4r5YCBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T20:09:24.273516Z"},"content_sha256":"d4858e2b6ebfb06e020d72b9e96573c9bd31c2f5a1184d2d8ce884e842aefe5d","schema_version":"1.0","event_id":"sha256:d4858e2b6ebfb06e020d72b9e96573c9bd31c2f5a1184d2d8ce884e842aefe5d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:CJJ6KBFDBWWTPSLGSZEOHKIPEK","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:43:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"izODmi2bWhJIswrMZppYVfKjOYrBu/9HfOpPkHLehOO3/pcEUtgtMSLUFcCQ6aGZ8I+oVKRhsih6kJY5FXm8Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T20:09:24.274174Z"},"content_sha256":"24dff5c89193a00e0e8110c6463b092e297f1ecf5ae6d7ac9f51b04b7f05f823","schema_version":"1.0","event_id":"sha256:24dff5c89193a00e0e8110c6463b092e297f1ecf5ae6d7ac9f51b04b7f05f823"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CJJ6KBFDBWWTPSLGSZEOHKIPEK/bundle.json","state_url":"https://pith.science/pith/CJJ6KBFDBWWTPSLGSZEOHKIPEK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CJJ6KBFDBWWTPSLGSZEOHKIPEK/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":"2026-05-27T20:09:24Z","links":{"resolver":"https://pith.science/pith/CJJ6KBFDBWWTPSLGSZEOHKIPEK","bundle":"https://pith.science/pith/CJJ6KBFDBWWTPSLGSZEOHKIPEK/bundle.json","state":"https://pith.science/pith/CJJ6KBFDBWWTPSLGSZEOHKIPEK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CJJ6KBFDBWWTPSLGSZEOHKIPEK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:CJJ6KBFDBWWTPSLGSZEOHKIPEK","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":"698a463ba307ee5debf8883da2c5152289653fa060558559b3737ba2a1ad50a9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2014-09-02T17:16:47Z","title_canon_sha256":"eac6bb013203fd343afbc70ecb4d987f475d2e9f704c55b1be718321cf084f44"},"schema_version":"1.0","source":{"id":"1409.0798","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1409.0798","created_at":"2026-05-18T02:43:46Z"},{"alias_kind":"arxiv_version","alias_value":"1409.0798v1","created_at":"2026-05-18T02:43:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1409.0798","created_at":"2026-05-18T02:43:46Z"},{"alias_kind":"pith_short_12","alias_value":"CJJ6KBFDBWWT","created_at":"2026-05-18T12:28:22Z"},{"alias_kind":"pith_short_16","alias_value":"CJJ6KBFDBWWTPSLG","created_at":"2026-05-18T12:28:22Z"},{"alias_kind":"pith_short_8","alias_value":"CJJ6KBFD","created_at":"2026-05-18T12:28:22Z"}],"graph_snapshots":[{"event_id":"sha256:24dff5c89193a00e0e8110c6463b092e297f1ecf5ae6d7ac9f51b04b7f05f823","target":"graph","created_at":"2026-05-18T02:43:46Z","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"},"paper":{"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.","authors_text":"Aaron J. Elmore, Aditya G. Parameswaran, Amit Chavan, Amol Deshpande, Anant Bhardwaj, Samuel Madden, Souvik Bhattacherjee","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2014-09-02T17:16:47Z","title":"DataHub: Collaborative Data Science & Dataset Version Management at Scale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1409.0798","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:d4858e2b6ebfb06e020d72b9e96573c9bd31c2f5a1184d2d8ce884e842aefe5d","target":"record","created_at":"2026-05-18T02:43:46Z","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":"698a463ba307ee5debf8883da2c5152289653fa060558559b3737ba2a1ad50a9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2014-09-02T17:16:47Z","title_canon_sha256":"eac6bb013203fd343afbc70ecb4d987f475d2e9f704c55b1be718321cf084f44"},"schema_version":"1.0","source":{"id":"1409.0798","kind":"arxiv","version":1}},"canonical_sha256":"1253e504a30dad37c9669648e3a90f22b1f6515d2038c91a4a723f2d7d891fbb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1253e504a30dad37c9669648e3a90f22b1f6515d2038c91a4a723f2d7d891fbb","first_computed_at":"2026-05-18T02:43:46.098260Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:43:46.098260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kdEEBQZBN+zS9glOvkk3wy0etgbR3djLnRIzaIOgfj5SpzzUxDxmzyZR/UiCihB8cFuNkn53IiUJg5xB5Bu0Dw==","signature_status":"signed_v1","signed_at":"2026-05-18T02:43:46.098714Z","signed_message":"canonical_sha256_bytes"},"source_id":"1409.0798","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4858e2b6ebfb06e020d72b9e96573c9bd31c2f5a1184d2d8ce884e842aefe5d","sha256:24dff5c89193a00e0e8110c6463b092e297f1ecf5ae6d7ac9f51b04b7f05f823"],"state_sha256":"3b18bbfb0562b5b22d7cf8138636a7a001285fda523d5202dfc79f58ffb8bbb2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vk9F7zKBAhKxdlMZik7D9HrxxeiskDsz2vGlMoHMQptj9vqHhlhPuhOgpxCJAP26tOTejiisSCTj7ozpF8DeDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T20:09:24.277651Z","bundle_sha256":"27ba51bc338c8a2c6664fb7b6f99cc0d7a291e77af1ec5d79b3aa815ded0eb6c"}}