{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:3S7PUINBEDOFNRYBWHUG4K4L5V","short_pith_number":"pith:3S7PUINB","canonical_record":{"source":{"id":"1811.09248","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-11-22T17:34:35Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"3f86d045abc8cf286bcd4f882b926f6fd20d99f75575d8cd7ac369f471149e6a","abstract_canon_sha256":"4a8e7d5da083770d48ad1a2af961452e7715498cffd96d3db0cbf5e025c10627"},"schema_version":"1.0"},"canonical_sha256":"dcbefa21a120dc56c701b1e86e2b8bed72cec9f1e654a0c9061461435a35d98f","source":{"kind":"arxiv","id":"1811.09248","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.09248","created_at":"2026-05-18T00:00:03Z"},{"alias_kind":"arxiv_version","alias_value":"1811.09248v1","created_at":"2026-05-18T00:00:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.09248","created_at":"2026-05-18T00:00:03Z"},{"alias_kind":"pith_short_12","alias_value":"3S7PUINBEDOF","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"3S7PUINBEDOFNRYB","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"3S7PUINB","created_at":"2026-05-18T12:32:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:3S7PUINBEDOFNRYBWHUG4K4L5V","target":"record","payload":{"canonical_record":{"source":{"id":"1811.09248","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-11-22T17:34:35Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"3f86d045abc8cf286bcd4f882b926f6fd20d99f75575d8cd7ac369f471149e6a","abstract_canon_sha256":"4a8e7d5da083770d48ad1a2af961452e7715498cffd96d3db0cbf5e025c10627"},"schema_version":"1.0"},"canonical_sha256":"dcbefa21a120dc56c701b1e86e2b8bed72cec9f1e654a0c9061461435a35d98f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:03.823752Z","signature_b64":"FDMWtNTuOibI04grKBlu/pvvsRBIYzG7WNT7hydUpueqChsPwmRq6FVoXF3ztwlmITaLcxeCXynH5n6xO+3dCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcbefa21a120dc56c701b1e86e2b8bed72cec9f1e654a0c9061461435a35d98f","last_reissued_at":"2026-05-18T00:00:03.823203Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:03.823203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.09248","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":"2026-05-18T00:00:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TJYMATck+SQU6UI071droUMCns4+vDv5N95nK7xWeL6pshotj8udvqRSAkPxW/zVzH1XoMstta1j7ie5l0tVCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T02:36:38.163983Z"},"content_sha256":"bbd0f18795be7f63c3de7c7071ab0c2385cde5a84f1595b53655cc208d6cb794","schema_version":"1.0","event_id":"sha256:bbd0f18795be7f63c3de7c7071ab0c2385cde5a84f1595b53655cc208d6cb794"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:3S7PUINBEDOFNRYBWHUG4K4L5V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Context Informed Data Wrangling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.DB","authors_text":"Alex Bogatu, Alvaro A. A. Fernandes, Cristina Civili, Edward Abel, John Keane, Leonid Libkin, Martin Koehler, Nikolaos Konstantinou, Norman W. Paton","submitted_at":"2018-11-22T17:34:35Z","abstract_excerpt":"The process of preparing potentially large and complex data sets for further analysis or manual examination is often called data wrangling. In classical warehousing environments, the steps in such a process have been carried out using Extract-Transform-Load platforms, with significant manual involvement in specifying, configuring or tuning many of them. Cost-effective data wrangling processes need to ensure that data wrangling steps benefit from automation wherever possible. In this paper, we define a methodology to fully automate an end-to-end data wrangling process incorporating data context"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.09248","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":"2026-05-18T00:00:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BM2zPb842+Y9dBCMbYpXhpWPExjs+nhWuyK7VSvEEU/WJtC/qyC1AZqt0Y4gbewH+tpX66X88gjm6gTe4UY6Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T02:36:38.164402Z"},"content_sha256":"79478e006cbe893477948609669667b5dbfd6303e23b067d0f0822091387c16e","schema_version":"1.0","event_id":"sha256:79478e006cbe893477948609669667b5dbfd6303e23b067d0f0822091387c16e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3S7PUINBEDOFNRYBWHUG4K4L5V/bundle.json","state_url":"https://pith.science/pith/3S7PUINBEDOFNRYBWHUG4K4L5V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3S7PUINBEDOFNRYBWHUG4K4L5V/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":"2026-05-30T02:36:38Z","links":{"resolver":"https://pith.science/pith/3S7PUINBEDOFNRYBWHUG4K4L5V","bundle":"https://pith.science/pith/3S7PUINBEDOFNRYBWHUG4K4L5V/bundle.json","state":"https://pith.science/pith/3S7PUINBEDOFNRYBWHUG4K4L5V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3S7PUINBEDOFNRYBWHUG4K4L5V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:3S7PUINBEDOFNRYBWHUG4K4L5V","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":"4a8e7d5da083770d48ad1a2af961452e7715498cffd96d3db0cbf5e025c10627","cross_cats_sorted":["cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-11-22T17:34:35Z","title_canon_sha256":"3f86d045abc8cf286bcd4f882b926f6fd20d99f75575d8cd7ac369f471149e6a"},"schema_version":"1.0","source":{"id":"1811.09248","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.09248","created_at":"2026-05-18T00:00:03Z"},{"alias_kind":"arxiv_version","alias_value":"1811.09248v1","created_at":"2026-05-18T00:00:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.09248","created_at":"2026-05-18T00:00:03Z"},{"alias_kind":"pith_short_12","alias_value":"3S7PUINBEDOF","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"3S7PUINBEDOFNRYB","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"3S7PUINB","created_at":"2026-05-18T12:32:05Z"}],"graph_snapshots":[{"event_id":"sha256:79478e006cbe893477948609669667b5dbfd6303e23b067d0f0822091387c16e","target":"graph","created_at":"2026-05-18T00:00:03Z","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":"The process of preparing potentially large and complex data sets for further analysis or manual examination is often called data wrangling. In classical warehousing environments, the steps in such a process have been carried out using Extract-Transform-Load platforms, with significant manual involvement in specifying, configuring or tuning many of them. Cost-effective data wrangling processes need to ensure that data wrangling steps benefit from automation wherever possible. In this paper, we define a methodology to fully automate an end-to-end data wrangling process incorporating data context","authors_text":"Alex Bogatu, Alvaro A. A. Fernandes, Cristina Civili, Edward Abel, John Keane, Leonid Libkin, Martin Koehler, Nikolaos Konstantinou, Norman W. Paton","cross_cats":["cs.DC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-11-22T17:34:35Z","title":"Data Context Informed Data Wrangling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.09248","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:bbd0f18795be7f63c3de7c7071ab0c2385cde5a84f1595b53655cc208d6cb794","target":"record","created_at":"2026-05-18T00:00:03Z","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":"4a8e7d5da083770d48ad1a2af961452e7715498cffd96d3db0cbf5e025c10627","cross_cats_sorted":["cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-11-22T17:34:35Z","title_canon_sha256":"3f86d045abc8cf286bcd4f882b926f6fd20d99f75575d8cd7ac369f471149e6a"},"schema_version":"1.0","source":{"id":"1811.09248","kind":"arxiv","version":1}},"canonical_sha256":"dcbefa21a120dc56c701b1e86e2b8bed72cec9f1e654a0c9061461435a35d98f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dcbefa21a120dc56c701b1e86e2b8bed72cec9f1e654a0c9061461435a35d98f","first_computed_at":"2026-05-18T00:00:03.823203Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:00:03.823203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FDMWtNTuOibI04grKBlu/pvvsRBIYzG7WNT7hydUpueqChsPwmRq6FVoXF3ztwlmITaLcxeCXynH5n6xO+3dCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:00:03.823752Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.09248","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bbd0f18795be7f63c3de7c7071ab0c2385cde5a84f1595b53655cc208d6cb794","sha256:79478e006cbe893477948609669667b5dbfd6303e23b067d0f0822091387c16e"],"state_sha256":"eacb87841018a6e623744baa8ef8a7d106b9bd81a937fb63845cb93523eae8e9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"soGgcHJs5kxa22nZ4aI+wPkyoCPIDYsUTaAeWrZ1sNDgiNGxJLmdCHQRGxn64qQohn9Q1axPauJlf8jEReSaAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T02:36:38.166926Z","bundle_sha256":"746e7ec2fcc6718ee791cd147f4859cab36e51d1ce521c9896a8f4feb268ba03"}}