{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7USGGG42DQS2S3DGKF6NSFIMNG","short_pith_number":"pith:7USGGG42","canonical_record":{"source":{"id":"2406.08335","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T15:41:06Z","cross_cats_sorted":["cs.AI","cs.DB","stat.CO"],"title_canon_sha256":"177de07a89e673f7198721fdb56e3a9c9d463c798debc524160935aae8553816","abstract_canon_sha256":"398abcaf337ed20c80cc5d68d20ea1ada6278b3f0aba2e9b36858c2e024cd590"},"schema_version":"1.0"},"canonical_sha256":"fd24631b9a1c25a96c66517cd9150c6995028a4c55235aa4c899a2c912f2f135","source":{"kind":"arxiv","id":"2406.08335","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.08335","created_at":"2026-07-05T08:34:20Z"},{"alias_kind":"arxiv_version","alias_value":"2406.08335v1","created_at":"2026-07-05T08:34:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08335","created_at":"2026-07-05T08:34:20Z"},{"alias_kind":"pith_short_12","alias_value":"7USGGG42DQS2","created_at":"2026-07-05T08:34:20Z"},{"alias_kind":"pith_short_16","alias_value":"7USGGG42DQS2S3DG","created_at":"2026-07-05T08:34:20Z"},{"alias_kind":"pith_short_8","alias_value":"7USGGG42","created_at":"2026-07-05T08:34:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7USGGG42DQS2S3DGKF6NSFIMNG","target":"record","payload":{"canonical_record":{"source":{"id":"2406.08335","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T15:41:06Z","cross_cats_sorted":["cs.AI","cs.DB","stat.CO"],"title_canon_sha256":"177de07a89e673f7198721fdb56e3a9c9d463c798debc524160935aae8553816","abstract_canon_sha256":"398abcaf337ed20c80cc5d68d20ea1ada6278b3f0aba2e9b36858c2e024cd590"},"schema_version":"1.0"},"canonical_sha256":"fd24631b9a1c25a96c66517cd9150c6995028a4c55235aa4c899a2c912f2f135","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:20.874411Z","signature_b64":"dXEYhk3aukwOs3HpC94DgXfGosjcBwVVxYdATU4FmB72JZ2AzOZ2bFnYhUSk5bLiRnD0pPb5+pJ4c8dHdUwkBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd24631b9a1c25a96c66517cd9150c6995028a4c55235aa4c899a2c912f2f135","last_reissued_at":"2026-07-05T08:34:20.873953Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:20.873953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.08335","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":"2026-07-05T08:34:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+TtnGUGU4pPc1uZtu+vy/oPYGfchiu/3lW+HYfrz37wANHqzG9zFeGBUcgGCXhv/muVGfH2f+vBiiNWi2o4ZBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:55:41.664502Z"},"content_sha256":"213a0ff0168e2823e756e3cd7ea8c88d1f78fb22714d0f91cc29cd91b5fcf647","schema_version":"1.0","event_id":"sha256:213a0ff0168e2823e756e3cd7ea8c88d1f78fb22714d0f91cc29cd91b5fcf647"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7USGGG42DQS2S3DGKF6NSFIMNG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Survey of Pipeline Tools for Data Engineering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DB","stat.CO"],"primary_cat":"cs.LG","authors_text":"Anthony Mbata, Mingjun Zhong, Yaji Sripada","submitted_at":"2024-06-12T15:41:06Z","abstract_excerpt":"Currently, a variety of pipeline tools are available for use in data engineering. Data scientists can use these tools to resolve data wrangling issues associated with data and accomplish some data engineering tasks from data ingestion through data preparation to utilization as input for machine learning (ML). Some of these tools have essential built-in components or can be combined with other tools to perform desired data engineering operations. While some tools are wholly or partly commercial, several open-source tools are available to perform expert-level data engineering tasks. This survey "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08335","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2406.08335/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":"2026-07-05T08:34:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5ChcOONu0ZxADl4Sf5bJP81SFE9NSX1QJ8FScDFh98JVJs3vj5zWw5hF8NumB2tSF/YiNW/t6tKdrJTmmvNmBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:55:41.665364Z"},"content_sha256":"c85fc0c604732b7ddb24e0ddf44490da5f191c6a8d964bee2a5571f1f7d6d8bb","schema_version":"1.0","event_id":"sha256:c85fc0c604732b7ddb24e0ddf44490da5f191c6a8d964bee2a5571f1f7d6d8bb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7USGGG42DQS2S3DGKF6NSFIMNG/bundle.json","state_url":"https://pith.science/pith/7USGGG42DQS2S3DGKF6NSFIMNG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7USGGG42DQS2S3DGKF6NSFIMNG/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":"2026-08-08T11:55:41Z","links":{"resolver":"https://pith.science/pith/7USGGG42DQS2S3DGKF6NSFIMNG","bundle":"https://pith.science/pith/7USGGG42DQS2S3DGKF6NSFIMNG/bundle.json","state":"https://pith.science/pith/7USGGG42DQS2S3DGKF6NSFIMNG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7USGGG42DQS2S3DGKF6NSFIMNG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7USGGG42DQS2S3DGKF6NSFIMNG","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":"398abcaf337ed20c80cc5d68d20ea1ada6278b3f0aba2e9b36858c2e024cd590","cross_cats_sorted":["cs.AI","cs.DB","stat.CO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T15:41:06Z","title_canon_sha256":"177de07a89e673f7198721fdb56e3a9c9d463c798debc524160935aae8553816"},"schema_version":"1.0","source":{"id":"2406.08335","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.08335","created_at":"2026-07-05T08:34:20Z"},{"alias_kind":"arxiv_version","alias_value":"2406.08335v1","created_at":"2026-07-05T08:34:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08335","created_at":"2026-07-05T08:34:20Z"},{"alias_kind":"pith_short_12","alias_value":"7USGGG42DQS2","created_at":"2026-07-05T08:34:20Z"},{"alias_kind":"pith_short_16","alias_value":"7USGGG42DQS2S3DG","created_at":"2026-07-05T08:34:20Z"},{"alias_kind":"pith_short_8","alias_value":"7USGGG42","created_at":"2026-07-05T08:34:20Z"}],"graph_snapshots":[{"event_id":"sha256:c85fc0c604732b7ddb24e0ddf44490da5f191c6a8d964bee2a5571f1f7d6d8bb","target":"graph","created_at":"2026-07-05T08:34:20Z","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/2406.08335/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Currently, a variety of pipeline tools are available for use in data engineering. Data scientists can use these tools to resolve data wrangling issues associated with data and accomplish some data engineering tasks from data ingestion through data preparation to utilization as input for machine learning (ML). Some of these tools have essential built-in components or can be combined with other tools to perform desired data engineering operations. While some tools are wholly or partly commercial, several open-source tools are available to perform expert-level data engineering tasks. This survey ","authors_text":"Anthony Mbata, Mingjun Zhong, Yaji Sripada","cross_cats":["cs.AI","cs.DB","stat.CO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T15:41:06Z","title":"A Survey of Pipeline Tools for Data Engineering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08335","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":"sha256:213a0ff0168e2823e756e3cd7ea8c88d1f78fb22714d0f91cc29cd91b5fcf647","target":"record","created_at":"2026-07-05T08:34:20Z","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":"398abcaf337ed20c80cc5d68d20ea1ada6278b3f0aba2e9b36858c2e024cd590","cross_cats_sorted":["cs.AI","cs.DB","stat.CO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T15:41:06Z","title_canon_sha256":"177de07a89e673f7198721fdb56e3a9c9d463c798debc524160935aae8553816"},"schema_version":"1.0","source":{"id":"2406.08335","kind":"arxiv","version":1}},"canonical_sha256":"fd24631b9a1c25a96c66517cd9150c6995028a4c55235aa4c899a2c912f2f135","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd24631b9a1c25a96c66517cd9150c6995028a4c55235aa4c899a2c912f2f135","first_computed_at":"2026-07-05T08:34:20.873953Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:34:20.873953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dXEYhk3aukwOs3HpC94DgXfGosjcBwVVxYdATU4FmB72JZ2AzOZ2bFnYhUSk5bLiRnD0pPb5+pJ4c8dHdUwkBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:34:20.874411Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.08335","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:213a0ff0168e2823e756e3cd7ea8c88d1f78fb22714d0f91cc29cd91b5fcf647","sha256:c85fc0c604732b7ddb24e0ddf44490da5f191c6a8d964bee2a5571f1f7d6d8bb"],"state_sha256":"2ceb12816ad743a79471763763758d7851cc2c23fb076a04372889203f8f1f4c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l2jqALZifKdoZWi0mWe8ed99yxQHqzjeaD76HM6im2MLiHTnyL1UTrOaF6onXqB8aQcTm+GeUq8zWsKULuEqAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:55:41.671869Z","bundle_sha256":"debb6578aff3b7ec86051d87d1ff767432109b74cb038c740b7eb445ee74af61"}}