{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FI2QGI2IPHL4WDXGCT663QHXPX","short_pith_number":"pith:FI2QGI2I","canonical_record":{"source":{"id":"2507.23118","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-30T21:46:22Z","cross_cats_sorted":[],"title_canon_sha256":"4fe5318975701c056f9c49cdd99c44e9f8013bdda4b69d6168f3e6dbf028ed25","abstract_canon_sha256":"a8fa44ba5a198860a95a94bb96977f9f3b19aef0f85750b10b72bfe905c21dac"},"schema_version":"1.0"},"canonical_sha256":"2a3503234879d7cb0ee614fdedc0f77de77effd0525d5230e04ecd29544856b8","source":{"kind":"arxiv","id":"2507.23118","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.23118","created_at":"2026-07-05T11:46:05Z"},{"alias_kind":"arxiv_version","alias_value":"2507.23118v1","created_at":"2026-07-05T11:46:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.23118","created_at":"2026-07-05T11:46:05Z"},{"alias_kind":"pith_short_12","alias_value":"FI2QGI2IPHL4","created_at":"2026-07-05T11:46:05Z"},{"alias_kind":"pith_short_16","alias_value":"FI2QGI2IPHL4WDXG","created_at":"2026-07-05T11:46:05Z"},{"alias_kind":"pith_short_8","alias_value":"FI2QGI2I","created_at":"2026-07-05T11:46:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FI2QGI2IPHL4WDXGCT663QHXPX","target":"record","payload":{"canonical_record":{"source":{"id":"2507.23118","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-30T21:46:22Z","cross_cats_sorted":[],"title_canon_sha256":"4fe5318975701c056f9c49cdd99c44e9f8013bdda4b69d6168f3e6dbf028ed25","abstract_canon_sha256":"a8fa44ba5a198860a95a94bb96977f9f3b19aef0f85750b10b72bfe905c21dac"},"schema_version":"1.0"},"canonical_sha256":"2a3503234879d7cb0ee614fdedc0f77de77effd0525d5230e04ecd29544856b8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:05.721834Z","signature_b64":"29m5v/Tbj4Qz9Oafvmv1HBJEdTGpjzkIBWTrnGff4zfBuIYUBK5D/w7hHPoaeBAwQ6761vRHMh6/LH0VYiYoCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a3503234879d7cb0ee614fdedc0f77de77effd0525d5230e04ecd29544856b8","last_reissued_at":"2026-07-05T11:46:05.721274Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:05.721274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.23118","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":"2026-07-05T11:46:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sFfUMYNYvHznqTUgoK/dSjpkSGq5eK1uOG1QBehzSfFxVRMRUBnvcOqDuRidkDbsDGCU/SnGkhBTQbyG3ZxzDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T20:44:45.333965Z"},"content_sha256":"97ea5178ea0b23f406ab3c116bc013b00bddedeb829249e17fcf4b04ea2ac4bb","schema_version":"1.0","event_id":"sha256:97ea5178ea0b23f406ab3c116bc013b00bddedeb829249e17fcf4b04ea2ac4bb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FI2QGI2IPHL4WDXGCT663QHXPX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FlowETL: An Autonomous Example-Driven Pipeline for Data Engineering","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Marcel Jaspars, Mattia Di Profio, Mingjun Zhong, Yaji Sripada","submitted_at":"2025-07-30T21:46:22Z","abstract_excerpt":"The Extract, Transform, Load (ETL) workflow is fundamental for populating and maintaining data warehouses and other data stores accessed by analysts for downstream tasks. A major shortcoming of modern ETL solutions is the extensive need for a human-in-the-loop, required to design and implement context-specific, and often non-generalisable transformations. While related work in the field of ETL automation shows promising progress, there is a lack of solutions capable of automatically designing and applying these transformations. We present FlowETL, a novel example-based autonomous ETL pipeline "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.23118","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/2507.23118/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":"2026-07-05T11:46:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HIaT8Cgfn6li85c9uNSB0haVOtqLtt5mb+G7UTgk2X9NoCODrEGL0wSXhcSCEq+UFF0o32j+QAUjpnaTs7IvBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T20:44:45.334526Z"},"content_sha256":"1bc0d978d0838609edab1205a6fe9cc3143a20429a20165009942a8266a373c2","schema_version":"1.0","event_id":"sha256:1bc0d978d0838609edab1205a6fe9cc3143a20429a20165009942a8266a373c2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FI2QGI2IPHL4WDXGCT663QHXPX/bundle.json","state_url":"https://pith.science/pith/FI2QGI2IPHL4WDXGCT663QHXPX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FI2QGI2IPHL4WDXGCT663QHXPX/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":"2026-08-06T20:44:45Z","links":{"resolver":"https://pith.science/pith/FI2QGI2IPHL4WDXGCT663QHXPX","bundle":"https://pith.science/pith/FI2QGI2IPHL4WDXGCT663QHXPX/bundle.json","state":"https://pith.science/pith/FI2QGI2IPHL4WDXGCT663QHXPX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FI2QGI2IPHL4WDXGCT663QHXPX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FI2QGI2IPHL4WDXGCT663QHXPX","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":"a8fa44ba5a198860a95a94bb96977f9f3b19aef0f85750b10b72bfe905c21dac","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-30T21:46:22Z","title_canon_sha256":"4fe5318975701c056f9c49cdd99c44e9f8013bdda4b69d6168f3e6dbf028ed25"},"schema_version":"1.0","source":{"id":"2507.23118","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.23118","created_at":"2026-07-05T11:46:05Z"},{"alias_kind":"arxiv_version","alias_value":"2507.23118v1","created_at":"2026-07-05T11:46:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.23118","created_at":"2026-07-05T11:46:05Z"},{"alias_kind":"pith_short_12","alias_value":"FI2QGI2IPHL4","created_at":"2026-07-05T11:46:05Z"},{"alias_kind":"pith_short_16","alias_value":"FI2QGI2IPHL4WDXG","created_at":"2026-07-05T11:46:05Z"},{"alias_kind":"pith_short_8","alias_value":"FI2QGI2I","created_at":"2026-07-05T11:46:05Z"}],"graph_snapshots":[{"event_id":"sha256:1bc0d978d0838609edab1205a6fe9cc3143a20429a20165009942a8266a373c2","target":"graph","created_at":"2026-07-05T11:46:05Z","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/2507.23118/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Extract, Transform, Load (ETL) workflow is fundamental for populating and maintaining data warehouses and other data stores accessed by analysts for downstream tasks. A major shortcoming of modern ETL solutions is the extensive need for a human-in-the-loop, required to design and implement context-specific, and often non-generalisable transformations. While related work in the field of ETL automation shows promising progress, there is a lack of solutions capable of automatically designing and applying these transformations. We present FlowETL, a novel example-based autonomous ETL pipeline ","authors_text":"Marcel Jaspars, Mattia Di Profio, Mingjun Zhong, Yaji Sripada","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-30T21:46:22Z","title":"FlowETL: An Autonomous Example-Driven Pipeline for Data Engineering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.23118","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":"sha256:97ea5178ea0b23f406ab3c116bc013b00bddedeb829249e17fcf4b04ea2ac4bb","target":"record","created_at":"2026-07-05T11:46:05Z","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":"a8fa44ba5a198860a95a94bb96977f9f3b19aef0f85750b10b72bfe905c21dac","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-30T21:46:22Z","title_canon_sha256":"4fe5318975701c056f9c49cdd99c44e9f8013bdda4b69d6168f3e6dbf028ed25"},"schema_version":"1.0","source":{"id":"2507.23118","kind":"arxiv","version":1}},"canonical_sha256":"2a3503234879d7cb0ee614fdedc0f77de77effd0525d5230e04ecd29544856b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a3503234879d7cb0ee614fdedc0f77de77effd0525d5230e04ecd29544856b8","first_computed_at":"2026-07-05T11:46:05.721274Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:46:05.721274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"29m5v/Tbj4Qz9Oafvmv1HBJEdTGpjzkIBWTrnGff4zfBuIYUBK5D/w7hHPoaeBAwQ6761vRHMh6/LH0VYiYoCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:46:05.721834Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.23118","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97ea5178ea0b23f406ab3c116bc013b00bddedeb829249e17fcf4b04ea2ac4bb","sha256:1bc0d978d0838609edab1205a6fe9cc3143a20429a20165009942a8266a373c2"],"state_sha256":"e7606e6f83ad508fed2756d4e0a1bfa01efb347998c9341b3c562a982cd10c24"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZtRMwKf7yM07wDbW2EQ5g9uwdUn9IYZFi8+BJKv1Y5o+YBci8QFbrHnEsX98uFRO9OJ0GwBcuQ3J3ngm1/8OBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T20:44:45.340025Z","bundle_sha256":"e14af08ded77252df3cd19c717549254b6fa4ea6653194c5f75978b12b98d163"}}