{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4RYNOSIMJSOESK7LROPP5KV24E","short_pith_number":"pith:4RYNOSIM","canonical_record":{"source":{"id":"2507.16073","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-07-21T21:20:25Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"bc53a64c3a1903578504c21b88c2d1fd348e9162ddf06cd9eee20e3eb75061dd","abstract_canon_sha256":"4db6e0fb22b8370d8a9bf9f19b4bfe24b62fbaf760d348b50398636cde70035c"},"schema_version":"1.0"},"canonical_sha256":"e470d7490c4c9c492beb8b9efeaabae11a764a26462dad9ae31cc042fee22554","source":{"kind":"arxiv","id":"2507.16073","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.16073","created_at":"2026-07-05T11:41:02Z"},{"alias_kind":"arxiv_version","alias_value":"2507.16073v1","created_at":"2026-07-05T11:41:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.16073","created_at":"2026-07-05T11:41:02Z"},{"alias_kind":"pith_short_12","alias_value":"4RYNOSIMJSOE","created_at":"2026-07-05T11:41:02Z"},{"alias_kind":"pith_short_16","alias_value":"4RYNOSIMJSOESK7L","created_at":"2026-07-05T11:41:02Z"},{"alias_kind":"pith_short_8","alias_value":"4RYNOSIM","created_at":"2026-07-05T11:41:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4RYNOSIMJSOESK7LROPP5KV24E","target":"record","payload":{"canonical_record":{"source":{"id":"2507.16073","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-07-21T21:20:25Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"bc53a64c3a1903578504c21b88c2d1fd348e9162ddf06cd9eee20e3eb75061dd","abstract_canon_sha256":"4db6e0fb22b8370d8a9bf9f19b4bfe24b62fbaf760d348b50398636cde70035c"},"schema_version":"1.0"},"canonical_sha256":"e470d7490c4c9c492beb8b9efeaabae11a764a26462dad9ae31cc042fee22554","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:41:02.329556Z","signature_b64":"etWItvnk0n2QWrLcPAgJo7cMoSgxbZ9ud0HzPmoqcO2p3ZpEX29EzjWfDzSR0UihfczbKKXtZXkNoW5UHvFAAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e470d7490c4c9c492beb8b9efeaabae11a764a26462dad9ae31cc042fee22554","last_reissued_at":"2026-07-05T11:41:02.329078Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:41:02.329078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.16073","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":"2026-07-05T11:41:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AAT/N71CHRDwU2cMVg5WJEJf8ZORI92ihfn4X87RHRldEckIjiqYL82eGra4DcqB/WEvoFwcgHGyH927LKfLDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:45:48.049918Z"},"content_sha256":"5d5d77f5f29ea2b90b86b9ad3405080e833d1155ca5ecf5aadb52c8629b52182","schema_version":"1.0","event_id":"sha256:5d5d77f5f29ea2b90b86b9ad3405080e833d1155ca5ecf5aadb52c8629b52182"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4RYNOSIMJSOESK7LROPP5KV24E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Buckaroo: A Direct Manipulation Visual Data Wrangler","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.HC","authors_text":"Andrew McNutt, Annabelle Warner, El Kindi Rezig, Paul Rosen","submitted_at":"2025-07-21T21:20:25Z","abstract_excerpt":"Preparing datasets -- a critical phase known as data wrangling -- constitutes the dominant phase of data science development, consuming upwards of 80% of the total project time. This phase encompasses a myriad of tasks: parsing data, restructuring it for analysis, repairing inaccuracies, merging sources, eliminating duplicates, and ensuring overall data integrity. Traditional approaches, typically through manual coding in languages such as Python or using spreadsheets, are not only laborious but also error-prone. These issues range from missing entries and formatting inconsistencies to data ty"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.16073","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/2507.16073/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":"2026-07-05T11:41:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EPRMY/pdheph4dwOzs2r8/TR+0RA+sJ4uNI/IdC8N1Y+duzcZICaCeaEN2B9JYhHelqbu4Mc1JNqioAFxNgFCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:45:48.050423Z"},"content_sha256":"fb0a15912d2ba4a7bbe23aeb407c508078b21abc69d7afac8447ff65ae91cf27","schema_version":"1.0","event_id":"sha256:fb0a15912d2ba4a7bbe23aeb407c508078b21abc69d7afac8447ff65ae91cf27"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4RYNOSIMJSOESK7LROPP5KV24E/bundle.json","state_url":"https://pith.science/pith/4RYNOSIMJSOESK7LROPP5KV24E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4RYNOSIMJSOESK7LROPP5KV24E/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":"2026-08-09T06:45:48Z","links":{"resolver":"https://pith.science/pith/4RYNOSIMJSOESK7LROPP5KV24E","bundle":"https://pith.science/pith/4RYNOSIMJSOESK7LROPP5KV24E/bundle.json","state":"https://pith.science/pith/4RYNOSIMJSOESK7LROPP5KV24E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4RYNOSIMJSOESK7LROPP5KV24E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4RYNOSIMJSOESK7LROPP5KV24E","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":"4db6e0fb22b8370d8a9bf9f19b4bfe24b62fbaf760d348b50398636cde70035c","cross_cats_sorted":["cs.DB"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-07-21T21:20:25Z","title_canon_sha256":"bc53a64c3a1903578504c21b88c2d1fd348e9162ddf06cd9eee20e3eb75061dd"},"schema_version":"1.0","source":{"id":"2507.16073","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.16073","created_at":"2026-07-05T11:41:02Z"},{"alias_kind":"arxiv_version","alias_value":"2507.16073v1","created_at":"2026-07-05T11:41:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.16073","created_at":"2026-07-05T11:41:02Z"},{"alias_kind":"pith_short_12","alias_value":"4RYNOSIMJSOE","created_at":"2026-07-05T11:41:02Z"},{"alias_kind":"pith_short_16","alias_value":"4RYNOSIMJSOESK7L","created_at":"2026-07-05T11:41:02Z"},{"alias_kind":"pith_short_8","alias_value":"4RYNOSIM","created_at":"2026-07-05T11:41:02Z"}],"graph_snapshots":[{"event_id":"sha256:fb0a15912d2ba4a7bbe23aeb407c508078b21abc69d7afac8447ff65ae91cf27","target":"graph","created_at":"2026-07-05T11:41:02Z","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/2507.16073/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Preparing datasets -- a critical phase known as data wrangling -- constitutes the dominant phase of data science development, consuming upwards of 80% of the total project time. This phase encompasses a myriad of tasks: parsing data, restructuring it for analysis, repairing inaccuracies, merging sources, eliminating duplicates, and ensuring overall data integrity. Traditional approaches, typically through manual coding in languages such as Python or using spreadsheets, are not only laborious but also error-prone. These issues range from missing entries and formatting inconsistencies to data ty","authors_text":"Andrew McNutt, Annabelle Warner, El Kindi Rezig, Paul Rosen","cross_cats":["cs.DB"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-07-21T21:20:25Z","title":"Buckaroo: A Direct Manipulation Visual Data Wrangler"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.16073","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":"sha256:5d5d77f5f29ea2b90b86b9ad3405080e833d1155ca5ecf5aadb52c8629b52182","target":"record","created_at":"2026-07-05T11:41:02Z","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":"4db6e0fb22b8370d8a9bf9f19b4bfe24b62fbaf760d348b50398636cde70035c","cross_cats_sorted":["cs.DB"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-07-21T21:20:25Z","title_canon_sha256":"bc53a64c3a1903578504c21b88c2d1fd348e9162ddf06cd9eee20e3eb75061dd"},"schema_version":"1.0","source":{"id":"2507.16073","kind":"arxiv","version":1}},"canonical_sha256":"e470d7490c4c9c492beb8b9efeaabae11a764a26462dad9ae31cc042fee22554","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e470d7490c4c9c492beb8b9efeaabae11a764a26462dad9ae31cc042fee22554","first_computed_at":"2026-07-05T11:41:02.329078Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:41:02.329078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"etWItvnk0n2QWrLcPAgJo7cMoSgxbZ9ud0HzPmoqcO2p3ZpEX29EzjWfDzSR0UihfczbKKXtZXkNoW5UHvFAAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:41:02.329556Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.16073","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d5d77f5f29ea2b90b86b9ad3405080e833d1155ca5ecf5aadb52c8629b52182","sha256:fb0a15912d2ba4a7bbe23aeb407c508078b21abc69d7afac8447ff65ae91cf27"],"state_sha256":"cee371c4754b546a627cb4118d52c112f3ca992bb2d0e0e88b147b8e314e2090"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+hI1UGfyJdk8vXHkGcCxn0P41qqLkUhmGJmmgrq4vZK618Z1ZclC08npdYW8kdVQW0Ntd+tNab7TQZDXjngWCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T06:45:48.053804Z","bundle_sha256":"e84f1280ab711d1e4f7eb187ddefca35b8410cd01db93e01b79de518931ea966"}}