{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GKDRCX2KU4UXO33O5N65J4RHKQ","short_pith_number":"pith:GKDRCX2K","canonical_record":{"source":{"id":"2503.06664","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-09T15:29:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"67e2e4a522fea8454a8a4b521c5b229ccb1353e9739958dcf82946b4e5f25e7a","abstract_canon_sha256":"16792f2ddd1f3f55a0015c4dff707f32782d1f5a03bfc0e7872fb75c8e738936"},"schema_version":"1.0"},"canonical_sha256":"3287115f4aa729776f6eeb7dd4f227543375d1b49ae0536a05c565362bca8aa7","source":{"kind":"arxiv","id":"2503.06664","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.06664","created_at":"2026-07-05T10:27:39Z"},{"alias_kind":"arxiv_version","alias_value":"2503.06664v1","created_at":"2026-07-05T10:27:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06664","created_at":"2026-07-05T10:27:39Z"},{"alias_kind":"pith_short_12","alias_value":"GKDRCX2KU4UX","created_at":"2026-07-05T10:27:39Z"},{"alias_kind":"pith_short_16","alias_value":"GKDRCX2KU4UXO33O","created_at":"2026-07-05T10:27:39Z"},{"alias_kind":"pith_short_8","alias_value":"GKDRCX2K","created_at":"2026-07-05T10:27:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GKDRCX2KU4UXO33O5N65J4RHKQ","target":"record","payload":{"canonical_record":{"source":{"id":"2503.06664","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-09T15:29:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"67e2e4a522fea8454a8a4b521c5b229ccb1353e9739958dcf82946b4e5f25e7a","abstract_canon_sha256":"16792f2ddd1f3f55a0015c4dff707f32782d1f5a03bfc0e7872fb75c8e738936"},"schema_version":"1.0"},"canonical_sha256":"3287115f4aa729776f6eeb7dd4f227543375d1b49ae0536a05c565362bca8aa7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:39.705286Z","signature_b64":"wocro7y7adpE5XKDWbbrP96Rv6FoyHrSkAEr69p1+jVk0CFBlhup8nW3/X38hBI2inR99XStVG+h3szNWy7wCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3287115f4aa729776f6eeb7dd4f227543375d1b49ae0536a05c565362bca8aa7","last_reissued_at":"2026-07-05T10:27:39.704755Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:39.704755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.06664","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":"2026-07-05T10:27:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DLktHXNFYjq2qAILJYwru34drwJyd3151bjUGtQ6hmKYj5Ka/QVpqvAu83EpH/rWPrU/0X9s+JISCju3MECPDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:57:32.905169Z"},"content_sha256":"c02fa55f8fe73ceeb6bc1ae044b137d8a51ef831765ec7effe2744f1542babce","schema_version":"1.0","event_id":"sha256:c02fa55f8fe73ceeb6bc1ae044b137d8a51ef831765ec7effe2744f1542babce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GKDRCX2KU4UXO33O5N65J4RHKQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploring LLM Agents for Cleaning Tabular Machine Learning Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Artur Dox, Christian Holz, Tommaso Bendinelli","submitted_at":"2025-03-09T15:29:46Z","abstract_excerpt":"High-quality, error-free datasets are a key ingredient in building reliable, accurate, and unbiased machine learning (ML) models. However, real world datasets often suffer from errors due to sensor malfunctions, data entry mistakes, or improper data integration across multiple sources that can severely degrade model performance. Detecting and correcting these issues typically require tailor-made solutions and demand extensive domain expertise. Consequently, automation is challenging, rendering the process labor-intensive and tedious. In this study, we investigate whether Large Language Models "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.06664","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/2503.06664/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":"2026-07-05T10:27:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rvcKEOawS6NUTUk1l1GjFjVRwz73wKx5dCg88n9RljvTBwBAFpbAa7IErzv94cJgEBI47YylF7R8BaOWxme4Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:57:32.906151Z"},"content_sha256":"e563ac2557693891f8140916c6219eba13fbcc1d869c50da39eb05ebecbcb7d5","schema_version":"1.0","event_id":"sha256:e563ac2557693891f8140916c6219eba13fbcc1d869c50da39eb05ebecbcb7d5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GKDRCX2KU4UXO33O5N65J4RHKQ/bundle.json","state_url":"https://pith.science/pith/GKDRCX2KU4UXO33O5N65J4RHKQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GKDRCX2KU4UXO33O5N65J4RHKQ/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":"2026-08-09T21:57:32Z","links":{"resolver":"https://pith.science/pith/GKDRCX2KU4UXO33O5N65J4RHKQ","bundle":"https://pith.science/pith/GKDRCX2KU4UXO33O5N65J4RHKQ/bundle.json","state":"https://pith.science/pith/GKDRCX2KU4UXO33O5N65J4RHKQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GKDRCX2KU4UXO33O5N65J4RHKQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GKDRCX2KU4UXO33O5N65J4RHKQ","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":"16792f2ddd1f3f55a0015c4dff707f32782d1f5a03bfc0e7872fb75c8e738936","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-09T15:29:46Z","title_canon_sha256":"67e2e4a522fea8454a8a4b521c5b229ccb1353e9739958dcf82946b4e5f25e7a"},"schema_version":"1.0","source":{"id":"2503.06664","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.06664","created_at":"2026-07-05T10:27:39Z"},{"alias_kind":"arxiv_version","alias_value":"2503.06664v1","created_at":"2026-07-05T10:27:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06664","created_at":"2026-07-05T10:27:39Z"},{"alias_kind":"pith_short_12","alias_value":"GKDRCX2KU4UX","created_at":"2026-07-05T10:27:39Z"},{"alias_kind":"pith_short_16","alias_value":"GKDRCX2KU4UXO33O","created_at":"2026-07-05T10:27:39Z"},{"alias_kind":"pith_short_8","alias_value":"GKDRCX2K","created_at":"2026-07-05T10:27:39Z"}],"graph_snapshots":[{"event_id":"sha256:e563ac2557693891f8140916c6219eba13fbcc1d869c50da39eb05ebecbcb7d5","target":"graph","created_at":"2026-07-05T10:27:39Z","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/2503.06664/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"High-quality, error-free datasets are a key ingredient in building reliable, accurate, and unbiased machine learning (ML) models. However, real world datasets often suffer from errors due to sensor malfunctions, data entry mistakes, or improper data integration across multiple sources that can severely degrade model performance. Detecting and correcting these issues typically require tailor-made solutions and demand extensive domain expertise. Consequently, automation is challenging, rendering the process labor-intensive and tedious. In this study, we investigate whether Large Language Models ","authors_text":"Artur Dox, Christian Holz, Tommaso Bendinelli","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-09T15:29:46Z","title":"Exploring LLM Agents for Cleaning Tabular Machine Learning Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.06664","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:c02fa55f8fe73ceeb6bc1ae044b137d8a51ef831765ec7effe2744f1542babce","target":"record","created_at":"2026-07-05T10:27:39Z","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":"16792f2ddd1f3f55a0015c4dff707f32782d1f5a03bfc0e7872fb75c8e738936","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-09T15:29:46Z","title_canon_sha256":"67e2e4a522fea8454a8a4b521c5b229ccb1353e9739958dcf82946b4e5f25e7a"},"schema_version":"1.0","source":{"id":"2503.06664","kind":"arxiv","version":1}},"canonical_sha256":"3287115f4aa729776f6eeb7dd4f227543375d1b49ae0536a05c565362bca8aa7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3287115f4aa729776f6eeb7dd4f227543375d1b49ae0536a05c565362bca8aa7","first_computed_at":"2026-07-05T10:27:39.704755Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:27:39.704755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wocro7y7adpE5XKDWbbrP96Rv6FoyHrSkAEr69p1+jVk0CFBlhup8nW3/X38hBI2inR99XStVG+h3szNWy7wCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:27:39.705286Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.06664","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c02fa55f8fe73ceeb6bc1ae044b137d8a51ef831765ec7effe2744f1542babce","sha256:e563ac2557693891f8140916c6219eba13fbcc1d869c50da39eb05ebecbcb7d5"],"state_sha256":"e9e02730c3b18e41421c27eac4283d356c02847f622b3d6e3842c5cb7773ca01"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EtFbZjpqfr4TVLzk1p5lsmY2QlOItmg8+4EmD4t0vigfG0j1v2OceFFYQ8vaJp5CuesiuFrMWoqZchJlXEwGCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T21:57:32.913113Z","bundle_sha256":"c81f93dcd47c626edbf41bcbd2fba47be316244f4149c0c1ed7cb5cd86208547"}}