{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:F3YRYDSRHSO5TG7TRUXI4O2XGI","short_pith_number":"pith:F3YRYDSR","canonical_record":{"source":{"id":"2410.15547","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2024-10-21T00:29:40Z","cross_cats_sorted":[],"title_canon_sha256":"f20c7ca61f30a9d4574e13244d61039f40c78d8ec006ba390a19b59cbc8b9639","abstract_canon_sha256":"3f63d731f67d6f0994f7e1b6870057f6ed61458d8eb166fa60a27d2113990a64"},"schema_version":"1.0"},"canonical_sha256":"2ef11c0e513c9dd99bf38d2e8e3b57323f7389a33cd2261fb491fd67c30f70a0","source":{"kind":"arxiv","id":"2410.15547","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.15547","created_at":"2026-07-05T09:23:21Z"},{"alias_kind":"arxiv_version","alias_value":"2410.15547v1","created_at":"2026-07-05T09:23:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15547","created_at":"2026-07-05T09:23:21Z"},{"alias_kind":"pith_short_12","alias_value":"F3YRYDSRHSO5","created_at":"2026-07-05T09:23:21Z"},{"alias_kind":"pith_short_16","alias_value":"F3YRYDSRHSO5TG7T","created_at":"2026-07-05T09:23:21Z"},{"alias_kind":"pith_short_8","alias_value":"F3YRYDSR","created_at":"2026-07-05T09:23:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:F3YRYDSRHSO5TG7TRUXI4O2XGI","target":"record","payload":{"canonical_record":{"source":{"id":"2410.15547","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2024-10-21T00:29:40Z","cross_cats_sorted":[],"title_canon_sha256":"f20c7ca61f30a9d4574e13244d61039f40c78d8ec006ba390a19b59cbc8b9639","abstract_canon_sha256":"3f63d731f67d6f0994f7e1b6870057f6ed61458d8eb166fa60a27d2113990a64"},"schema_version":"1.0"},"canonical_sha256":"2ef11c0e513c9dd99bf38d2e8e3b57323f7389a33cd2261fb491fd67c30f70a0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:21.118933Z","signature_b64":"ekSJ3tBQk0B5lur8D32eI47uJaHRy9MHk++mNsWlZw14N7UGIqNaeyYHS/YKxGEc3gBKMxPH4GJRE/GiL+YvCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ef11c0e513c9dd99bf38d2e8e3b57323f7389a33cd2261fb491fd67c30f70a0","last_reissued_at":"2026-07-05T09:23:21.118479Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:21.118479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.15547","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":"2026-07-05T09:23:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2xjlWMRGzEN7cn3IxDBFJUWdASYB6SeIwzOsQjmIBlHe1Kf+ua1+1tqOxxajsHwB1xN+XNYPp3O4EUnbUYV/AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T13:40:34.609275Z"},"content_sha256":"877e8941c65b0210bac00f5c8b4b0ed33426b2edbc17bad91d34d6d2f54b7051","schema_version":"1.0","event_id":"sha256:877e8941c65b0210bac00f5c8b4b0ed33426b2edbc17bad91d34d6d2f54b7051"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:F3YRYDSRHSO5TG7TRUXI4O2XGI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Cleaning Using Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Eugene Wu, Shuo Zhang, Zezhou Huang","submitted_at":"2024-10-21T00:29:40Z","abstract_excerpt":"Data cleaning is a crucial yet challenging task in data analysis, often requiring significant manual effort. To automate data cleaning, previous systems have relied on statistical rules derived from erroneous data, resulting in low accuracy and recall. This work introduces Cocoon, a novel data cleaning system that leverages large language models for rules based on semantic understanding and combines them with statistical error detection. However, data cleaning is still too complex a task for current LLMs to handle in one shot. To address this, we introduce Cocoon, which decomposes complex clea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15547","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/2410.15547/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":"2026-07-05T09:23:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6e49YSR9+C975QaZwmJHuD3RWXX5AJ2mhACawpuINrl/xLA/pDZc8MTGYqt7RfS03hxl64aMHoiAxa+g7Kz0BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T13:40:34.609651Z"},"content_sha256":"aa1085d5dc2b69839dbc6970223460923b04a7fc2a8a737c755e5931204eb069","schema_version":"1.0","event_id":"sha256:aa1085d5dc2b69839dbc6970223460923b04a7fc2a8a737c755e5931204eb069"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F3YRYDSRHSO5TG7TRUXI4O2XGI/bundle.json","state_url":"https://pith.science/pith/F3YRYDSRHSO5TG7TRUXI4O2XGI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F3YRYDSRHSO5TG7TRUXI4O2XGI/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":"2026-08-20T13:40:34Z","links":{"resolver":"https://pith.science/pith/F3YRYDSRHSO5TG7TRUXI4O2XGI","bundle":"https://pith.science/pith/F3YRYDSRHSO5TG7TRUXI4O2XGI/bundle.json","state":"https://pith.science/pith/F3YRYDSRHSO5TG7TRUXI4O2XGI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F3YRYDSRHSO5TG7TRUXI4O2XGI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F3YRYDSRHSO5TG7TRUXI4O2XGI","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":"3f63d731f67d6f0994f7e1b6870057f6ed61458d8eb166fa60a27d2113990a64","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2024-10-21T00:29:40Z","title_canon_sha256":"f20c7ca61f30a9d4574e13244d61039f40c78d8ec006ba390a19b59cbc8b9639"},"schema_version":"1.0","source":{"id":"2410.15547","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.15547","created_at":"2026-07-05T09:23:21Z"},{"alias_kind":"arxiv_version","alias_value":"2410.15547v1","created_at":"2026-07-05T09:23:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15547","created_at":"2026-07-05T09:23:21Z"},{"alias_kind":"pith_short_12","alias_value":"F3YRYDSRHSO5","created_at":"2026-07-05T09:23:21Z"},{"alias_kind":"pith_short_16","alias_value":"F3YRYDSRHSO5TG7T","created_at":"2026-07-05T09:23:21Z"},{"alias_kind":"pith_short_8","alias_value":"F3YRYDSR","created_at":"2026-07-05T09:23:21Z"}],"graph_snapshots":[{"event_id":"sha256:aa1085d5dc2b69839dbc6970223460923b04a7fc2a8a737c755e5931204eb069","target":"graph","created_at":"2026-07-05T09:23:21Z","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/2410.15547/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data cleaning is a crucial yet challenging task in data analysis, often requiring significant manual effort. To automate data cleaning, previous systems have relied on statistical rules derived from erroneous data, resulting in low accuracy and recall. This work introduces Cocoon, a novel data cleaning system that leverages large language models for rules based on semantic understanding and combines them with statistical error detection. However, data cleaning is still too complex a task for current LLMs to handle in one shot. To address this, we introduce Cocoon, which decomposes complex clea","authors_text":"Eugene Wu, Shuo Zhang, Zezhou Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2024-10-21T00:29:40Z","title":"Data Cleaning Using Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15547","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":"sha256:877e8941c65b0210bac00f5c8b4b0ed33426b2edbc17bad91d34d6d2f54b7051","target":"record","created_at":"2026-07-05T09:23:21Z","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":"3f63d731f67d6f0994f7e1b6870057f6ed61458d8eb166fa60a27d2113990a64","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2024-10-21T00:29:40Z","title_canon_sha256":"f20c7ca61f30a9d4574e13244d61039f40c78d8ec006ba390a19b59cbc8b9639"},"schema_version":"1.0","source":{"id":"2410.15547","kind":"arxiv","version":1}},"canonical_sha256":"2ef11c0e513c9dd99bf38d2e8e3b57323f7389a33cd2261fb491fd67c30f70a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ef11c0e513c9dd99bf38d2e8e3b57323f7389a33cd2261fb491fd67c30f70a0","first_computed_at":"2026-07-05T09:23:21.118479Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:23:21.118479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ekSJ3tBQk0B5lur8D32eI47uJaHRy9MHk++mNsWlZw14N7UGIqNaeyYHS/YKxGEc3gBKMxPH4GJRE/GiL+YvCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:23:21.118933Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.15547","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:877e8941c65b0210bac00f5c8b4b0ed33426b2edbc17bad91d34d6d2f54b7051","sha256:aa1085d5dc2b69839dbc6970223460923b04a7fc2a8a737c755e5931204eb069"],"state_sha256":"1f02fa6901c651bb718d7af2a25df87917a923483addbb52f2bdd52ef4640dc0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JbE/rR1xKbJyps+k4O+g/mcfy1/Ge97gSPeG+W+bYN/6qBxZNFit0piSVYRyGFKs3zzRe1IzDL+fDpALn+hgBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T13:40:34.613434Z","bundle_sha256":"12acc1b5d316faf80de027da0473adb66153a674b3d5609ff980949d3f741dca"}}