{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QTFBFNEZE5OPZIDTZ6AQPRXRPU","short_pith_number":"pith:QTFBFNEZ","canonical_record":{"source":{"id":"2504.10762","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-04-14T23:26:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"51661b12c31a230c1d8b2a4fe08953ccf9be3f9486f2ac77dbe27eaa42f27dec","abstract_canon_sha256":"c70da4aca133e74d757129c2fc992d279c0119fda888a89732aec1ab7fbae600"},"schema_version":"1.0"},"canonical_sha256":"84ca12b499275cfca073cf8107c6f17d05619540df316e756251be81d54dfbd4","source":{"kind":"arxiv","id":"2504.10762","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.10762","created_at":"2026-07-05T10:49:23Z"},{"alias_kind":"arxiv_version","alias_value":"2504.10762v1","created_at":"2026-07-05T10:49:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.10762","created_at":"2026-07-05T10:49:23Z"},{"alias_kind":"pith_short_12","alias_value":"QTFBFNEZE5OP","created_at":"2026-07-05T10:49:23Z"},{"alias_kind":"pith_short_16","alias_value":"QTFBFNEZE5OPZIDT","created_at":"2026-07-05T10:49:23Z"},{"alias_kind":"pith_short_8","alias_value":"QTFBFNEZ","created_at":"2026-07-05T10:49:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QTFBFNEZE5OPZIDTZ6AQPRXRPU","target":"record","payload":{"canonical_record":{"source":{"id":"2504.10762","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-04-14T23:26:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"51661b12c31a230c1d8b2a4fe08953ccf9be3f9486f2ac77dbe27eaa42f27dec","abstract_canon_sha256":"c70da4aca133e74d757129c2fc992d279c0119fda888a89732aec1ab7fbae600"},"schema_version":"1.0"},"canonical_sha256":"84ca12b499275cfca073cf8107c6f17d05619540df316e756251be81d54dfbd4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:23.880771Z","signature_b64":"vSdOya7V3p4TmMTkOkVc0+84OvTiuzmTqCacTZV69BN26KbZAW/1CeG25bh7GUtL862+ZBG4gUGWx6vO7gtqAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84ca12b499275cfca073cf8107c6f17d05619540df316e756251be81d54dfbd4","last_reissued_at":"2026-07-05T10:49:23.880204Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:23.880204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.10762","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":"2026-07-05T10:49:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ttCa98tnuXQ10L6kfg7VTl220NSKPJ1rxL8iShv613QihP9ze56tYamJ2H3s4CBzlcvKVmXP2Wkc6MQV+XSUCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:40:03.496821Z"},"content_sha256":"2674aff2c55303ec8f84fdbfccee0cd22e3243f2b9bc5d0ac86797639b72730e","schema_version":"1.0","event_id":"sha256:2674aff2c55303ec8f84fdbfccee0cd22e3243f2b9bc5d0ac86797639b72730e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QTFBFNEZE5OPZIDTZ6AQPRXRPU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Auto-Test: Learning Semantic-Domain Constraints for Unsupervised Error Detection in Tables","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"Dongmei Zhang, Haidong Zhang, Qixu Chen, Raymond Chi-Wing Wong, Song Ge, Surajit Chaudhuri, Weiwei Cui, Yeye He","submitted_at":"2025-04-14T23:26:55Z","abstract_excerpt":"Data cleaning is a long-standing challenge in data management. While powerful logic and statistical algorithms have been developed to detect and repair data errors in tables, existing algorithms predominantly rely on domain-experts to first manually specify data-quality constraints specific to a given table, before data cleaning algorithms can be applied.\n  In this work, we propose a new class of data-quality constraints that we call Semantic-Domain Constraints, which can be reliably inferred and automatically applied to any tables, without requiring domain-experts to manually specify on a per"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.10762","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/2504.10762/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":"2026-07-05T10:49:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yw8ebGeW03QJhC7SmaJZq0AbM89qEKeoIDQ8S8jUyv5ez794kYjj78MMDw190U3sRAFNEArJcglKyTogjcMEAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:40:03.497192Z"},"content_sha256":"7de9a685ce17b6e8ac5b965efa17f8dd30127490f903665ae848602d178db55c","schema_version":"1.0","event_id":"sha256:7de9a685ce17b6e8ac5b965efa17f8dd30127490f903665ae848602d178db55c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QTFBFNEZE5OPZIDTZ6AQPRXRPU/bundle.json","state_url":"https://pith.science/pith/QTFBFNEZE5OPZIDTZ6AQPRXRPU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QTFBFNEZE5OPZIDTZ6AQPRXRPU/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":"2026-07-07T11:40:03Z","links":{"resolver":"https://pith.science/pith/QTFBFNEZE5OPZIDTZ6AQPRXRPU","bundle":"https://pith.science/pith/QTFBFNEZE5OPZIDTZ6AQPRXRPU/bundle.json","state":"https://pith.science/pith/QTFBFNEZE5OPZIDTZ6AQPRXRPU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QTFBFNEZE5OPZIDTZ6AQPRXRPU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QTFBFNEZE5OPZIDTZ6AQPRXRPU","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":"c70da4aca133e74d757129c2fc992d279c0119fda888a89732aec1ab7fbae600","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-04-14T23:26:55Z","title_canon_sha256":"51661b12c31a230c1d8b2a4fe08953ccf9be3f9486f2ac77dbe27eaa42f27dec"},"schema_version":"1.0","source":{"id":"2504.10762","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.10762","created_at":"2026-07-05T10:49:23Z"},{"alias_kind":"arxiv_version","alias_value":"2504.10762v1","created_at":"2026-07-05T10:49:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.10762","created_at":"2026-07-05T10:49:23Z"},{"alias_kind":"pith_short_12","alias_value":"QTFBFNEZE5OP","created_at":"2026-07-05T10:49:23Z"},{"alias_kind":"pith_short_16","alias_value":"QTFBFNEZE5OPZIDT","created_at":"2026-07-05T10:49:23Z"},{"alias_kind":"pith_short_8","alias_value":"QTFBFNEZ","created_at":"2026-07-05T10:49:23Z"}],"graph_snapshots":[{"event_id":"sha256:7de9a685ce17b6e8ac5b965efa17f8dd30127490f903665ae848602d178db55c","target":"graph","created_at":"2026-07-05T10:49:23Z","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/2504.10762/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data cleaning is a long-standing challenge in data management. While powerful logic and statistical algorithms have been developed to detect and repair data errors in tables, existing algorithms predominantly rely on domain-experts to first manually specify data-quality constraints specific to a given table, before data cleaning algorithms can be applied.\n  In this work, we propose a new class of data-quality constraints that we call Semantic-Domain Constraints, which can be reliably inferred and automatically applied to any tables, without requiring domain-experts to manually specify on a per","authors_text":"Dongmei Zhang, Haidong Zhang, Qixu Chen, Raymond Chi-Wing Wong, Song Ge, Surajit Chaudhuri, Weiwei Cui, Yeye He","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-04-14T23:26:55Z","title":"Auto-Test: Learning Semantic-Domain Constraints for Unsupervised Error Detection in Tables"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.10762","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":"sha256:2674aff2c55303ec8f84fdbfccee0cd22e3243f2b9bc5d0ac86797639b72730e","target":"record","created_at":"2026-07-05T10:49:23Z","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":"c70da4aca133e74d757129c2fc992d279c0119fda888a89732aec1ab7fbae600","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-04-14T23:26:55Z","title_canon_sha256":"51661b12c31a230c1d8b2a4fe08953ccf9be3f9486f2ac77dbe27eaa42f27dec"},"schema_version":"1.0","source":{"id":"2504.10762","kind":"arxiv","version":1}},"canonical_sha256":"84ca12b499275cfca073cf8107c6f17d05619540df316e756251be81d54dfbd4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"84ca12b499275cfca073cf8107c6f17d05619540df316e756251be81d54dfbd4","first_computed_at":"2026-07-05T10:49:23.880204Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:49:23.880204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vSdOya7V3p4TmMTkOkVc0+84OvTiuzmTqCacTZV69BN26KbZAW/1CeG25bh7GUtL862+ZBG4gUGWx6vO7gtqAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:49:23.880771Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.10762","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2674aff2c55303ec8f84fdbfccee0cd22e3243f2b9bc5d0ac86797639b72730e","sha256:7de9a685ce17b6e8ac5b965efa17f8dd30127490f903665ae848602d178db55c"],"state_sha256":"09cf8ba35d5d0f0920e938b6c07f24020526909c0e160f2100092e0b6222fdc2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ka4hIhu+E/dCIeuEg1nPvGRbKh1ZEf9vczLpE1/crbA/FrZZ7GShwDATP89wUd9F06+wOG0VoMOzO+pHxVnsDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T11:40:03.499134Z","bundle_sha256":"186ee40734e731cddb0efcdf1e91f4e6c4daef7e010b653a2f0c45619d896a4d"}}