{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:IU5R5Q7S6JN2EVJJEDUMHZV7CF","short_pith_number":"pith:IU5R5Q7S","canonical_record":{"source":{"id":"1702.00820","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-02-02T20:25:41Z","cross_cats_sorted":[],"title_canon_sha256":"e7df463ab764b6d53f98e3a6ff26764c8e369ec53843cc1503fe2c182974856c","abstract_canon_sha256":"c1806fa45040090982ce2da30af2a4cdd6114b1d477378b908f45ca9a6b50ad1"},"schema_version":"1.0"},"canonical_sha256":"453b1ec3f2f25ba2552920e8c3e6bf1152a10c2c4c837c0584844cac1e0d92f6","source":{"kind":"arxiv","id":"1702.00820","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.00820","created_at":"2026-05-18T00:51:29Z"},{"alias_kind":"arxiv_version","alias_value":"1702.00820v1","created_at":"2026-05-18T00:51:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.00820","created_at":"2026-05-18T00:51:29Z"},{"alias_kind":"pith_short_12","alias_value":"IU5R5Q7S6JN2","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"IU5R5Q7S6JN2EVJJ","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"IU5R5Q7S","created_at":"2026-05-18T12:31:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:IU5R5Q7S6JN2EVJJEDUMHZV7CF","target":"record","payload":{"canonical_record":{"source":{"id":"1702.00820","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-02-02T20:25:41Z","cross_cats_sorted":[],"title_canon_sha256":"e7df463ab764b6d53f98e3a6ff26764c8e369ec53843cc1503fe2c182974856c","abstract_canon_sha256":"c1806fa45040090982ce2da30af2a4cdd6114b1d477378b908f45ca9a6b50ad1"},"schema_version":"1.0"},"canonical_sha256":"453b1ec3f2f25ba2552920e8c3e6bf1152a10c2c4c837c0584844cac1e0d92f6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:51:29.693413Z","signature_b64":"5ClTUlS1Y/H92tkfW6e0OGz0mGl2QFNI8ZVbEv/YjVN8Wq6+a6rM5p5deuOx9KqQRwyQx9SmAQh+y9ibMfZWDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"453b1ec3f2f25ba2552920e8c3e6bf1152a10c2c4c837c0584844cac1e0d92f6","last_reissued_at":"2026-05-18T00:51:29.692758Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:51:29.692758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1702.00820","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":"2026-05-18T00:51:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m1IKXoMl3EG94ydwUlqOvPykAazCDWosi9V5iL2tQekUpUqSOC29LqO1JVUvXOnT6XHFCSV6JEekQYuW8R93CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T17:46:30.730246Z"},"content_sha256":"7532e5253fc0151d86d1df7ec00e7308650e9ef94d3b1b18195aa96ba7d8054a","schema_version":"1.0","event_id":"sha256:7532e5253fc0151d86d1df7ec00e7308650e9ef94d3b1b18195aa96ba7d8054a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:IU5R5Q7S6JN2EVJJEDUMHZV7CF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HoloClean: Holistic Data Repairs with Probabilistic Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Christopher R\\'e, Ihab F. Ilyas, Theodoros Rekatsinas, Xu Chu","submitted_at":"2017-02-02T20:25:41Z","abstract_excerpt":"We introduce HoloClean, a framework for holistic data repairing driven by probabilistic inference. HoloClean unifies existing qualitative data repairing approaches, which rely on integrity constraints or external data sources, with quantitative data repairing methods, which leverage statistical properties of the input data. Given an inconsistent dataset as input, HoloClean automatically generates a probabilistic program that performs data repairing. Inspired by recent theoretical advances in probabilistic inference, we introduce a series of optimizations which ensure that inference over HoloCl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.00820","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":""},"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":"2026-05-18T00:51:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mYVa+dkn5dx6w9whcEGZo29MFlujqMrfg/LktyPL878RBTueXDNvXoAYi9214EuwKzFFFQw7T2KxHk1wXEqaCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T17:46:30.730933Z"},"content_sha256":"2cba2398caccc82dc16545228e9fea9a72db60150e50e351a197dc74c2beb364","schema_version":"1.0","event_id":"sha256:2cba2398caccc82dc16545228e9fea9a72db60150e50e351a197dc74c2beb364"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IU5R5Q7S6JN2EVJJEDUMHZV7CF/bundle.json","state_url":"https://pith.science/pith/IU5R5Q7S6JN2EVJJEDUMHZV7CF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IU5R5Q7S6JN2EVJJEDUMHZV7CF/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":"2026-05-29T17:46:30Z","links":{"resolver":"https://pith.science/pith/IU5R5Q7S6JN2EVJJEDUMHZV7CF","bundle":"https://pith.science/pith/IU5R5Q7S6JN2EVJJEDUMHZV7CF/bundle.json","state":"https://pith.science/pith/IU5R5Q7S6JN2EVJJEDUMHZV7CF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IU5R5Q7S6JN2EVJJEDUMHZV7CF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:IU5R5Q7S6JN2EVJJEDUMHZV7CF","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":"c1806fa45040090982ce2da30af2a4cdd6114b1d477378b908f45ca9a6b50ad1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-02-02T20:25:41Z","title_canon_sha256":"e7df463ab764b6d53f98e3a6ff26764c8e369ec53843cc1503fe2c182974856c"},"schema_version":"1.0","source":{"id":"1702.00820","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.00820","created_at":"2026-05-18T00:51:29Z"},{"alias_kind":"arxiv_version","alias_value":"1702.00820v1","created_at":"2026-05-18T00:51:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.00820","created_at":"2026-05-18T00:51:29Z"},{"alias_kind":"pith_short_12","alias_value":"IU5R5Q7S6JN2","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"IU5R5Q7S6JN2EVJJ","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"IU5R5Q7S","created_at":"2026-05-18T12:31:21Z"}],"graph_snapshots":[{"event_id":"sha256:2cba2398caccc82dc16545228e9fea9a72db60150e50e351a197dc74c2beb364","target":"graph","created_at":"2026-05-18T00:51:29Z","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"},"paper":{"abstract_excerpt":"We introduce HoloClean, a framework for holistic data repairing driven by probabilistic inference. HoloClean unifies existing qualitative data repairing approaches, which rely on integrity constraints or external data sources, with quantitative data repairing methods, which leverage statistical properties of the input data. Given an inconsistent dataset as input, HoloClean automatically generates a probabilistic program that performs data repairing. Inspired by recent theoretical advances in probabilistic inference, we introduce a series of optimizations which ensure that inference over HoloCl","authors_text":"Christopher R\\'e, Ihab F. Ilyas, Theodoros Rekatsinas, Xu Chu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-02-02T20:25:41Z","title":"HoloClean: Holistic Data Repairs with Probabilistic Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.00820","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":"sha256:7532e5253fc0151d86d1df7ec00e7308650e9ef94d3b1b18195aa96ba7d8054a","target":"record","created_at":"2026-05-18T00:51:29Z","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":"c1806fa45040090982ce2da30af2a4cdd6114b1d477378b908f45ca9a6b50ad1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-02-02T20:25:41Z","title_canon_sha256":"e7df463ab764b6d53f98e3a6ff26764c8e369ec53843cc1503fe2c182974856c"},"schema_version":"1.0","source":{"id":"1702.00820","kind":"arxiv","version":1}},"canonical_sha256":"453b1ec3f2f25ba2552920e8c3e6bf1152a10c2c4c837c0584844cac1e0d92f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"453b1ec3f2f25ba2552920e8c3e6bf1152a10c2c4c837c0584844cac1e0d92f6","first_computed_at":"2026-05-18T00:51:29.692758Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:51:29.692758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5ClTUlS1Y/H92tkfW6e0OGz0mGl2QFNI8ZVbEv/YjVN8Wq6+a6rM5p5deuOx9KqQRwyQx9SmAQh+y9ibMfZWDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:51:29.693413Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.00820","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7532e5253fc0151d86d1df7ec00e7308650e9ef94d3b1b18195aa96ba7d8054a","sha256:2cba2398caccc82dc16545228e9fea9a72db60150e50e351a197dc74c2beb364"],"state_sha256":"e28b32a0aa8077cfca787094fa706ef6ca88be929cb14c5fc008eddd80a426e5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dtJiLNKC1Ht+PSV/YgSJSs34TNtXg4NR16lnLd1h5s7k9XyVDbPWduTVQXI9Dtcr3M8uYCpzHmP9bjsNG4NmCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T17:46:30.734378Z","bundle_sha256":"750a39ec4c8ec7f53b28234d690dfa70aab2324a1afe068d509664ba701735a9"}}