{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:S4IJD2TYPKKSH7AV53327DDS3Z","short_pith_number":"pith:S4IJD2TY","canonical_record":{"source":{"id":"2607.25356","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2026-07-28T07:03:50Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"bdfa3d43780894aab22e89d1e8fbdb546d8cafd29a79698dde88dab9830322af","abstract_canon_sha256":"48b3de31e170afa00046ef86d5bd179a941eb778543b0b8df8a2a103d77bace4"},"schema_version":"1.0"},"canonical_sha256":"971091ea787a9523fc15eef7af8c72de692fba594631ed96094d9f9425b301ae","source":{"kind":"arxiv","id":"2607.25356","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.25356","created_at":"2026-07-29T01:25:11Z"},{"alias_kind":"arxiv_version","alias_value":"2607.25356v1","created_at":"2026-07-29T01:25:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.25356","created_at":"2026-07-29T01:25:11Z"},{"alias_kind":"pith_short_12","alias_value":"S4IJD2TYPKKS","created_at":"2026-07-29T01:25:11Z"},{"alias_kind":"pith_short_16","alias_value":"S4IJD2TYPKKSH7AV","created_at":"2026-07-29T01:25:11Z"},{"alias_kind":"pith_short_8","alias_value":"S4IJD2TY","created_at":"2026-07-29T01:25:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:S4IJD2TYPKKSH7AV53327DDS3Z","target":"record","payload":{"canonical_record":{"source":{"id":"2607.25356","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2026-07-28T07:03:50Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"bdfa3d43780894aab22e89d1e8fbdb546d8cafd29a79698dde88dab9830322af","abstract_canon_sha256":"48b3de31e170afa00046ef86d5bd179a941eb778543b0b8df8a2a103d77bace4"},"schema_version":"1.0"},"canonical_sha256":"971091ea787a9523fc15eef7af8c72de692fba594631ed96094d9f9425b301ae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T01:25:11.082829Z","signature_b64":"RHnIniTUEwBoImK1ZRIUzEcSPnpBxfL2H35mekCmkjVkId+VmlPQ6Wo3ywLK+CjeQ3wuPutd73KQMEI+ZypjDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"971091ea787a9523fc15eef7af8c72de692fba594631ed96094d9f9425b301ae","last_reissued_at":"2026-07-29T01:25:11.082001Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T01:25:11.082001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.25356","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":"2026-07-29T01:25:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FNSXwb48Ii4hnX3VvS+IYzsl+QRz/pFIyGzIG987I7ipF4X3SUUmY61Jol9yU1wx9Hihhke44M5CXWENLLBhAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T16:21:55.212329Z"},"content_sha256":"cb51e2d82e6d82dc2892fcb82d04581abc677f616c04823b0584fbb617a900b6","schema_version":"1.0","event_id":"sha256:cb51e2d82e6d82dc2892fcb82d04581abc677f616c04823b0584fbb617a900b6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:S4IJD2TYPKKSH7AV53327DDS3Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Quality Profiling at Scale with Progressive Sampling: A Benchmark for Data-Centric AI Pipelines","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.DB","authors_text":"Laure Berti-Equille","submitted_at":"2026-07-28T07:03:50Z","abstract_excerpt":"Data quality profiling -- computing missing-value rates, duplicate fractions, outlier densities, and functional-dependency violations -- is foundational for data-centric AI pipelines, yet exhaustive scans over millions of rows are prohibitively slow for near-real-time monitoring. Progressive sampling is the standard alternative; the open question is which strategy best preserves profile fidelity at scale. We benchmark nine sampling strategies -- blind (random uniform, geometric, Yamane, cluster) and proxy-guided (Metropolis-Hastings, DAG, stratified by column type or quality score, importance-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.25356","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/2607.25356/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":"2026-07-29T01:25:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"drNoVLQ9b94YlnNBEIywZ5gibEZMGUVnLZesQt7PwGFsLM+vRldDGySdqyUv8TX97z/f3gQe25rUN2x0oB1oCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T16:21:55.213446Z"},"content_sha256":"22b9b4097c7f02826b06c2284634a0910a93312b21d43598757c37c1b9de85fd","schema_version":"1.0","event_id":"sha256:22b9b4097c7f02826b06c2284634a0910a93312b21d43598757c37c1b9de85fd"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:S4IJD2TYPKKSH7AV53327DDS3Z","target":"integrity","payload":{"note":"DOI is split by whitespace or line breaks in the printed bibliography. Reconstructed DOI 10.1504/IJIQ.2011.043780 resolves to 'Assessment and analysis of information quality: a multidimensional model and case studies'. A reader following the printed text alone cannot reach it.","snippet":"Berti-Équille, L., Comyn-Wattiau, I., Cosquer, M., Kedad, Z., Nugier, S., Peralta, V., Cherfi, S.S.S., Thion-Goasdoué, V.: Assessment and analysis of information quality: A multidimensional model and case studies. International Journal of I","arxiv_id":"2607.25356","detector":"doi_compliance","evidence":{"ref_index":6,"verdict_class":"incontrovertible","resolved_title":"Assessment and analysis of information quality: a multidimensional model and case studies","printed_excerpt":"10.1504/ijiq.2011","reconstructed_doi":"10.1504/IJIQ.2011.043780"},"severity":"advisory","ref_index":6,"audited_at":"2026-08-01T02:52:20.465284Z","event_type":"pith.integrity.v1","detected_doi":"10.1504/IJIQ.2011.043780","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"1ce054deae09e8b1d4c16b9e54dd5c15276844e3577e9715c1d372144028cf00","paper_version":1,"verdict_class":"incontrovertible","resolved_title":"Assessment and analysis of information quality: a multidimensional model and case studies","detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":14955,"payload_sha256":"0536a1f000cb9984a39937703c938746c447552a96b3a75cf9253da47f57eb73","signature_b64":"40VlnSTGiK1AnuzUfHQ2BTq8WlooeA4E5wGRQYQBXZtiLfdDuydYR6vlyIb3FZNxNRm2oZPJk4VLyyqf3pglAg==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-01T02:56:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sGaw6VIrFEpATgHLrkv7EHC5HIZeZ7P1m1wBUQDb5sPRBwOW/GEAUHgVP7RNmsInixWpNA/IqTKuy8imUsm+Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T16:21:55.223573Z"},"content_sha256":"99073a9263fd6d8ef2efc9310b5f535c17a162e46a0e92099a28bc2ad829f05a","schema_version":"1.0","event_id":"sha256:99073a9263fd6d8ef2efc9310b5f535c17a162e46a0e92099a28bc2ad829f05a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S4IJD2TYPKKSH7AV53327DDS3Z/bundle.json","state_url":"https://pith.science/pith/S4IJD2TYPKKSH7AV53327DDS3Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S4IJD2TYPKKSH7AV53327DDS3Z/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":"2026-08-05T16:21:55Z","links":{"resolver":"https://pith.science/pith/S4IJD2TYPKKSH7AV53327DDS3Z","bundle":"https://pith.science/pith/S4IJD2TYPKKSH7AV53327DDS3Z/bundle.json","state":"https://pith.science/pith/S4IJD2TYPKKSH7AV53327DDS3Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S4IJD2TYPKKSH7AV53327DDS3Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:S4IJD2TYPKKSH7AV53327DDS3Z","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"48b3de31e170afa00046ef86d5bd179a941eb778543b0b8df8a2a103d77bace4","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2026-07-28T07:03:50Z","title_canon_sha256":"bdfa3d43780894aab22e89d1e8fbdb546d8cafd29a79698dde88dab9830322af"},"schema_version":"1.0","source":{"id":"2607.25356","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.25356","created_at":"2026-07-29T01:25:11Z"},{"alias_kind":"arxiv_version","alias_value":"2607.25356v1","created_at":"2026-07-29T01:25:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.25356","created_at":"2026-07-29T01:25:11Z"},{"alias_kind":"pith_short_12","alias_value":"S4IJD2TYPKKS","created_at":"2026-07-29T01:25:11Z"},{"alias_kind":"pith_short_16","alias_value":"S4IJD2TYPKKSH7AV","created_at":"2026-07-29T01:25:11Z"},{"alias_kind":"pith_short_8","alias_value":"S4IJD2TY","created_at":"2026-07-29T01:25:11Z"}],"graph_snapshots":[{"event_id":"sha256:22b9b4097c7f02826b06c2284634a0910a93312b21d43598757c37c1b9de85fd","target":"graph","created_at":"2026-07-29T01:25:11Z","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/2607.25356/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data quality profiling -- computing missing-value rates, duplicate fractions, outlier densities, and functional-dependency violations -- is foundational for data-centric AI pipelines, yet exhaustive scans over millions of rows are prohibitively slow for near-real-time monitoring. Progressive sampling is the standard alternative; the open question is which strategy best preserves profile fidelity at scale. We benchmark nine sampling strategies -- blind (random uniform, geometric, Yamane, cluster) and proxy-guided (Metropolis-Hastings, DAG, stratified by column type or quality score, importance-","authors_text":"Laure Berti-Equille","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2026-07-28T07:03:50Z","title":"Data Quality Profiling at Scale with Progressive Sampling: A Benchmark for Data-Centric AI Pipelines"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.25356","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:cb51e2d82e6d82dc2892fcb82d04581abc677f616c04823b0584fbb617a900b6","target":"record","created_at":"2026-07-29T01:25:11Z","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":"48b3de31e170afa00046ef86d5bd179a941eb778543b0b8df8a2a103d77bace4","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2026-07-28T07:03:50Z","title_canon_sha256":"bdfa3d43780894aab22e89d1e8fbdb546d8cafd29a79698dde88dab9830322af"},"schema_version":"1.0","source":{"id":"2607.25356","kind":"arxiv","version":1}},"canonical_sha256":"971091ea787a9523fc15eef7af8c72de692fba594631ed96094d9f9425b301ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"971091ea787a9523fc15eef7af8c72de692fba594631ed96094d9f9425b301ae","first_computed_at":"2026-07-29T01:25:11.082001Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-29T01:25:11.082001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RHnIniTUEwBoImK1ZRIUzEcSPnpBxfL2H35mekCmkjVkId+VmlPQ6Wo3ywLK+CjeQ3wuPutd73KQMEI+ZypjDg==","signature_status":"signed_v1","signed_at":"2026-07-29T01:25:11.082829Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.25356","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb51e2d82e6d82dc2892fcb82d04581abc677f616c04823b0584fbb617a900b6","sha256:22b9b4097c7f02826b06c2284634a0910a93312b21d43598757c37c1b9de85fd","sha256:99073a9263fd6d8ef2efc9310b5f535c17a162e46a0e92099a28bc2ad829f05a"],"state_sha256":"0747a376304fb4764f65b6748882885ad48960dc9e8fa321cb88f0a64c898146"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FsTn55XGfuDKizJgmvTJ5s8HMau8cbi8bUGKgXIK3S6JfSdSpyfLb0bjshcvKiKiJSndb9xtj2LJTE+R61RJBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T16:21:55.226516Z","bundle_sha256":"2be75835000afe5a02d01874c65460efaf159564fe0a621026ffeb80e6548ff9"}}