{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:MU57QG24PQR5RCN6V6F47W3HYD","short_pith_number":"pith:MU57QG24","canonical_record":{"source":{"id":"2606.30371","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2026-06-29T14:34:22Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"0f7f0bbd42e7115a11fc6eb2f451ebcf46458aa41b6ecaf3b34ec13ff2e910db","abstract_canon_sha256":"f64c48110f095eab7e452096c8a50b27777e92d348d1a257083ae460163e077e"},"schema_version":"1.0"},"canonical_sha256":"653bf81b5c7c23d889beaf8bcfdb67c0cdad354d630bd0ef5bed01a5d0a55a82","source":{"kind":"arxiv","id":"2606.30371","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.30371","created_at":"2026-06-30T02:18:12Z"},{"alias_kind":"arxiv_version","alias_value":"2606.30371v1","created_at":"2026-06-30T02:18:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30371","created_at":"2026-06-30T02:18:12Z"},{"alias_kind":"pith_short_12","alias_value":"MU57QG24PQR5","created_at":"2026-06-30T02:18:12Z"},{"alias_kind":"pith_short_16","alias_value":"MU57QG24PQR5RCN6","created_at":"2026-06-30T02:18:12Z"},{"alias_kind":"pith_short_8","alias_value":"MU57QG24","created_at":"2026-06-30T02:18:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:MU57QG24PQR5RCN6V6F47W3HYD","target":"record","payload":{"canonical_record":{"source":{"id":"2606.30371","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2026-06-29T14:34:22Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"0f7f0bbd42e7115a11fc6eb2f451ebcf46458aa41b6ecaf3b34ec13ff2e910db","abstract_canon_sha256":"f64c48110f095eab7e452096c8a50b27777e92d348d1a257083ae460163e077e"},"schema_version":"1.0"},"canonical_sha256":"653bf81b5c7c23d889beaf8bcfdb67c0cdad354d630bd0ef5bed01a5d0a55a82","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:18:12.342463Z","signature_b64":"gKLRc1IdaggVpNlH2MdJ73uYSLqGzz9hAzS1zgjHdoLkYsTX2+ZALRv46bqKD24Q1zotQ0PGdghwgKt/J1WeAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"653bf81b5c7c23d889beaf8bcfdb67c0cdad354d630bd0ef5bed01a5d0a55a82","last_reissued_at":"2026-06-30T02:18:12.341831Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:18:12.341831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.30371","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":"2026-06-30T02:18:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q/rDaDaP8mHr4Y6epnpp8mnw9R+P8jq82wQgWCAMURv5Al2iD41qXsdKwWN/Lm8srClf+LDXp47aOsaOgtklDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T21:29:08.504493Z"},"content_sha256":"a191b8c6f8146517092c2f3e38277d0936f3c71a10c7b04bb22c1ac3ed596671","schema_version":"1.0","event_id":"sha256:a191b8c6f8146517092c2f3e38277d0936f3c71a10c7b04bb22c1ac3ed596671"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:MU57QG24PQR5RCN6V6F47W3HYD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MaDI-Bench: An End-to-End Data Integration Benchmark","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.DB","authors_text":"Aaron Steiner, Christian Bizer, Ralph Peeters","submitted_at":"2026-06-29T14:34:22Z","abstract_excerpt":"Data integration combines heterogeneous data sets into a single, coherent representation. Data integration involves a sequence of interdependent tasks including schema matching, value normalization, entity blocking, entity matching, and data fusion. Existing benchmarks either evaluate these steps in isolation or cover only incomplete versions of the data integration pipeline, omitting specific steps. The lack of public end-to-end data integration benchmarks hinders research on data integration methods that address the integration process as a whole. This paper fills this gap by introducing the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30371","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/2606.30371/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":"2026-06-30T02:18:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hVwH6BZAjZTa6by2W60a2PPiMqkhqbbFnFZSJL3xXmOAbAY7c3xC/TfbbR6IITvlcSum8hWtTBNysNdP+OXeAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T21:29:08.504867Z"},"content_sha256":"15c6f154b12d371ab2b0fb8629c7f45c2500103ff843c19e6a4d93cd6d2af1fb","schema_version":"1.0","event_id":"sha256:15c6f154b12d371ab2b0fb8629c7f45c2500103ff843c19e6a4d93cd6d2af1fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MU57QG24PQR5RCN6V6F47W3HYD/bundle.json","state_url":"https://pith.science/pith/MU57QG24PQR5RCN6V6F47W3HYD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MU57QG24PQR5RCN6V6F47W3HYD/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":"2026-07-01T21:29:08Z","links":{"resolver":"https://pith.science/pith/MU57QG24PQR5RCN6V6F47W3HYD","bundle":"https://pith.science/pith/MU57QG24PQR5RCN6V6F47W3HYD/bundle.json","state":"https://pith.science/pith/MU57QG24PQR5RCN6V6F47W3HYD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MU57QG24PQR5RCN6V6F47W3HYD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MU57QG24PQR5RCN6V6F47W3HYD","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":"f64c48110f095eab7e452096c8a50b27777e92d348d1a257083ae460163e077e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2026-06-29T14:34:22Z","title_canon_sha256":"0f7f0bbd42e7115a11fc6eb2f451ebcf46458aa41b6ecaf3b34ec13ff2e910db"},"schema_version":"1.0","source":{"id":"2606.30371","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.30371","created_at":"2026-06-30T02:18:12Z"},{"alias_kind":"arxiv_version","alias_value":"2606.30371v1","created_at":"2026-06-30T02:18:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30371","created_at":"2026-06-30T02:18:12Z"},{"alias_kind":"pith_short_12","alias_value":"MU57QG24PQR5","created_at":"2026-06-30T02:18:12Z"},{"alias_kind":"pith_short_16","alias_value":"MU57QG24PQR5RCN6","created_at":"2026-06-30T02:18:12Z"},{"alias_kind":"pith_short_8","alias_value":"MU57QG24","created_at":"2026-06-30T02:18:12Z"}],"graph_snapshots":[{"event_id":"sha256:15c6f154b12d371ab2b0fb8629c7f45c2500103ff843c19e6a4d93cd6d2af1fb","target":"graph","created_at":"2026-06-30T02:18:12Z","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/2606.30371/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data integration combines heterogeneous data sets into a single, coherent representation. Data integration involves a sequence of interdependent tasks including schema matching, value normalization, entity blocking, entity matching, and data fusion. Existing benchmarks either evaluate these steps in isolation or cover only incomplete versions of the data integration pipeline, omitting specific steps. The lack of public end-to-end data integration benchmarks hinders research on data integration methods that address the integration process as a whole. This paper fills this gap by introducing the","authors_text":"Aaron Steiner, Christian Bizer, Ralph Peeters","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2026-06-29T14:34:22Z","title":"MaDI-Bench: An End-to-End Data Integration Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30371","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:a191b8c6f8146517092c2f3e38277d0936f3c71a10c7b04bb22c1ac3ed596671","target":"record","created_at":"2026-06-30T02:18:12Z","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":"f64c48110f095eab7e452096c8a50b27777e92d348d1a257083ae460163e077e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2026-06-29T14:34:22Z","title_canon_sha256":"0f7f0bbd42e7115a11fc6eb2f451ebcf46458aa41b6ecaf3b34ec13ff2e910db"},"schema_version":"1.0","source":{"id":"2606.30371","kind":"arxiv","version":1}},"canonical_sha256":"653bf81b5c7c23d889beaf8bcfdb67c0cdad354d630bd0ef5bed01a5d0a55a82","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"653bf81b5c7c23d889beaf8bcfdb67c0cdad354d630bd0ef5bed01a5d0a55a82","first_computed_at":"2026-06-30T02:18:12.341831Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T02:18:12.341831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gKLRc1IdaggVpNlH2MdJ73uYSLqGzz9hAzS1zgjHdoLkYsTX2+ZALRv46bqKD24Q1zotQ0PGdghwgKt/J1WeAw==","signature_status":"signed_v1","signed_at":"2026-06-30T02:18:12.342463Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.30371","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a191b8c6f8146517092c2f3e38277d0936f3c71a10c7b04bb22c1ac3ed596671","sha256:15c6f154b12d371ab2b0fb8629c7f45c2500103ff843c19e6a4d93cd6d2af1fb"],"state_sha256":"b8f55eda171df4b933d77c39dde3146a32667fc012822b3ac5c2266f1173184d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NzY4iIzz4eRLtzk9+s4a7OGB56nZJvaORVJS7UQgR82u3DJCfGQyRjqdfcteKlXPRqvhsnXmpAwK1PRGullBCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-01T21:29:08.506909Z","bundle_sha256":"38a5ffb11883cec6e5933d05d5a329cbff0565a9c1be6dc925019edb8fa80934"}}