{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7YS22BHEB3DJH567EASOGMYD3H","short_pith_number":"pith:7YS22BHE","canonical_record":{"source":{"id":"2507.02020","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-07-02T14:37:31Z","cross_cats_sorted":[],"title_canon_sha256":"415f24128504e5ac794809aec9dafef9244391a436ffb7ea532c21793e85efc2","abstract_canon_sha256":"a74b4bf5c350184734388f1193b17d8e9f58c93b6299a4760323859a373d9ab5"},"schema_version":"1.0"},"canonical_sha256":"fe25ad04e40ec693f7df2024e33303d9ce1599dd4ddd4cb4c99b960c0631c40b","source":{"kind":"arxiv","id":"2507.02020","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.02020","created_at":"2026-07-05T11:31:10Z"},{"alias_kind":"arxiv_version","alias_value":"2507.02020v1","created_at":"2026-07-05T11:31:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02020","created_at":"2026-07-05T11:31:10Z"},{"alias_kind":"pith_short_12","alias_value":"7YS22BHEB3DJ","created_at":"2026-07-05T11:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"7YS22BHEB3DJH567","created_at":"2026-07-05T11:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"7YS22BHE","created_at":"2026-07-05T11:31:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7YS22BHEB3DJH567EASOGMYD3H","target":"record","payload":{"canonical_record":{"source":{"id":"2507.02020","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-07-02T14:37:31Z","cross_cats_sorted":[],"title_canon_sha256":"415f24128504e5ac794809aec9dafef9244391a436ffb7ea532c21793e85efc2","abstract_canon_sha256":"a74b4bf5c350184734388f1193b17d8e9f58c93b6299a4760323859a373d9ab5"},"schema_version":"1.0"},"canonical_sha256":"fe25ad04e40ec693f7df2024e33303d9ce1599dd4ddd4cb4c99b960c0631c40b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:10.795574Z","signature_b64":"CGvCObsDuvf1doGPyphhJAzZ3owu9aADSvdvd9H4yd4WcfpTn2mS0OY5sfpBLZkChW1LzyLVEUEZO8evgkD+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe25ad04e40ec693f7df2024e33303d9ce1599dd4ddd4cb4c99b960c0631c40b","last_reissued_at":"2026-07-05T11:31:10.795016Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:10.795016Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.02020","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":"2026-07-05T11:31:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uDBEq+3GVkgt4Qx8iT4FY4m2aWDU2rUArhbsPpDyFXHf7XQAoglt+upi33VuUKdNrUzwl2TZQaIl6HX69VeZCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:45:25.382687Z"},"content_sha256":"4fb3afaf53c68cf36126c0e066c2e80a1e709d6fc015be5885610d658632beec","schema_version":"1.0","event_id":"sha256:4fb3afaf53c68cf36126c0e066c2e80a1e709d6fc015be5885610d658632beec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7YS22BHEB3DJH567EASOGMYD3H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Template-Based Schema Matching of Multi-Layout Tenancy Schedules:A Comparative Study of a Template-Based Hybrid Matcher and the ALITE Full Disjunction Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Joep van Vliet, Seyed Sahand Mohammadi Ziabari, Tim Uilkema, Yao Ma","submitted_at":"2025-07-02T14:37:31Z","abstract_excerpt":"The lack of standardized tabular formats for tenancy schedules across real estate firms creates significant inefficiencies in data integration. Existing automated integration methods, such as Full Disjunction (FD)-based models like ALITE, prioritize completeness but result in schema bloat, sparse attributes and limited business usability. We propose a novel hybrid, template-based schema matcher that aligns multi-layout tenancy schedules to a predefined target schema. The matcher combines schema (Jaccard, Levenshtein) and instance-based metrics (data types, distributions) with globally optimal "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02020","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/2507.02020/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":"2026-07-05T11:31:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TFplh5YY8X+eweGtW4RNDIJoYHhgpeHXVkgKQs9qnaWfSLHt/hING34QIgDNNzdAS+LhXh0dHg/YthaA7eQOAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:45:25.383172Z"},"content_sha256":"a725271e674b1d938cb7a0f7cb6d7a99a6d4e13463437d80eba4921ac6184615","schema_version":"1.0","event_id":"sha256:a725271e674b1d938cb7a0f7cb6d7a99a6d4e13463437d80eba4921ac6184615"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7YS22BHEB3DJH567EASOGMYD3H/bundle.json","state_url":"https://pith.science/pith/7YS22BHEB3DJH567EASOGMYD3H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7YS22BHEB3DJH567EASOGMYD3H/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":"2026-08-07T15:45:25Z","links":{"resolver":"https://pith.science/pith/7YS22BHEB3DJH567EASOGMYD3H","bundle":"https://pith.science/pith/7YS22BHEB3DJH567EASOGMYD3H/bundle.json","state":"https://pith.science/pith/7YS22BHEB3DJH567EASOGMYD3H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7YS22BHEB3DJH567EASOGMYD3H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7YS22BHEB3DJH567EASOGMYD3H","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":"a74b4bf5c350184734388f1193b17d8e9f58c93b6299a4760323859a373d9ab5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-07-02T14:37:31Z","title_canon_sha256":"415f24128504e5ac794809aec9dafef9244391a436ffb7ea532c21793e85efc2"},"schema_version":"1.0","source":{"id":"2507.02020","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.02020","created_at":"2026-07-05T11:31:10Z"},{"alias_kind":"arxiv_version","alias_value":"2507.02020v1","created_at":"2026-07-05T11:31:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02020","created_at":"2026-07-05T11:31:10Z"},{"alias_kind":"pith_short_12","alias_value":"7YS22BHEB3DJ","created_at":"2026-07-05T11:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"7YS22BHEB3DJH567","created_at":"2026-07-05T11:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"7YS22BHE","created_at":"2026-07-05T11:31:10Z"}],"graph_snapshots":[{"event_id":"sha256:a725271e674b1d938cb7a0f7cb6d7a99a6d4e13463437d80eba4921ac6184615","target":"graph","created_at":"2026-07-05T11:31:10Z","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/2507.02020/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The lack of standardized tabular formats for tenancy schedules across real estate firms creates significant inefficiencies in data integration. Existing automated integration methods, such as Full Disjunction (FD)-based models like ALITE, prioritize completeness but result in schema bloat, sparse attributes and limited business usability. We propose a novel hybrid, template-based schema matcher that aligns multi-layout tenancy schedules to a predefined target schema. The matcher combines schema (Jaccard, Levenshtein) and instance-based metrics (data types, distributions) with globally optimal ","authors_text":"Joep van Vliet, Seyed Sahand Mohammadi Ziabari, Tim Uilkema, Yao Ma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-07-02T14:37:31Z","title":"Template-Based Schema Matching of Multi-Layout Tenancy Schedules:A Comparative Study of a Template-Based Hybrid Matcher and the ALITE Full Disjunction Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02020","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":"sha256:4fb3afaf53c68cf36126c0e066c2e80a1e709d6fc015be5885610d658632beec","target":"record","created_at":"2026-07-05T11:31:10Z","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":"a74b4bf5c350184734388f1193b17d8e9f58c93b6299a4760323859a373d9ab5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-07-02T14:37:31Z","title_canon_sha256":"415f24128504e5ac794809aec9dafef9244391a436ffb7ea532c21793e85efc2"},"schema_version":"1.0","source":{"id":"2507.02020","kind":"arxiv","version":1}},"canonical_sha256":"fe25ad04e40ec693f7df2024e33303d9ce1599dd4ddd4cb4c99b960c0631c40b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe25ad04e40ec693f7df2024e33303d9ce1599dd4ddd4cb4c99b960c0631c40b","first_computed_at":"2026-07-05T11:31:10.795016Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:31:10.795016Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CGvCObsDuvf1doGPyphhJAzZ3owu9aADSvdvd9H4yd4WcfpTn2mS0OY5sfpBLZkChW1LzyLVEUEZO8evgkD+BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:31:10.795574Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.02020","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fb3afaf53c68cf36126c0e066c2e80a1e709d6fc015be5885610d658632beec","sha256:a725271e674b1d938cb7a0f7cb6d7a99a6d4e13463437d80eba4921ac6184615"],"state_sha256":"e2959d7dd22a490da0eabe7182de91159cad23ee317c20be83b6f12ab62df222"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QMbrSkogU7ta3nFXFO0tnI+QaAxl7MyOcd78bhESXsD7FyrLWZHkF1g8pjjyQ13pPSisvasguYaEev+OCglQCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T15:45:25.389416Z","bundle_sha256":"ad594b4772288c89580a57c5d8ada75bf18b91f8b3c570e7adfa5260508b1db5"}}