{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:A6YJCE7RNGOQJCFN6GBPNNSDO7","short_pith_number":"pith:A6YJCE7R","canonical_record":{"source":{"id":"2607.06012","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-07T08:54:11Z","cross_cats_sorted":[],"title_canon_sha256":"78544ec16a57f7121476f5b11200b0f88d55adbd11832fcfcd4d9993d840351a","abstract_canon_sha256":"63cbb8111d94c34c38c9918b857b92ba0de1f9e0c511d931f29aac9c7d297eae"},"schema_version":"1.0"},"canonical_sha256":"07b09113f1699d0488adf182f6b64377f05906652cbba0b7fef9b3e7a5d930b8","source":{"kind":"arxiv","id":"2607.06012","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.06012","created_at":"2026-07-08T01:18:53Z"},{"alias_kind":"arxiv_version","alias_value":"2607.06012v1","created_at":"2026-07-08T01:18:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06012","created_at":"2026-07-08T01:18:53Z"},{"alias_kind":"pith_short_12","alias_value":"A6YJCE7RNGOQ","created_at":"2026-07-08T01:18:53Z"},{"alias_kind":"pith_short_16","alias_value":"A6YJCE7RNGOQJCFN","created_at":"2026-07-08T01:18:53Z"},{"alias_kind":"pith_short_8","alias_value":"A6YJCE7R","created_at":"2026-07-08T01:18:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:A6YJCE7RNGOQJCFN6GBPNNSDO7","target":"record","payload":{"canonical_record":{"source":{"id":"2607.06012","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-07T08:54:11Z","cross_cats_sorted":[],"title_canon_sha256":"78544ec16a57f7121476f5b11200b0f88d55adbd11832fcfcd4d9993d840351a","abstract_canon_sha256":"63cbb8111d94c34c38c9918b857b92ba0de1f9e0c511d931f29aac9c7d297eae"},"schema_version":"1.0"},"canonical_sha256":"07b09113f1699d0488adf182f6b64377f05906652cbba0b7fef9b3e7a5d930b8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-08T01:18:53.933526Z","signature_b64":"ZtmoKrjIwafCXl/3scy5dSVzPjHt0zskAnnGG38Ui9mkqvZxqF5fHJwlmkPmaeCCnjBNrHHPbMdu9c1LyfD2DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07b09113f1699d0488adf182f6b64377f05906652cbba0b7fef9b3e7a5d930b8","last_reissued_at":"2026-07-08T01:18:53.932956Z","signature_status":"signed_v1","first_computed_at":"2026-07-08T01:18:53.932956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.06012","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":"2026-07-08T01:18:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ltkxvW6Gd6iKXs6vUidq/8i4DXGaq5J8OfeBM7WJmABmR7kdzyCMW/65hgoHk/tIoa1V/lRqnM08u+iVBORODA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T18:03:19.714017Z"},"content_sha256":"958872e3f8a6bb482b97ad69efd6e4b8ed6b2ad26940fa9f56520b5dfc91e44d","schema_version":"1.0","event_id":"sha256:958872e3f8a6bb482b97ad69efd6e4b8ed6b2ad26940fa9f56520b5dfc91e44d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:A6YJCE7RNGOQJCFN6GBPNNSDO7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Structured Data Extraction from Real Estate Documents using Clustering, Classification, and Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Carlos Francisco Moreno-Garc\\'ia, Muhammad Assad Shehbaz","submitted_at":"2026-07-07T08:54:11Z","abstract_excerpt":"Real estate property listings expose structured metadata through the API. Still, the richest property-level information (i.e., legal status, structural condition, utility supplies, heating systems) sits in attached questionnaire documents that no automated system currently processes at scale. These documents are heterogeneous. Some are digitally generated with selectable text, others are scanned physical forms. There are even more complex layouts that contain checkbox annotations that defeat conventional text extraction. In this paper, we present an end-to-end pipeline for acquiring, classifyi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06012","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/2607.06012/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":"2026-07-08T01:18:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vOHs+TxqiK/F+fWIYewhLRTLOe4aOCImIcmpiH4m1yJ5DzhqC0J13kAwLTSgpW6WV+M0FM7ER1t/pO3b+vGCCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T18:03:19.714541Z"},"content_sha256":"40f8bfeded87bd8133418cf9996ae7815f388eab5398abbb21d339a9ae544c9f","schema_version":"1.0","event_id":"sha256:40f8bfeded87bd8133418cf9996ae7815f388eab5398abbb21d339a9ae544c9f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A6YJCE7RNGOQJCFN6GBPNNSDO7/bundle.json","state_url":"https://pith.science/pith/A6YJCE7RNGOQJCFN6GBPNNSDO7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A6YJCE7RNGOQJCFN6GBPNNSDO7/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":"2026-08-12T18:03:19Z","links":{"resolver":"https://pith.science/pith/A6YJCE7RNGOQJCFN6GBPNNSDO7","bundle":"https://pith.science/pith/A6YJCE7RNGOQJCFN6GBPNNSDO7/bundle.json","state":"https://pith.science/pith/A6YJCE7RNGOQJCFN6GBPNNSDO7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A6YJCE7RNGOQJCFN6GBPNNSDO7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:A6YJCE7RNGOQJCFN6GBPNNSDO7","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":"63cbb8111d94c34c38c9918b857b92ba0de1f9e0c511d931f29aac9c7d297eae","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-07T08:54:11Z","title_canon_sha256":"78544ec16a57f7121476f5b11200b0f88d55adbd11832fcfcd4d9993d840351a"},"schema_version":"1.0","source":{"id":"2607.06012","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.06012","created_at":"2026-07-08T01:18:53Z"},{"alias_kind":"arxiv_version","alias_value":"2607.06012v1","created_at":"2026-07-08T01:18:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06012","created_at":"2026-07-08T01:18:53Z"},{"alias_kind":"pith_short_12","alias_value":"A6YJCE7RNGOQ","created_at":"2026-07-08T01:18:53Z"},{"alias_kind":"pith_short_16","alias_value":"A6YJCE7RNGOQJCFN","created_at":"2026-07-08T01:18:53Z"},{"alias_kind":"pith_short_8","alias_value":"A6YJCE7R","created_at":"2026-07-08T01:18:53Z"}],"graph_snapshots":[{"event_id":"sha256:40f8bfeded87bd8133418cf9996ae7815f388eab5398abbb21d339a9ae544c9f","target":"graph","created_at":"2026-07-08T01:18:53Z","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/2607.06012/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Real estate property listings expose structured metadata through the API. Still, the richest property-level information (i.e., legal status, structural condition, utility supplies, heating systems) sits in attached questionnaire documents that no automated system currently processes at scale. These documents are heterogeneous. Some are digitally generated with selectable text, others are scanned physical forms. There are even more complex layouts that contain checkbox annotations that defeat conventional text extraction. In this paper, we present an end-to-end pipeline for acquiring, classifyi","authors_text":"Carlos Francisco Moreno-Garc\\'ia, Muhammad Assad Shehbaz","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-07T08:54:11Z","title":"Structured Data Extraction from Real Estate Documents using Clustering, Classification, and Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06012","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":"sha256:958872e3f8a6bb482b97ad69efd6e4b8ed6b2ad26940fa9f56520b5dfc91e44d","target":"record","created_at":"2026-07-08T01:18:53Z","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":"63cbb8111d94c34c38c9918b857b92ba0de1f9e0c511d931f29aac9c7d297eae","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-07T08:54:11Z","title_canon_sha256":"78544ec16a57f7121476f5b11200b0f88d55adbd11832fcfcd4d9993d840351a"},"schema_version":"1.0","source":{"id":"2607.06012","kind":"arxiv","version":1}},"canonical_sha256":"07b09113f1699d0488adf182f6b64377f05906652cbba0b7fef9b3e7a5d930b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"07b09113f1699d0488adf182f6b64377f05906652cbba0b7fef9b3e7a5d930b8","first_computed_at":"2026-07-08T01:18:53.932956Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-08T01:18:53.932956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZtmoKrjIwafCXl/3scy5dSVzPjHt0zskAnnGG38Ui9mkqvZxqF5fHJwlmkPmaeCCnjBNrHHPbMdu9c1LyfD2DA==","signature_status":"signed_v1","signed_at":"2026-07-08T01:18:53.933526Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.06012","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:958872e3f8a6bb482b97ad69efd6e4b8ed6b2ad26940fa9f56520b5dfc91e44d","sha256:40f8bfeded87bd8133418cf9996ae7815f388eab5398abbb21d339a9ae544c9f"],"state_sha256":"4a58df5ea62c0a1a9616ca665b4bcc551f252f3f24267a27bc11c9a0ac78afaf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FZDjWEU+amBf01i8Yanm4Ig70uxCbK8LHmtHY6ANrjCMMTlICTpj4h0QD6loVCx5m4Vc3Iz5NzdyUIGtj7kpDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T18:03:19.720074Z","bundle_sha256":"325132474647b2e60ffb680a1b230747f79038bf7d989c3395d51f5dc79a5a56"}}