{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3AOUGLBZE7AD7NL3HNDAAQPKN2","short_pith_number":"pith:3AOUGLBZ","canonical_record":{"source":{"id":"2404.18043","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-28T01:38:38Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"af94958afda9f9559218e2a32f3135a468a8cb3c8e4ae40458c992dbde6ea2b1","abstract_canon_sha256":"3e3c923dff9c32241281b13b1083f172574d23c2022f768a63db0a80ed521b1e"},"schema_version":"1.0"},"canonical_sha256":"d81d432c3927c03fb57b3b460041ea6ead0e988f704894b577bb63f035a70ae3","source":{"kind":"arxiv","id":"2404.18043","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.18043","created_at":"2026-07-05T11:52:12Z"},{"alias_kind":"arxiv_version","alias_value":"2404.18043v3","created_at":"2026-07-05T11:52:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.18043","created_at":"2026-07-05T11:52:12Z"},{"alias_kind":"pith_short_12","alias_value":"3AOUGLBZE7AD","created_at":"2026-07-05T11:52:12Z"},{"alias_kind":"pith_short_16","alias_value":"3AOUGLBZE7AD7NL3","created_at":"2026-07-05T11:52:12Z"},{"alias_kind":"pith_short_8","alias_value":"3AOUGLBZ","created_at":"2026-07-05T11:52:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3AOUGLBZE7AD7NL3HNDAAQPKN2","target":"record","payload":{"canonical_record":{"source":{"id":"2404.18043","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-28T01:38:38Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"af94958afda9f9559218e2a32f3135a468a8cb3c8e4ae40458c992dbde6ea2b1","abstract_canon_sha256":"3e3c923dff9c32241281b13b1083f172574d23c2022f768a63db0a80ed521b1e"},"schema_version":"1.0"},"canonical_sha256":"d81d432c3927c03fb57b3b460041ea6ead0e988f704894b577bb63f035a70ae3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:12.939162Z","signature_b64":"63Di9GR2zyOpXOggV4DcW+lK5BiuFLyTcJOjVn/Rk/ljCSFttBIiN8240DPnWHQ2f9MDbJ3KYeDwnbbEkgecBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d81d432c3927c03fb57b3b460041ea6ead0e988f704894b577bb63f035a70ae3","last_reissued_at":"2026-07-05T11:52:12.938745Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:12.938745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.18043","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:52:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"70qaq1izfRXaN6Cpe138DBkWUVK9aYTp68M231FXQB03xzqPjMj+y3aLmC6ksPyRjDEpJpuaEEnrrzRqb+m5CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:14:31.171554Z"},"content_sha256":"61d3a73b8aa907ff45ae115ff6a95ec4c095cc9f7f18637776158b11f0173281","schema_version":"1.0","event_id":"sha256:61d3a73b8aa907ff45ae115ff6a95ec4c095cc9f7f18637776158b11f0173281"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3AOUGLBZE7AD7NL3HNDAAQPKN2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Utilizing Large Language Models for Information Extraction from Real Estate Transactions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Haoxiang Gao, Jinghan Cao, Shiqi Yang, Yu Zhao","submitted_at":"2024-04-28T01:38:38Z","abstract_excerpt":"Real estate sales contracts contain crucial information for property transactions, but manual data extraction can be time-consuming and error-prone. This paper explores the application of large language models, specifically transformer-based architectures, for automated information extraction from real estate contracts. We discuss challenges, techniques, and future directions in leveraging these models to improve efficiency and accuracy in real estate contract analysis. We generated synthetic contracts using the real-world transaction dataset, thereby fine-tuning the large-language model and a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.18043","kind":"arxiv","version":3},"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/2404.18043/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":"2026-07-05T11:52:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hT73mYCIJMGUPbqwZPpE0fdM8LKYw7HbgJS9u/9ADYxYrguEZGg0w3erOBEDc2zQbZSxRN7QhbGL2h5gFAKmAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:14:31.172080Z"},"content_sha256":"d7693a16a3def8e5267ffccc6dc8bf347760d4fb6aa768694c0d0e756f34a6c1","schema_version":"1.0","event_id":"sha256:d7693a16a3def8e5267ffccc6dc8bf347760d4fb6aa768694c0d0e756f34a6c1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3AOUGLBZE7AD7NL3HNDAAQPKN2/bundle.json","state_url":"https://pith.science/pith/3AOUGLBZE7AD7NL3HNDAAQPKN2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3AOUGLBZE7AD7NL3HNDAAQPKN2/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":"2026-08-06T01:14:31Z","links":{"resolver":"https://pith.science/pith/3AOUGLBZE7AD7NL3HNDAAQPKN2","bundle":"https://pith.science/pith/3AOUGLBZE7AD7NL3HNDAAQPKN2/bundle.json","state":"https://pith.science/pith/3AOUGLBZE7AD7NL3HNDAAQPKN2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3AOUGLBZE7AD7NL3HNDAAQPKN2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3AOUGLBZE7AD7NL3HNDAAQPKN2","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":"3e3c923dff9c32241281b13b1083f172574d23c2022f768a63db0a80ed521b1e","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-28T01:38:38Z","title_canon_sha256":"af94958afda9f9559218e2a32f3135a468a8cb3c8e4ae40458c992dbde6ea2b1"},"schema_version":"1.0","source":{"id":"2404.18043","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.18043","created_at":"2026-07-05T11:52:12Z"},{"alias_kind":"arxiv_version","alias_value":"2404.18043v3","created_at":"2026-07-05T11:52:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.18043","created_at":"2026-07-05T11:52:12Z"},{"alias_kind":"pith_short_12","alias_value":"3AOUGLBZE7AD","created_at":"2026-07-05T11:52:12Z"},{"alias_kind":"pith_short_16","alias_value":"3AOUGLBZE7AD7NL3","created_at":"2026-07-05T11:52:12Z"},{"alias_kind":"pith_short_8","alias_value":"3AOUGLBZ","created_at":"2026-07-05T11:52:12Z"}],"graph_snapshots":[{"event_id":"sha256:d7693a16a3def8e5267ffccc6dc8bf347760d4fb6aa768694c0d0e756f34a6c1","target":"graph","created_at":"2026-07-05T11:52:12Z","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/2404.18043/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Real estate sales contracts contain crucial information for property transactions, but manual data extraction can be time-consuming and error-prone. This paper explores the application of large language models, specifically transformer-based architectures, for automated information extraction from real estate contracts. We discuss challenges, techniques, and future directions in leveraging these models to improve efficiency and accuracy in real estate contract analysis. We generated synthetic contracts using the real-world transaction dataset, thereby fine-tuning the large-language model and a","authors_text":"Haoxiang Gao, Jinghan Cao, Shiqi Yang, Yu Zhao","cross_cats":["cs.IR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-28T01:38:38Z","title":"Utilizing Large Language Models for Information Extraction from Real Estate Transactions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.18043","kind":"arxiv","version":3},"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":"sha256:61d3a73b8aa907ff45ae115ff6a95ec4c095cc9f7f18637776158b11f0173281","target":"record","created_at":"2026-07-05T11:52:12Z","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":"3e3c923dff9c32241281b13b1083f172574d23c2022f768a63db0a80ed521b1e","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-28T01:38:38Z","title_canon_sha256":"af94958afda9f9559218e2a32f3135a468a8cb3c8e4ae40458c992dbde6ea2b1"},"schema_version":"1.0","source":{"id":"2404.18043","kind":"arxiv","version":3}},"canonical_sha256":"d81d432c3927c03fb57b3b460041ea6ead0e988f704894b577bb63f035a70ae3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d81d432c3927c03fb57b3b460041ea6ead0e988f704894b577bb63f035a70ae3","first_computed_at":"2026-07-05T11:52:12.938745Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:52:12.938745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"63Di9GR2zyOpXOggV4DcW+lK5BiuFLyTcJOjVn/Rk/ljCSFttBIiN8240DPnWHQ2f9MDbJ3KYeDwnbbEkgecBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:52:12.939162Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.18043","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61d3a73b8aa907ff45ae115ff6a95ec4c095cc9f7f18637776158b11f0173281","sha256:d7693a16a3def8e5267ffccc6dc8bf347760d4fb6aa768694c0d0e756f34a6c1"],"state_sha256":"b38f84cc9061364238ae121bd82e5f0d206010c890b67abb6d7faef8ae2c6831"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lK76dMZCCPnSNMmjNs6Kq+Hd/1OTXnPOkatOpBVtkuHzyn3G3wtB/MnJt1LBIyP8Pd13MzcQlvUKtLh/FndWCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T01:14:31.176988Z","bundle_sha256":"e1ffb1fc8d7e977edb7746ace493127e9519d9aac2b2ba7395e262b5f63e0cf8"}}