{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:H6INDLDWF5GVBMZLV5AHJXU6FJ","short_pith_number":"pith:H6INDLDW","canonical_record":{"source":{"id":"2605.13236","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T09:24:51Z","cross_cats_sorted":[],"title_canon_sha256":"fe79062cdf076f9644c3d32ed6cb8bca93db15e8b31c9e33624e587158396817","abstract_canon_sha256":"c7cb25196997d81cf2c32c3d17cdf0197232fb6aff5adeb7a2f41a43a7729dfc"},"schema_version":"1.0"},"canonical_sha256":"3f90d1ac762f4d50b32baf4074de9e2a59841cc5921b97e36d03cacedc62688d","source":{"kind":"arxiv","id":"2605.13236","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13236","created_at":"2026-05-18T02:44:49Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13236v1","created_at":"2026-05-18T02:44:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13236","created_at":"2026-05-18T02:44:49Z"},{"alias_kind":"pith_short_12","alias_value":"H6INDLDWF5GV","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"H6INDLDWF5GVBMZL","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"H6INDLDW","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:H6INDLDWF5GVBMZLV5AHJXU6FJ","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13236","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T09:24:51Z","cross_cats_sorted":[],"title_canon_sha256":"fe79062cdf076f9644c3d32ed6cb8bca93db15e8b31c9e33624e587158396817","abstract_canon_sha256":"c7cb25196997d81cf2c32c3d17cdf0197232fb6aff5adeb7a2f41a43a7729dfc"},"schema_version":"1.0"},"canonical_sha256":"3f90d1ac762f4d50b32baf4074de9e2a59841cc5921b97e36d03cacedc62688d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:49.545713Z","signature_b64":"6aK2CfQodQcwk3EUDuQci3pzeT3tiatOWgj85Ss5GbTrTaHh7LjlwcgKzdSHw9itgP7LAvU44ZnZvdMuIfuzDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f90d1ac762f4d50b32baf4074de9e2a59841cc5921b97e36d03cacedc62688d","last_reissued_at":"2026-05-18T02:44:49.545185Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:49.545185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13236","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":"2026-05-18T02:44:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"in626W6PY5x8ouugzg34zZVhCVibQaN/AA5jRLn5m//twyBoXuzvDhlmeboVl9oj2cArbaD6XD9xbLi0MdKqBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T21:07:29.383069Z"},"content_sha256":"a208101db04789ea97433fe0182f2fd8c0f4abe24f2facc45543f6ee56ea59ce","schema_version":"1.0","event_id":"sha256:a208101db04789ea97433fe0182f2fd8c0f4abe24f2facc45543f6ee56ea59ce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:H6INDLDWF5GVBMZLV5AHJXU6FJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Hybrid Framework for Natural Language Querying of IFC Models with Relational and Graph Representations","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"Transforming IFC models into relational tables and graphs lets an LLM answer natural language queries about building data with over 93 percent first-attempt accuracy.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haowen Xu, Johnson Xuesong Shen, Rabindra Lamsal, Sisi Zlatanova, Yafei Sun","submitted_at":"2026-05-13T09:24:51Z","abstract_excerpt":"Building Information Modeling (BIM) is widely used in the Architecture, Engineering, and Construction (AEC) industry, but the complexity of Industry Foundation Classes (IFC) limits accessibility for non-expert users. To address this, we introduce IfcLLM, a hybrid framework for natural language interaction with IFC-based BIM models. It transforms IFC models into complementary representations: a relational representation for structured element properties and geometry, and a graph representation for topological relationships. These representations are integrated through iterative retry-and-refine"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"combining complementary representations with iterative reasoning enables more accessible natural language querying of IFC data while supporting routine BIM analysis tasks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The transformations to relational and graph representations preserve all information needed for accurate querying, and the LLM can reliably detect and correct its own errors through iteration without introducing new inaccuracies.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"IfcLLM combines relational and graph representations of IFC models with iterative LLM reasoning to deliver 93.3-100% first-attempt accuracy on natural language queries across three test models.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Transforming IFC models into relational tables and graphs lets an LLM answer natural language queries about building data with over 93 percent first-attempt accuracy.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"34619d8f749ece0054e97d8c10d2ac3a088ea42cc80d0b2511adec8a18b329c1"},"source":{"id":"2605.13236","kind":"arxiv","version":1},"verdict":{"id":"77a86c08-06ea-4f6e-b33d-07d039a782b5","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:10:11.336493Z","strongest_claim":"combining complementary representations with iterative reasoning enables more accessible natural language querying of IFC data while supporting routine BIM analysis tasks.","one_line_summary":"IfcLLM combines relational and graph representations of IFC models with iterative LLM reasoning to deliver 93.3-100% first-attempt accuracy on natural language queries across three test models.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The transformations to relational and graph representations preserve all information needed for accurate querying, and the LLM can reliably detect and correct its own errors through iteration without introducing new inaccuracies.","pith_extraction_headline":"Transforming IFC models into relational tables and graphs lets an LLM answer natural language queries about building data with over 93 percent first-attempt accuracy."},"references":{"count":88,"sample":[{"doi":"","year":null,"title":"C. M. Eastman, BIM handbook: A guide to building information modeling for owners, managers, designers, engineers and contractors, John Wiley & Sons,","work_id":"d7f157e6-aea4-4c8c-94d6-17b79db54573","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1002/9781119287568","year":null,"title":"doi:10.1002/9781119287568","work_id":"f5dd05ba-0949-493b-9504-14a66dd24c16","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1016/j.autcon.2019.03.005","year":2019,"title":"H. Wang, Y. Pan, X. Luo, Integration of bim and gis in sustainable built environment: A review and bibliometric analysis, Automation in construction 103 (2019) 41–52. doi:10.1016/j.autcon.2019.03.005","work_id":"5d64fe89-6e66-4392-9e52-f530508e6336","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1016/j.landusepol.2021.105355","year":2021,"title":"A. Alattas, E. Kalogianni, T. Alzahrani, S. Zlatanova, P. van Oosterom, Map- ping private, common, and exclusive common spaces in buildings from bim/ifc to ladm. a case study from saudi arabia, Land U","work_id":"07f9ea1f-bce9-4e9e-8fc8-58cf9fdb40c3","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1016/j.autcon.2020.103436","year":2021,"title":"L. Liu, B. Li, S. Zlatanova, P. van Oosterom, Indoor navigation supported by the industry foundation classes (ifc): A survey, Automation in Construction 121 (2021) 103436. doi:10.1016/j.autcon.2020.10","work_id":"0be7e10e-8e5a-4a98-a75c-dfffef483b41","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":88,"snapshot_sha256":"a511d9246d67ab48b1054f9d279b8c13dd6e070419b0397adeacd3ba31664142","internal_anchors":5},"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":"77a86c08-06ea-4f6e-b33d-07d039a782b5"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XsGixzEpJFen60m//jfOb7rs1mspwICOrye80NQhOHfiUMPU3s/TCF1pWUo3Xiqddjgs8TOHtFb3cPVUQ3H0AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T21:07:29.383737Z"},"content_sha256":"aa97dc1a5a118945c5459b4fa61bacdf8be4ae348e2b952d7e160eb1487f4a0e","schema_version":"1.0","event_id":"sha256:aa97dc1a5a118945c5459b4fa61bacdf8be4ae348e2b952d7e160eb1487f4a0e"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:H6INDLDWF5GVBMZLV5AHJXU6FJ","target":"integrity","payload":{"note":"Identifier '10.1061/(asce)cp.1943-5487' is syntactically valid but the DOI registry (doi.org) returned 404, and Crossref / OpenAlex / internal corpus also have no record. The cited work could not be located through any authoritative source.","snippet":"N. Wang, R. R. Issa, C. J. Anumba, Nlp-based query-answering system for information extraction from building information models, Journal of comput- ing in civil engineering 36 (2022) 04022004. doi:10.1061/(ASCE)CP.1943-5487. 0001019","arxiv_id":"2605.13236","detector":"doi_compliance","evidence":{"doi":"10.1061/(asce)cp.1943-5487","arxiv_id":null,"ref_index":54,"raw_excerpt":"N. Wang, R. R. Issa, C. J. Anumba, Nlp-based query-answering system for information extraction from building information models, Journal of comput- ing in civil engineering 36 (2022) 04022004. doi:10.1061/(ASCE)CP.1943-5487. 0001019","verdict_class":"cross_source","checked_sources":["crossref_by_doi","openalex_by_doi","doi_org_head"]},"severity":"critical","ref_index":54,"audited_at":"2026-05-19T06:43:20.103387Z","event_type":"pith.integrity.v1","detected_doi":"10.1061/(asce)cp.1943-5487","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"unresolvable_identifier","evidence_hash":"6a788b8d3a1319b8939828ef0beafe5e41c0a8806a8d4d7dc684f03cf8e5d832","paper_version":1,"verdict_class":"cross_source","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":200,"payload_sha256":"98431b4e2b35fbd8cc2ef428045a485f7d84f828775e6e116d19488631e28523","signature_b64":"WsdRrKYM9v27bme5rF3qHZnpB9w5FvcoOxcSAIwv4WHSj+2QbGRTCc0kWwYJjEKRq7MNeus7h1o6/DSey3fwCA==","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":"2026-05-19T06:46:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XklALHRVQDPcGt8s3gJgqo/X95sdPQ7o15gjqI3Vz2dF43VJ/L19YcdCi4AIZN2dPGrlYZEjYLA5bn5vkFKtAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T21:07:29.384653Z"},"content_sha256":"3a6fe35891ba784691f5dd94dd919be451a4febe86b1ad148e6a034761730e6c","schema_version":"1.0","event_id":"sha256:3a6fe35891ba784691f5dd94dd919be451a4febe86b1ad148e6a034761730e6c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H6INDLDWF5GVBMZLV5AHJXU6FJ/bundle.json","state_url":"https://pith.science/pith/H6INDLDWF5GVBMZLV5AHJXU6FJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H6INDLDWF5GVBMZLV5AHJXU6FJ/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":"2026-05-21T21:07:29Z","links":{"resolver":"https://pith.science/pith/H6INDLDWF5GVBMZLV5AHJXU6FJ","bundle":"https://pith.science/pith/H6INDLDWF5GVBMZLV5AHJXU6FJ/bundle.json","state":"https://pith.science/pith/H6INDLDWF5GVBMZLV5AHJXU6FJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H6INDLDWF5GVBMZLV5AHJXU6FJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:H6INDLDWF5GVBMZLV5AHJXU6FJ","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":"c7cb25196997d81cf2c32c3d17cdf0197232fb6aff5adeb7a2f41a43a7729dfc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T09:24:51Z","title_canon_sha256":"fe79062cdf076f9644c3d32ed6cb8bca93db15e8b31c9e33624e587158396817"},"schema_version":"1.0","source":{"id":"2605.13236","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13236","created_at":"2026-05-18T02:44:49Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13236v1","created_at":"2026-05-18T02:44:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13236","created_at":"2026-05-18T02:44:49Z"},{"alias_kind":"pith_short_12","alias_value":"H6INDLDWF5GV","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"H6INDLDWF5GVBMZL","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"H6INDLDW","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:aa97dc1a5a118945c5459b4fa61bacdf8be4ae348e2b952d7e160eb1487f4a0e","target":"graph","created_at":"2026-05-18T02:44:49Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"combining complementary representations with iterative reasoning enables more accessible natural language querying of IFC data while supporting routine BIM analysis tasks."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The transformations to relational and graph representations preserve all information needed for accurate querying, and the LLM can reliably detect and correct its own errors through iteration without introducing new inaccuracies."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"IfcLLM combines relational and graph representations of IFC models with iterative LLM reasoning to deliver 93.3-100% first-attempt accuracy on natural language queries across three test models."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Transforming IFC models into relational tables and graphs lets an LLM answer natural language queries about building data with over 93 percent first-attempt accuracy."}],"snapshot_sha256":"34619d8f749ece0054e97d8c10d2ac3a088ea42cc80d0b2511adec8a18b329c1"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Building Information Modeling (BIM) is widely used in the Architecture, Engineering, and Construction (AEC) industry, but the complexity of Industry Foundation Classes (IFC) limits accessibility for non-expert users. To address this, we introduce IfcLLM, a hybrid framework for natural language interaction with IFC-based BIM models. It transforms IFC models into complementary representations: a relational representation for structured element properties and geometry, and a graph representation for topological relationships. These representations are integrated through iterative retry-and-refine","authors_text":"Haowen Xu, Johnson Xuesong Shen, Rabindra Lamsal, Sisi Zlatanova, Yafei Sun","cross_cats":[],"headline":"Transforming IFC models into relational tables and graphs lets an LLM answer natural language queries about building data with over 93 percent first-attempt accuracy.","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T09:24:51Z","title":"A Hybrid Framework for Natural Language Querying of IFC Models with Relational and Graph Representations"},"references":{"count":88,"internal_anchors":5,"resolved_work":88,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"C. M. Eastman, BIM handbook: A guide to building information modeling for owners, managers, designers, engineers and contractors, John Wiley & Sons,","work_id":"d7f157e6-aea4-4c8c-94d6-17b79db54573","year":null},{"cited_arxiv_id":"","doi":"10.1002/9781119287568","is_internal_anchor":false,"ref_index":2,"title":"doi:10.1002/9781119287568","work_id":"f5dd05ba-0949-493b-9504-14a66dd24c16","year":null},{"cited_arxiv_id":"","doi":"10.1016/j.autcon.2019.03.005","is_internal_anchor":false,"ref_index":3,"title":"H. Wang, Y. Pan, X. Luo, Integration of bim and gis in sustainable built environment: A review and bibliometric analysis, Automation in construction 103 (2019) 41–52. doi:10.1016/j.autcon.2019.03.005","work_id":"5d64fe89-6e66-4392-9e52-f530508e6336","year":2019},{"cited_arxiv_id":"","doi":"10.1016/j.landusepol.2021.105355","is_internal_anchor":false,"ref_index":4,"title":"A. Alattas, E. Kalogianni, T. Alzahrani, S. Zlatanova, P. van Oosterom, Map- ping private, common, and exclusive common spaces in buildings from bim/ifc to ladm. a case study from saudi arabia, Land U","work_id":"07f9ea1f-bce9-4e9e-8fc8-58cf9fdb40c3","year":2021},{"cited_arxiv_id":"","doi":"10.1016/j.autcon.2020.103436","is_internal_anchor":false,"ref_index":5,"title":"L. Liu, B. Li, S. Zlatanova, P. van Oosterom, Indoor navigation supported by the industry foundation classes (ifc): A survey, Automation in Construction 121 (2021) 103436. doi:10.1016/j.autcon.2020.10","work_id":"0be7e10e-8e5a-4a98-a75c-dfffef483b41","year":2021}],"snapshot_sha256":"a511d9246d67ab48b1054f9d279b8c13dd6e070419b0397adeacd3ba31664142"},"source":{"id":"2605.13236","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T19:10:11.336493Z","id":"77a86c08-06ea-4f6e-b33d-07d039a782b5","model_set":{"reader":"grok-4.3"},"one_line_summary":"IfcLLM combines relational and graph representations of IFC models with iterative LLM reasoning to deliver 93.3-100% first-attempt accuracy on natural language queries across three test models.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Transforming IFC models into relational tables and graphs lets an LLM answer natural language queries about building data with over 93 percent first-attempt accuracy.","strongest_claim":"combining complementary representations with iterative reasoning enables more accessible natural language querying of IFC data while supporting routine BIM analysis tasks.","weakest_assumption":"The transformations to relational and graph representations preserve all information needed for accurate querying, and the LLM can reliably detect and correct its own errors through iteration without introducing new inaccuracies."}},"verdict_id":"77a86c08-06ea-4f6e-b33d-07d039a782b5"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a208101db04789ea97433fe0182f2fd8c0f4abe24f2facc45543f6ee56ea59ce","target":"record","created_at":"2026-05-18T02:44:49Z","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":"c7cb25196997d81cf2c32c3d17cdf0197232fb6aff5adeb7a2f41a43a7729dfc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T09:24:51Z","title_canon_sha256":"fe79062cdf076f9644c3d32ed6cb8bca93db15e8b31c9e33624e587158396817"},"schema_version":"1.0","source":{"id":"2605.13236","kind":"arxiv","version":1}},"canonical_sha256":"3f90d1ac762f4d50b32baf4074de9e2a59841cc5921b97e36d03cacedc62688d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f90d1ac762f4d50b32baf4074de9e2a59841cc5921b97e36d03cacedc62688d","first_computed_at":"2026-05-18T02:44:49.545185Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:49.545185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6aK2CfQodQcwk3EUDuQci3pzeT3tiatOWgj85Ss5GbTrTaHh7LjlwcgKzdSHw9itgP7LAvU44ZnZvdMuIfuzDw==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:49.545713Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13236","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a208101db04789ea97433fe0182f2fd8c0f4abe24f2facc45543f6ee56ea59ce","sha256:aa97dc1a5a118945c5459b4fa61bacdf8be4ae348e2b952d7e160eb1487f4a0e","sha256:3a6fe35891ba784691f5dd94dd919be451a4febe86b1ad148e6a034761730e6c"],"state_sha256":"57be6956d428e410ac44f8e6ce630a3f7b031e1f8949b5d3afbd51b3a43b7e4f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iWgk4LdLu5iG/743xRJZByqWFtf1UFPeclsL6JdR4PqPgNywtJ6rwRBfUqCKdlnPoImLa5mD2CftzerNxOTyBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T21:07:29.387651Z","bundle_sha256":"a600ff0a2c76801fa1f187f4d49642f849de60eccd19479d9b585a7e741c660f"}}