{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BJ6RHKS3BO674UICNJRYQLTDIQ","short_pith_number":"pith:BJ6RHKS3","schema_version":"1.0","canonical_sha256":"0a7d13aa5b0bbdfe51026a63882e63443390c180403c9fd043a0a50dd9d43fe2","source":{"kind":"arxiv","id":"2508.13833","version":1},"attestation_state":"computed","paper":{"title":"Extracting Structured Requirements from Unstructured Building Technical Specifications for Building Information Modeling","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Insaf Nahri, Mathieu Thorel, Nicolas Bus, Philippe V\\'eron, Romain Pinqui\\'e","submitted_at":"2025-08-19T13:55:41Z","abstract_excerpt":"This study explores the integration of Building Information Modeling (BIM) with Natural Language Processing (NLP) to automate the extraction of requirements from unstructured French Building Technical Specification (BTS) documents within the construction industry. Employing Named Entity Recognition (NER) and Relation Extraction (RE) techniques, the study leverages the transformer-based model CamemBERT and applies transfer learning with the French language model Fr\\_core\\_news\\_lg, both pre-trained on a large French corpus in the general domain. To benchmark these models, additional approaches "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2508.13833","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-19T13:55:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e8afb1623450e095516fade072232974572cfbfa7c04befe55880c9e46519d59","abstract_canon_sha256":"1d152e0a984e6c94a9ff730676fab5581b5dbac3b64671f6ce582d5b90cea04e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:08.347824Z","signature_b64":"nO95boaWrYC2mbllCxHoTqMBt2YCVXMd5WloMUffnxZ625VKdHsx3yFuTwYds1fVPkxi0xU0HPJxWv1UQuktAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a7d13aa5b0bbdfe51026a63882e63443390c180403c9fd043a0a50dd9d43fe2","last_reissued_at":"2026-07-05T11:56:08.347389Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:08.347389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Extracting Structured Requirements from Unstructured Building Technical Specifications for Building Information Modeling","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Insaf Nahri, Mathieu Thorel, Nicolas Bus, Philippe V\\'eron, Romain Pinqui\\'e","submitted_at":"2025-08-19T13:55:41Z","abstract_excerpt":"This study explores the integration of Building Information Modeling (BIM) with Natural Language Processing (NLP) to automate the extraction of requirements from unstructured French Building Technical Specification (BTS) documents within the construction industry. Employing Named Entity Recognition (NER) and Relation Extraction (RE) techniques, the study leverages the transformer-based model CamemBERT and applies transfer learning with the French language model Fr\\_core\\_news\\_lg, both pre-trained on a large French corpus in the general domain. To benchmark these models, additional approaches "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.13833","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/2508.13833/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2508.13833","created_at":"2026-07-05T11:56:08.347447+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.13833v1","created_at":"2026-07-05T11:56:08.347447+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.13833","created_at":"2026-07-05T11:56:08.347447+00:00"},{"alias_kind":"pith_short_12","alias_value":"BJ6RHKS3BO67","created_at":"2026-07-05T11:56:08.347447+00:00"},{"alias_kind":"pith_short_16","alias_value":"BJ6RHKS3BO674UIC","created_at":"2026-07-05T11:56:08.347447+00:00"},{"alias_kind":"pith_short_8","alias_value":"BJ6RHKS3","created_at":"2026-07-05T11:56:08.347447+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BJ6RHKS3BO674UICNJRYQLTDIQ","json":"https://pith.science/pith/BJ6RHKS3BO674UICNJRYQLTDIQ.json","graph_json":"https://pith.science/api/pith-number/BJ6RHKS3BO674UICNJRYQLTDIQ/graph.json","events_json":"https://pith.science/api/pith-number/BJ6RHKS3BO674UICNJRYQLTDIQ/events.json","paper":"https://pith.science/paper/BJ6RHKS3"},"agent_actions":{"view_html":"https://pith.science/pith/BJ6RHKS3BO674UICNJRYQLTDIQ","download_json":"https://pith.science/pith/BJ6RHKS3BO674UICNJRYQLTDIQ.json","view_paper":"https://pith.science/paper/BJ6RHKS3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.13833&json=true","fetch_graph":"https://pith.science/api/pith-number/BJ6RHKS3BO674UICNJRYQLTDIQ/graph.json","fetch_events":"https://pith.science/api/pith-number/BJ6RHKS3BO674UICNJRYQLTDIQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BJ6RHKS3BO674UICNJRYQLTDIQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BJ6RHKS3BO674UICNJRYQLTDIQ/action/storage_attestation","attest_author":"https://pith.science/pith/BJ6RHKS3BO674UICNJRYQLTDIQ/action/author_attestation","sign_citation":"https://pith.science/pith/BJ6RHKS3BO674UICNJRYQLTDIQ/action/citation_signature","submit_replication":"https://pith.science/pith/BJ6RHKS3BO674UICNJRYQLTDIQ/action/replication_record"}},"created_at":"2026-07-05T11:56:08.347447+00:00","updated_at":"2026-07-05T11:56:08.347447+00:00"}