{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:H5OKPFXEYYRYEPXY6BS32IIMKJ","short_pith_number":"pith:H5OKPFXE","schema_version":"1.0","canonical_sha256":"3f5ca796e4c623823ef8f065bd210c5275886cda8c7c0efb3b8f3870c92f9342","source":{"kind":"arxiv","id":"2508.05676","version":1},"attestation_state":"computed","paper":{"title":"Domain-Specific Fine-Tuning and Prompt-Based Learning: A Comparative Study for developing Natural Language-Based BIM Information Retrieval Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Botao Zhong, Hanbin Luo, Han Gao, Kai Lia, Timo Hartmann","submitted_at":"2025-08-05T08:51:51Z","abstract_excerpt":"Building Information Modeling (BIM) is essential for managing building data across the entire lifecycle, supporting tasks from design to maintenance. Natural Language Interface (NLI) systems are increasingly explored as user-friendly tools for information retrieval in Building Information Modeling (BIM) environments. Despite their potential, accurately extracting BIM-related data through natural language queries remains a persistent challenge due to the complexity use queries and specificity of domain knowledge. This study presents a comparative analysis of two prominent approaches for develop"},"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":"2508.05676","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-08-05T08:51:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a7a6160d96fb126e24505283fddc71561d9507f6aef48e8cf71be17cb90cb76b","abstract_canon_sha256":"c4ca72030d9dd724992657104b8e9e569024b69e5712513d297439f6ba556ecd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:41.366534Z","signature_b64":"bNQqS53B+sV5qPe6O5q44lXT4bwtcc/VK0qPTkpIZj66szGVTAx81NjFS1RXVZTsJGFPLvzV/8VZj+NhNI6YDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f5ca796e4c623823ef8f065bd210c5275886cda8c7c0efb3b8f3870c92f9342","last_reissued_at":"2026-07-05T11:50:41.366014Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:41.366014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Domain-Specific Fine-Tuning and Prompt-Based Learning: A Comparative Study for developing Natural Language-Based BIM Information Retrieval Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Botao Zhong, Hanbin Luo, Han Gao, Kai Lia, Timo Hartmann","submitted_at":"2025-08-05T08:51:51Z","abstract_excerpt":"Building Information Modeling (BIM) is essential for managing building data across the entire lifecycle, supporting tasks from design to maintenance. Natural Language Interface (NLI) systems are increasingly explored as user-friendly tools for information retrieval in Building Information Modeling (BIM) environments. Despite their potential, accurately extracting BIM-related data through natural language queries remains a persistent challenge due to the complexity use queries and specificity of domain knowledge. This study presents a comparative analysis of two prominent approaches for develop"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.05676","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/2508.05676/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":"2508.05676","created_at":"2026-07-05T11:50:41.366080+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.05676v1","created_at":"2026-07-05T11:50:41.366080+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.05676","created_at":"2026-07-05T11:50:41.366080+00:00"},{"alias_kind":"pith_short_12","alias_value":"H5OKPFXEYYRY","created_at":"2026-07-05T11:50:41.366080+00:00"},{"alias_kind":"pith_short_16","alias_value":"H5OKPFXEYYRYEPXY","created_at":"2026-07-05T11:50:41.366080+00:00"},{"alias_kind":"pith_short_8","alias_value":"H5OKPFXE","created_at":"2026-07-05T11:50:41.366080+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01698","citing_title":"BIM Information Extraction Through LLM-based Adaptive Exploration","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H5OKPFXEYYRYEPXY6BS32IIMKJ","json":"https://pith.science/pith/H5OKPFXEYYRYEPXY6BS32IIMKJ.json","graph_json":"https://pith.science/api/pith-number/H5OKPFXEYYRYEPXY6BS32IIMKJ/graph.json","events_json":"https://pith.science/api/pith-number/H5OKPFXEYYRYEPXY6BS32IIMKJ/events.json","paper":"https://pith.science/paper/H5OKPFXE"},"agent_actions":{"view_html":"https://pith.science/pith/H5OKPFXEYYRYEPXY6BS32IIMKJ","download_json":"https://pith.science/pith/H5OKPFXEYYRYEPXY6BS32IIMKJ.json","view_paper":"https://pith.science/paper/H5OKPFXE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.05676&json=true","fetch_graph":"https://pith.science/api/pith-number/H5OKPFXEYYRYEPXY6BS32IIMKJ/graph.json","fetch_events":"https://pith.science/api/pith-number/H5OKPFXEYYRYEPXY6BS32IIMKJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H5OKPFXEYYRYEPXY6BS32IIMKJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H5OKPFXEYYRYEPXY6BS32IIMKJ/action/storage_attestation","attest_author":"https://pith.science/pith/H5OKPFXEYYRYEPXY6BS32IIMKJ/action/author_attestation","sign_citation":"https://pith.science/pith/H5OKPFXEYYRYEPXY6BS32IIMKJ/action/citation_signature","submit_replication":"https://pith.science/pith/H5OKPFXEYYRYEPXY6BS32IIMKJ/action/replication_record"}},"created_at":"2026-07-05T11:50:41.366080+00:00","updated_at":"2026-07-05T11:50:41.366080+00:00"}