{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:KFHYUYZOEJL7RQ6RRCUT54OEAG","short_pith_number":"pith:KFHYUYZO","canonical_record":{"source":{"id":"2508.16081","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-22T04:14:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6b58d8a2df57c8757defc31e93bbe7bdb7125df72d2a29c2dc3e47c73e92c3e1","abstract_canon_sha256":"2d72ef634fed55d911d079ab5c4231c0392e628a3229a04f241340b24d4e0256"},"schema_version":"1.0"},"canonical_sha256":"514f8a632e2257f8c3d188a93ef1c401a27d9c5c7c896d3319c715d14cc66cc4","source":{"kind":"arxiv","id":"2508.16081","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.16081","created_at":"2026-07-05T11:57:41Z"},{"alias_kind":"arxiv_version","alias_value":"2508.16081v1","created_at":"2026-07-05T11:57:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.16081","created_at":"2026-07-05T11:57:41Z"},{"alias_kind":"pith_short_12","alias_value":"KFHYUYZOEJL7","created_at":"2026-07-05T11:57:41Z"},{"alias_kind":"pith_short_16","alias_value":"KFHYUYZOEJL7RQ6R","created_at":"2026-07-05T11:57:41Z"},{"alias_kind":"pith_short_8","alias_value":"KFHYUYZO","created_at":"2026-07-05T11:57:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:KFHYUYZOEJL7RQ6RRCUT54OEAG","target":"record","payload":{"canonical_record":{"source":{"id":"2508.16081","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-22T04:14:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6b58d8a2df57c8757defc31e93bbe7bdb7125df72d2a29c2dc3e47c73e92c3e1","abstract_canon_sha256":"2d72ef634fed55d911d079ab5c4231c0392e628a3229a04f241340b24d4e0256"},"schema_version":"1.0"},"canonical_sha256":"514f8a632e2257f8c3d188a93ef1c401a27d9c5c7c896d3319c715d14cc66cc4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:57:41.609322Z","signature_b64":"71CZQiz/gY3hrwqctMvoB6l++sFrWG/iR8Tbv7wsdmCv8VQ+tBj6nyvO9M59YvSu/UUSVRZA4KHk3gw98Q6RAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"514f8a632e2257f8c3d188a93ef1c401a27d9c5c7c896d3319c715d14cc66cc4","last_reissued_at":"2026-07-05T11:57:41.608824Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:57:41.608824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.16081","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":"2026-07-05T11:57:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5cbkU7Z5GmYsXvm1IK5OvUATozl/xVkXI9UNsxCKoclZ/sMEyIiaDbACMr3+NEmtehqLRngPVLSEHKK22aPcCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T19:00:22.446722Z"},"content_sha256":"fb3ee8d51143d702745e9fa83735ebc1eb26bd7790f2e7815b36396ae1eb083a","schema_version":"1.0","event_id":"sha256:fb3ee8d51143d702745e9fa83735ebc1eb26bd7790f2e7815b36396ae1eb083a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:KFHYUYZOEJL7RQ6RRCUT54OEAG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CEQuest: Benchmarking Large Language Models for Construction Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Lufan Wang, Rui Liu, Yanzhao Wu","submitted_at":"2025-08-22T04:14:20Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of general-domain tasks. However, their effectiveness in specialized fields, such as construction, remains underexplored. In this paper, we introduce CEQuest, a novel benchmark dataset specifically designed to evaluate the performance of LLMs in answering construction-related questions, particularly in the areas of construction drawing interpretation and estimation. We conduct comprehensive experiments using five state-of-the-art LLMs, including Gemma 3, Phi4, LLaVA, Llama 3.3, and GPT-4.1, and evaluate "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.16081","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/2508.16081/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":"2026-07-05T11:57:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nV6uxrbLGVjbcXyB5UOl2CIUmvnVwPc4i5ZH9t9aXOdP0DnCdDYukM3QL7W5aK2KuG6xUqSWtZ4yHRy/kZOABQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T19:00:22.447378Z"},"content_sha256":"51a33d113a4ade9c14ca37d9519dec64912c710dd5c46fb38d8215dcc04c30d1","schema_version":"1.0","event_id":"sha256:51a33d113a4ade9c14ca37d9519dec64912c710dd5c46fb38d8215dcc04c30d1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KFHYUYZOEJL7RQ6RRCUT54OEAG/bundle.json","state_url":"https://pith.science/pith/KFHYUYZOEJL7RQ6RRCUT54OEAG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KFHYUYZOEJL7RQ6RRCUT54OEAG/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":"2026-08-21T19:00:22Z","links":{"resolver":"https://pith.science/pith/KFHYUYZOEJL7RQ6RRCUT54OEAG","bundle":"https://pith.science/pith/KFHYUYZOEJL7RQ6RRCUT54OEAG/bundle.json","state":"https://pith.science/pith/KFHYUYZOEJL7RQ6RRCUT54OEAG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KFHYUYZOEJL7RQ6RRCUT54OEAG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KFHYUYZOEJL7RQ6RRCUT54OEAG","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":"2d72ef634fed55d911d079ab5c4231c0392e628a3229a04f241340b24d4e0256","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-22T04:14:20Z","title_canon_sha256":"6b58d8a2df57c8757defc31e93bbe7bdb7125df72d2a29c2dc3e47c73e92c3e1"},"schema_version":"1.0","source":{"id":"2508.16081","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.16081","created_at":"2026-07-05T11:57:41Z"},{"alias_kind":"arxiv_version","alias_value":"2508.16081v1","created_at":"2026-07-05T11:57:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.16081","created_at":"2026-07-05T11:57:41Z"},{"alias_kind":"pith_short_12","alias_value":"KFHYUYZOEJL7","created_at":"2026-07-05T11:57:41Z"},{"alias_kind":"pith_short_16","alias_value":"KFHYUYZOEJL7RQ6R","created_at":"2026-07-05T11:57:41Z"},{"alias_kind":"pith_short_8","alias_value":"KFHYUYZO","created_at":"2026-07-05T11:57:41Z"}],"graph_snapshots":[{"event_id":"sha256:51a33d113a4ade9c14ca37d9519dec64912c710dd5c46fb38d8215dcc04c30d1","target":"graph","created_at":"2026-07-05T11:57:41Z","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/2508.16081/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of general-domain tasks. However, their effectiveness in specialized fields, such as construction, remains underexplored. In this paper, we introduce CEQuest, a novel benchmark dataset specifically designed to evaluate the performance of LLMs in answering construction-related questions, particularly in the areas of construction drawing interpretation and estimation. We conduct comprehensive experiments using five state-of-the-art LLMs, including Gemma 3, Phi4, LLaVA, Llama 3.3, and GPT-4.1, and evaluate ","authors_text":"Lufan Wang, Rui Liu, Yanzhao Wu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-22T04:14:20Z","title":"CEQuest: Benchmarking Large Language Models for Construction Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.16081","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:fb3ee8d51143d702745e9fa83735ebc1eb26bd7790f2e7815b36396ae1eb083a","target":"record","created_at":"2026-07-05T11:57:41Z","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":"2d72ef634fed55d911d079ab5c4231c0392e628a3229a04f241340b24d4e0256","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-22T04:14:20Z","title_canon_sha256":"6b58d8a2df57c8757defc31e93bbe7bdb7125df72d2a29c2dc3e47c73e92c3e1"},"schema_version":"1.0","source":{"id":"2508.16081","kind":"arxiv","version":1}},"canonical_sha256":"514f8a632e2257f8c3d188a93ef1c401a27d9c5c7c896d3319c715d14cc66cc4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"514f8a632e2257f8c3d188a93ef1c401a27d9c5c7c896d3319c715d14cc66cc4","first_computed_at":"2026-07-05T11:57:41.608824Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:57:41.608824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"71CZQiz/gY3hrwqctMvoB6l++sFrWG/iR8Tbv7wsdmCv8VQ+tBj6nyvO9M59YvSu/UUSVRZA4KHk3gw98Q6RAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:57:41.609322Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.16081","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb3ee8d51143d702745e9fa83735ebc1eb26bd7790f2e7815b36396ae1eb083a","sha256:51a33d113a4ade9c14ca37d9519dec64912c710dd5c46fb38d8215dcc04c30d1"],"state_sha256":"217a2ba4d6eea82134e08a083ebdd85f1a79c241ee9f98e205190af55e40d73c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XHF1sehuZsXUPoAV/kmU+XNwcCSisuaDBA4OzFNMP2rE18ZcMjcf2kFCdvk+0fqQlX1Zs3cM9dSWnojcLNivAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T19:00:22.452182Z","bundle_sha256":"b3a70e322806b622d91061a72c853bdd4b6147c44021e5941e4b05c99161547f"}}