{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VSJXIMP7FBDIRPR5EK2Z7QFE5P","short_pith_number":"pith:VSJXIMP7","schema_version":"1.0","canonical_sha256":"ac937431ff284688be3d22b59fc0a4ebfdac25ba697ef3d77fd49cbd618ed192","source":{"kind":"arxiv","id":"2404.07917","version":2},"attestation_state":"computed","paper":{"title":"DesignQA: A Multimodal Benchmark for Evaluating Large Language Models' Understanding of Engineering Documentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Anna C. Doris, Daniele Grandi, Faez Ahmed, Hyunmin Cheong, Md Ferdous Alam, Mohammadmehdi Ataei, Ryan Tomich","submitted_at":"2024-04-11T16:59:54Z","abstract_excerpt":"This research introduces DesignQA, a novel benchmark aimed at evaluating the proficiency of multimodal large language models (MLLMs) in comprehending and applying engineering requirements in technical documentation. Developed with a focus on real-world engineering challenges, DesignQA uniquely combines multimodal data-including textual design requirements, CAD images, and engineering drawings-derived from the Formula SAE student competition. Different from many existing MLLM benchmarks, DesignQA contains document-grounded visual questions where the input image and input document come from diff"},"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":"2404.07917","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-04-11T16:59:54Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"6287fb813e40377e14452d5d87089de5f19970076c04e8a5819c1038c1708411","abstract_canon_sha256":"49a05ebd3016e7c269eb5074c30e2510825e0a5a2a1e77e7047c6b0c8d7ff66c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:58:23.748452Z","signature_b64":"e0tABH7roX1qJuEBGBeJ4zjp+z9JiuNLN6W2zj3rZz/VR8hoFMe58pxvlkbPVGlRLonNm8jyf7CkD+55AAnrDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac937431ff284688be3d22b59fc0a4ebfdac25ba697ef3d77fd49cbd618ed192","last_reissued_at":"2026-07-05T08:58:23.747988Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:58:23.747988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DesignQA: A Multimodal Benchmark for Evaluating Large Language Models' Understanding of Engineering Documentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Anna C. Doris, Daniele Grandi, Faez Ahmed, Hyunmin Cheong, Md Ferdous Alam, Mohammadmehdi Ataei, Ryan Tomich","submitted_at":"2024-04-11T16:59:54Z","abstract_excerpt":"This research introduces DesignQA, a novel benchmark aimed at evaluating the proficiency of multimodal large language models (MLLMs) in comprehending and applying engineering requirements in technical documentation. Developed with a focus on real-world engineering challenges, DesignQA uniquely combines multimodal data-including textual design requirements, CAD images, and engineering drawings-derived from the Formula SAE student competition. Different from many existing MLLM benchmarks, DesignQA contains document-grounded visual questions where the input image and input document come from diff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07917","kind":"arxiv","version":2},"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/2404.07917/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":"2404.07917","created_at":"2026-07-05T08:58:23.748042+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.07917v2","created_at":"2026-07-05T08:58:23.748042+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07917","created_at":"2026-07-05T08:58:23.748042+00:00"},{"alias_kind":"pith_short_12","alias_value":"VSJXIMP7FBDI","created_at":"2026-07-05T08:58:23.748042+00:00"},{"alias_kind":"pith_short_16","alias_value":"VSJXIMP7FBDIRPR5","created_at":"2026-07-05T08:58:23.748042+00:00"},{"alias_kind":"pith_short_8","alias_value":"VSJXIMP7","created_at":"2026-07-05T08:58:23.748042+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29399","citing_title":"LLM-Guided Planning for Multi-hop Reasoning over Multimodal Nuclear Regulatory Documents","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VSJXIMP7FBDIRPR5EK2Z7QFE5P","json":"https://pith.science/pith/VSJXIMP7FBDIRPR5EK2Z7QFE5P.json","graph_json":"https://pith.science/api/pith-number/VSJXIMP7FBDIRPR5EK2Z7QFE5P/graph.json","events_json":"https://pith.science/api/pith-number/VSJXIMP7FBDIRPR5EK2Z7QFE5P/events.json","paper":"https://pith.science/paper/VSJXIMP7"},"agent_actions":{"view_html":"https://pith.science/pith/VSJXIMP7FBDIRPR5EK2Z7QFE5P","download_json":"https://pith.science/pith/VSJXIMP7FBDIRPR5EK2Z7QFE5P.json","view_paper":"https://pith.science/paper/VSJXIMP7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.07917&json=true","fetch_graph":"https://pith.science/api/pith-number/VSJXIMP7FBDIRPR5EK2Z7QFE5P/graph.json","fetch_events":"https://pith.science/api/pith-number/VSJXIMP7FBDIRPR5EK2Z7QFE5P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VSJXIMP7FBDIRPR5EK2Z7QFE5P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VSJXIMP7FBDIRPR5EK2Z7QFE5P/action/storage_attestation","attest_author":"https://pith.science/pith/VSJXIMP7FBDIRPR5EK2Z7QFE5P/action/author_attestation","sign_citation":"https://pith.science/pith/VSJXIMP7FBDIRPR5EK2Z7QFE5P/action/citation_signature","submit_replication":"https://pith.science/pith/VSJXIMP7FBDIRPR5EK2Z7QFE5P/action/replication_record"}},"created_at":"2026-07-05T08:58:23.748042+00:00","updated_at":"2026-07-05T08:58:23.748042+00:00"}