{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YOCWNIXQ3A5OE26S3HY422FL2L","short_pith_number":"pith:YOCWNIXQ","schema_version":"1.0","canonical_sha256":"c38566a2f0d83ae26bd2d9f1cd68abd2c000ea33f0d9a7ac81f2806e68c5d6e4","source":{"kind":"arxiv","id":"2507.19525","version":1},"attestation_state":"computed","paper":{"title":"MMCircuitEval: A Comprehensive Multimodal Circuit-Focused Benchmark for Evaluating LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chenchen Zhao, Chengjie Liu, Chenhao Xue, Chujie Chen, Guangyu Sun, Gwok-Waa Wan, Hefei Feng, Jun Yang, Ning Xu, Qiang Xu, Weiyu Chen, XiangYu Wen, Xin Cheng, Xi Wang, Yibo Lin, Yi Liu, Yinan Zhu, Ying Wang, Yongqi Fu, Yunhao Zhou, Yuxiang Zhao, Zhengyuan Shi","submitted_at":"2025-07-20T05:46:32Z","abstract_excerpt":"The emergence of multimodal large language models (MLLMs) presents promising opportunities for automation and enhancement in Electronic Design Automation (EDA). However, comprehensively evaluating these models in circuit design remains challenging due to the narrow scope of existing benchmarks. To bridge this gap, we introduce MMCircuitEval, the first multimodal benchmark specifically designed to assess MLLM performance comprehensively across diverse EDA tasks. MMCircuitEval comprises 3614 meticulously curated question-answer (QA) pairs spanning digital and analog circuits across critical EDA "},"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":"2507.19525","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-20T05:46:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ae1a94fde94efa793a97c97a9ff944ac5d6415884d6680470ddd5babc881a920","abstract_canon_sha256":"1aaa073ff59a839bdb55a657c9baae8746c824d3ec4df9c761d27ed2c39c5a59"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:35.815244Z","signature_b64":"dF2Gglp4E5ZpqfBVVSIN7ixdwARS0Y6FV1ks8gcfi2DKSXnDZ3oEgfz9YVSGgEKu65gqAN4HSWzgPeZ2rsEgDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c38566a2f0d83ae26bd2d9f1cd68abd2c000ea33f0d9a7ac81f2806e68c5d6e4","last_reissued_at":"2026-07-05T11:43:35.814770Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:35.814770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMCircuitEval: A Comprehensive Multimodal Circuit-Focused Benchmark for Evaluating LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chenchen Zhao, Chengjie Liu, Chenhao Xue, Chujie Chen, Guangyu Sun, Gwok-Waa Wan, Hefei Feng, Jun Yang, Ning Xu, Qiang Xu, Weiyu Chen, XiangYu Wen, Xin Cheng, Xi Wang, Yibo Lin, Yi Liu, Yinan Zhu, Ying Wang, Yongqi Fu, Yunhao Zhou, Yuxiang Zhao, Zhengyuan Shi","submitted_at":"2025-07-20T05:46:32Z","abstract_excerpt":"The emergence of multimodal large language models (MLLMs) presents promising opportunities for automation and enhancement in Electronic Design Automation (EDA). However, comprehensively evaluating these models in circuit design remains challenging due to the narrow scope of existing benchmarks. To bridge this gap, we introduce MMCircuitEval, the first multimodal benchmark specifically designed to assess MLLM performance comprehensively across diverse EDA tasks. MMCircuitEval comprises 3614 meticulously curated question-answer (QA) pairs spanning digital and analog circuits across critical EDA "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19525","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/2507.19525/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":"2507.19525","created_at":"2026-07-05T11:43:35.814823+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.19525v1","created_at":"2026-07-05T11:43:35.814823+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19525","created_at":"2026-07-05T11:43:35.814823+00:00"},{"alias_kind":"pith_short_12","alias_value":"YOCWNIXQ3A5O","created_at":"2026-07-05T11:43:35.814823+00:00"},{"alias_kind":"pith_short_16","alias_value":"YOCWNIXQ3A5OE26S","created_at":"2026-07-05T11:43:35.814823+00:00"},{"alias_kind":"pith_short_8","alias_value":"YOCWNIXQ","created_at":"2026-07-05T11:43:35.814823+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.15037","citing_title":"CircuChain: Disentangling Competence and Compliance in LLM Circuit Analysis","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YOCWNIXQ3A5OE26S3HY422FL2L","json":"https://pith.science/pith/YOCWNIXQ3A5OE26S3HY422FL2L.json","graph_json":"https://pith.science/api/pith-number/YOCWNIXQ3A5OE26S3HY422FL2L/graph.json","events_json":"https://pith.science/api/pith-number/YOCWNIXQ3A5OE26S3HY422FL2L/events.json","paper":"https://pith.science/paper/YOCWNIXQ"},"agent_actions":{"view_html":"https://pith.science/pith/YOCWNIXQ3A5OE26S3HY422FL2L","download_json":"https://pith.science/pith/YOCWNIXQ3A5OE26S3HY422FL2L.json","view_paper":"https://pith.science/paper/YOCWNIXQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.19525&json=true","fetch_graph":"https://pith.science/api/pith-number/YOCWNIXQ3A5OE26S3HY422FL2L/graph.json","fetch_events":"https://pith.science/api/pith-number/YOCWNIXQ3A5OE26S3HY422FL2L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YOCWNIXQ3A5OE26S3HY422FL2L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YOCWNIXQ3A5OE26S3HY422FL2L/action/storage_attestation","attest_author":"https://pith.science/pith/YOCWNIXQ3A5OE26S3HY422FL2L/action/author_attestation","sign_citation":"https://pith.science/pith/YOCWNIXQ3A5OE26S3HY422FL2L/action/citation_signature","submit_replication":"https://pith.science/pith/YOCWNIXQ3A5OE26S3HY422FL2L/action/replication_record"}},"created_at":"2026-07-05T11:43:35.814823+00:00","updated_at":"2026-07-05T11:43:35.814823+00:00"}