{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YY7RDGARVYA6ZO3QF5X3RDATBA","short_pith_number":"pith:YY7RDGAR","schema_version":"1.0","canonical_sha256":"c63f119811ae01ecbb702f6fb88c1308319b5552c394daeaf897b08ea705d4c5","source":{"kind":"arxiv","id":"2411.01492","version":2},"attestation_state":"computed","paper":{"title":"EEE-Bench: A Comprehensive Multimodal Electrical And Electronics Engineering Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jike Zhong, Konstantinos Psounis, Ming Li, Tianle Chen, Yuxiang Lai","submitted_at":"2024-11-03T09:17:56Z","abstract_excerpt":"Recent studies on large language models (LLMs) and large multimodal models (LMMs) have demonstrated promising skills in various domains including science and mathematics. However, their capability in more challenging and real-world related scenarios like engineering has not been systematically studied. To bridge this gap, we propose EEE-Bench, a multimodal benchmark aimed at assessing LMMs' capabilities in solving practical engineering tasks, using electrical and electronics engineering (EEE) as the testbed. Our benchmark consists of 2860 carefully curated problems spanning 10 essential subdom"},"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":"2411.01492","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-03T09:17:56Z","cross_cats_sorted":[],"title_canon_sha256":"7b1259493f05c9f77f06b7a9823b979ed99e9a78a63985d9f481e1a61e4cb8ab","abstract_canon_sha256":"5e36dfb480f935b9e7bb6081405baa84b98c08da3b24312b68c11bb671945caf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:20:41.584808Z","signature_b64":"SYyxBMPVTy+jv5vohPy6JxUWZdOJ++6k8rvWgO8Yk8u+h0YDV0XQxpdrNwVOL9wMYtLaWaGHie7gVSdiktReAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c63f119811ae01ecbb702f6fb88c1308319b5552c394daeaf897b08ea705d4c5","last_reissued_at":"2026-07-05T10:20:41.584267Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:20:41.584267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EEE-Bench: A Comprehensive Multimodal Electrical And Electronics Engineering Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jike Zhong, Konstantinos Psounis, Ming Li, Tianle Chen, Yuxiang Lai","submitted_at":"2024-11-03T09:17:56Z","abstract_excerpt":"Recent studies on large language models (LLMs) and large multimodal models (LMMs) have demonstrated promising skills in various domains including science and mathematics. However, their capability in more challenging and real-world related scenarios like engineering has not been systematically studied. To bridge this gap, we propose EEE-Bench, a multimodal benchmark aimed at assessing LMMs' capabilities in solving practical engineering tasks, using electrical and electronics engineering (EEE) as the testbed. Our benchmark consists of 2860 carefully curated problems spanning 10 essential subdom"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.01492","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/2411.01492/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":"2411.01492","created_at":"2026-07-05T10:20:41.584343+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.01492v2","created_at":"2026-07-05T10:20:41.584343+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.01492","created_at":"2026-07-05T10:20:41.584343+00:00"},{"alias_kind":"pith_short_12","alias_value":"YY7RDGARVYA6","created_at":"2026-07-05T10:20:41.584343+00:00"},{"alias_kind":"pith_short_16","alias_value":"YY7RDGARVYA6ZO3Q","created_at":"2026-07-05T10:20:41.584343+00:00"},{"alias_kind":"pith_short_8","alias_value":"YY7RDGAR","created_at":"2026-07-05T10:20:41.584343+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.17677","citing_title":"EngiBench: A Benchmark for Evaluating Large Language Models on Engineering Problem Solving","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YY7RDGARVYA6ZO3QF5X3RDATBA","json":"https://pith.science/pith/YY7RDGARVYA6ZO3QF5X3RDATBA.json","graph_json":"https://pith.science/api/pith-number/YY7RDGARVYA6ZO3QF5X3RDATBA/graph.json","events_json":"https://pith.science/api/pith-number/YY7RDGARVYA6ZO3QF5X3RDATBA/events.json","paper":"https://pith.science/paper/YY7RDGAR"},"agent_actions":{"view_html":"https://pith.science/pith/YY7RDGARVYA6ZO3QF5X3RDATBA","download_json":"https://pith.science/pith/YY7RDGARVYA6ZO3QF5X3RDATBA.json","view_paper":"https://pith.science/paper/YY7RDGAR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.01492&json=true","fetch_graph":"https://pith.science/api/pith-number/YY7RDGARVYA6ZO3QF5X3RDATBA/graph.json","fetch_events":"https://pith.science/api/pith-number/YY7RDGARVYA6ZO3QF5X3RDATBA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YY7RDGARVYA6ZO3QF5X3RDATBA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YY7RDGARVYA6ZO3QF5X3RDATBA/action/storage_attestation","attest_author":"https://pith.science/pith/YY7RDGARVYA6ZO3QF5X3RDATBA/action/author_attestation","sign_citation":"https://pith.science/pith/YY7RDGARVYA6ZO3QF5X3RDATBA/action/citation_signature","submit_replication":"https://pith.science/pith/YY7RDGARVYA6ZO3QF5X3RDATBA/action/replication_record"}},"created_at":"2026-07-05T10:20:41.584343+00:00","updated_at":"2026-07-05T10:20:41.584343+00:00"}