{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WUQW62N4EBKWN6KO53CXVHQFIA","short_pith_number":"pith:WUQW62N4","schema_version":"1.0","canonical_sha256":"b5216f69bc205566f94eeec57a9e054018130ecf0adbd0090f7f23a8a3eedef2","source":{"kind":"arxiv","id":"2502.11829","version":1},"attestation_state":"computed","paper":{"title":"Code-Vision: Evaluating Multimodal LLMs Logic Understanding and Code Generation Capabilities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.CL","authors_text":"Hanbin Wang, Jingwei Song, Junting Lu, Kai Tian, Keyuan Cheng, Wenhui Hu, Xiaoxuan Zhou, Xueyang Liu, Yuxin Zuo, Zhipeng Xu","submitted_at":"2025-02-17T14:25:45Z","abstract_excerpt":"This paper introduces Code-Vision, a benchmark designed to evaluate the logical understanding and code generation capabilities of Multimodal Large Language Models (MLLMs). It challenges MLLMs to generate a correct program that fulfills specific functionality requirements based on a given flowchart, which visually represents the desired algorithm or process. Code-Vision comprises three subsets: HumanEval-V, Algorithm, and MATH, which evaluate MLLMs' coding abilities across basic programming, algorithmic, and mathematical problem-solving domains. Our experiments evaluate 12 MLLMs on Code-Vision."},"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":"2502.11829","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-17T14:25:45Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"e8247776d425e28227a5e573e9240f53c411800793801d401670c912cf4ab2ea","abstract_canon_sha256":"6b7c054e5f51e736d24b1ab96dddebd28af2645596a41850479a84d78a6c2e20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:34.808473Z","signature_b64":"LxMuY+hhuQkmWUb+HmvMJ8pNGqTn8eFwUd+MD+3HMi2dHFHsrnf/8iGgTVrYBIFKeBUQ+Reiirz60V75iCx0AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5216f69bc205566f94eeec57a9e054018130ecf0adbd0090f7f23a8a3eedef2","last_reissued_at":"2026-07-05T10:15:34.807981Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:34.807981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Code-Vision: Evaluating Multimodal LLMs Logic Understanding and Code Generation Capabilities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.CL","authors_text":"Hanbin Wang, Jingwei Song, Junting Lu, Kai Tian, Keyuan Cheng, Wenhui Hu, Xiaoxuan Zhou, Xueyang Liu, Yuxin Zuo, Zhipeng Xu","submitted_at":"2025-02-17T14:25:45Z","abstract_excerpt":"This paper introduces Code-Vision, a benchmark designed to evaluate the logical understanding and code generation capabilities of Multimodal Large Language Models (MLLMs). It challenges MLLMs to generate a correct program that fulfills specific functionality requirements based on a given flowchart, which visually represents the desired algorithm or process. Code-Vision comprises three subsets: HumanEval-V, Algorithm, and MATH, which evaluate MLLMs' coding abilities across basic programming, algorithmic, and mathematical problem-solving domains. Our experiments evaluate 12 MLLMs on Code-Vision."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11829","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/2502.11829/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":"2502.11829","created_at":"2026-07-05T10:15:34.808034+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.11829v1","created_at":"2026-07-05T10:15:34.808034+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11829","created_at":"2026-07-05T10:15:34.808034+00:00"},{"alias_kind":"pith_short_12","alias_value":"WUQW62N4EBKW","created_at":"2026-07-05T10:15:34.808034+00:00"},{"alias_kind":"pith_short_16","alias_value":"WUQW62N4EBKWN6KO","created_at":"2026-07-05T10:15:34.808034+00:00"},{"alias_kind":"pith_short_8","alias_value":"WUQW62N4","created_at":"2026-07-05T10:15:34.808034+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03378","citing_title":"Neural Change Prediction: Relating Software Changes to Their Effects and Vice Versa","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08089","citing_title":"GALA: Multimodal Graph Alignment for Bug Localization in Automated Program Repair","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WUQW62N4EBKWN6KO53CXVHQFIA","json":"https://pith.science/pith/WUQW62N4EBKWN6KO53CXVHQFIA.json","graph_json":"https://pith.science/api/pith-number/WUQW62N4EBKWN6KO53CXVHQFIA/graph.json","events_json":"https://pith.science/api/pith-number/WUQW62N4EBKWN6KO53CXVHQFIA/events.json","paper":"https://pith.science/paper/WUQW62N4"},"agent_actions":{"view_html":"https://pith.science/pith/WUQW62N4EBKWN6KO53CXVHQFIA","download_json":"https://pith.science/pith/WUQW62N4EBKWN6KO53CXVHQFIA.json","view_paper":"https://pith.science/paper/WUQW62N4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.11829&json=true","fetch_graph":"https://pith.science/api/pith-number/WUQW62N4EBKWN6KO53CXVHQFIA/graph.json","fetch_events":"https://pith.science/api/pith-number/WUQW62N4EBKWN6KO53CXVHQFIA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WUQW62N4EBKWN6KO53CXVHQFIA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WUQW62N4EBKWN6KO53CXVHQFIA/action/storage_attestation","attest_author":"https://pith.science/pith/WUQW62N4EBKWN6KO53CXVHQFIA/action/author_attestation","sign_citation":"https://pith.science/pith/WUQW62N4EBKWN6KO53CXVHQFIA/action/citation_signature","submit_replication":"https://pith.science/pith/WUQW62N4EBKWN6KO53CXVHQFIA/action/replication_record"}},"created_at":"2026-07-05T10:15:34.808034+00:00","updated_at":"2026-07-05T10:15:34.808034+00:00"}