{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WUQW62N4EBKWN6KO53CXVHQFIA","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":"6b7c054e5f51e736d24b1ab96dddebd28af2645596a41850479a84d78a6c2e20","cross_cats_sorted":["cs.AI","cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-17T14:25:45Z","title_canon_sha256":"e8247776d425e28227a5e573e9240f53c411800793801d401670c912cf4ab2ea"},"schema_version":"1.0","source":{"id":"2502.11829","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.11829","created_at":"2026-07-05T10:15:34Z"},{"alias_kind":"arxiv_version","alias_value":"2502.11829v1","created_at":"2026-07-05T10:15:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11829","created_at":"2026-07-05T10:15:34Z"},{"alias_kind":"pith_short_12","alias_value":"WUQW62N4EBKW","created_at":"2026-07-05T10:15:34Z"},{"alias_kind":"pith_short_16","alias_value":"WUQW62N4EBKWN6KO","created_at":"2026-07-05T10:15:34Z"},{"alias_kind":"pith_short_8","alias_value":"WUQW62N4","created_at":"2026-07-05T10:15:34Z"}],"graph_snapshots":[{"event_id":"sha256:9353b1f2f2e64855ebcd08756507b71081756bfc029ebb7b3b2faef7624f7d45","target":"graph","created_at":"2026-07-05T10:15:34Z","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/2502.11829/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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.","authors_text":"Hanbin Wang, Jingwei Song, Junting Lu, Kai Tian, Keyuan Cheng, Wenhui Hu, Xiaoxuan Zhou, Xueyang Liu, Yuxin Zuo, Zhipeng Xu","cross_cats":["cs.AI","cs.SE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-17T14:25:45Z","title":"Code-Vision: Evaluating Multimodal LLMs Logic Understanding and Code Generation Capabilities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11829","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:df680dbe9ede533fff37afba5fb8985595a6588327f88d9dc4f9d4796b026fd5","target":"record","created_at":"2026-07-05T10:15:34Z","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":"6b7c054e5f51e736d24b1ab96dddebd28af2645596a41850479a84d78a6c2e20","cross_cats_sorted":["cs.AI","cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-17T14:25:45Z","title_canon_sha256":"e8247776d425e28227a5e573e9240f53c411800793801d401670c912cf4ab2ea"},"schema_version":"1.0","source":{"id":"2502.11829","kind":"arxiv","version":1}},"canonical_sha256":"b5216f69bc205566f94eeec57a9e054018130ecf0adbd0090f7f23a8a3eedef2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b5216f69bc205566f94eeec57a9e054018130ecf0adbd0090f7f23a8a3eedef2","first_computed_at":"2026-07-05T10:15:34.807981Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:15:34.807981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LxMuY+hhuQkmWUb+HmvMJ8pNGqTn8eFwUd+MD+3HMi2dHFHsrnf/8iGgTVrYBIFKeBUQ+Reiirz60V75iCx0AA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:15:34.808473Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.11829","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df680dbe9ede533fff37afba5fb8985595a6588327f88d9dc4f9d4796b026fd5","sha256:9353b1f2f2e64855ebcd08756507b71081756bfc029ebb7b3b2faef7624f7d45"],"state_sha256":"10c5d0f98cad207544ce261100e69f795faa5c182069d79af036e08fecf17659"}