{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:O6AZVFVZM2SF6H3VVC5PZJ5533","short_pith_number":"pith:O6AZVFVZ","schema_version":"1.0","canonical_sha256":"77819a96b966a45f1f75a8bafca7bddec26c7098ee0da18268bbfdbaad68a2cf","source":{"kind":"arxiv","id":"2506.02073","version":1},"attestation_state":"computed","paper":{"title":"Flow2Code: Evaluating Large Language Models for Flowchart-based Code Generation Capability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Aimin Zhou, Jiayi Zeng, Mengliang He, Wei Zhang, Xiaoming Shi, Yankai Jiang, Zeming Liu","submitted_at":"2025-06-02T07:48:57Z","abstract_excerpt":"While large language models (LLMs) show promise in code generation, existing benchmarks neglect the flowchart-based code generation. To promote further research on flowchart-based code generation, this work presents Flow2Code, a novel benchmark for flowchart-based code generation evaluation. The evaluation dataset spans 15 programming languages and includes 5,622 code segments paired with 16,866 flowcharts of three types: code, UML, and pseudocode. Extensive experiments with 13 multimodal LLMs reveal that current LLMs can not generate code based on flowcharts perfectly. Besides, experiment res"},"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":"2506.02073","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-06-02T07:48:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c42b04a3eb2390b14f80c21dfabec8107ee4b6a16d637bc3dbc5bd01897b0705","abstract_canon_sha256":"109144318df0c2510651853a0750dbf3686ba0b17b8473c1a40fbf803866bf43"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:31.941417Z","signature_b64":"k7MtpaZKcNjUhpdldVzAoKte6Tol5F71GPH4fKMqjCW04h5lqdgZFgiBD/44xG7y0iPpDlW0dNsG5D4NFM1rCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77819a96b966a45f1f75a8bafca7bddec26c7098ee0da18268bbfdbaad68a2cf","last_reissued_at":"2026-07-05T11:14:31.940976Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:31.940976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Flow2Code: Evaluating Large Language Models for Flowchart-based Code Generation Capability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Aimin Zhou, Jiayi Zeng, Mengliang He, Wei Zhang, Xiaoming Shi, Yankai Jiang, Zeming Liu","submitted_at":"2025-06-02T07:48:57Z","abstract_excerpt":"While large language models (LLMs) show promise in code generation, existing benchmarks neglect the flowchart-based code generation. To promote further research on flowchart-based code generation, this work presents Flow2Code, a novel benchmark for flowchart-based code generation evaluation. The evaluation dataset spans 15 programming languages and includes 5,622 code segments paired with 16,866 flowcharts of three types: code, UML, and pseudocode. Extensive experiments with 13 multimodal LLMs reveal that current LLMs can not generate code based on flowcharts perfectly. Besides, experiment res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02073","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/2506.02073/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":"2506.02073","created_at":"2026-07-05T11:14:31.941033+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02073v1","created_at":"2026-07-05T11:14:31.941033+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02073","created_at":"2026-07-05T11:14:31.941033+00:00"},{"alias_kind":"pith_short_12","alias_value":"O6AZVFVZM2SF","created_at":"2026-07-05T11:14:31.941033+00:00"},{"alias_kind":"pith_short_16","alias_value":"O6AZVFVZM2SF6H3V","created_at":"2026-07-05T11:14:31.941033+00:00"},{"alias_kind":"pith_short_8","alias_value":"O6AZVFVZ","created_at":"2026-07-05T11:14:31.941033+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.15932","citing_title":"Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O6AZVFVZM2SF6H3VVC5PZJ5533","json":"https://pith.science/pith/O6AZVFVZM2SF6H3VVC5PZJ5533.json","graph_json":"https://pith.science/api/pith-number/O6AZVFVZM2SF6H3VVC5PZJ5533/graph.json","events_json":"https://pith.science/api/pith-number/O6AZVFVZM2SF6H3VVC5PZJ5533/events.json","paper":"https://pith.science/paper/O6AZVFVZ"},"agent_actions":{"view_html":"https://pith.science/pith/O6AZVFVZM2SF6H3VVC5PZJ5533","download_json":"https://pith.science/pith/O6AZVFVZM2SF6H3VVC5PZJ5533.json","view_paper":"https://pith.science/paper/O6AZVFVZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02073&json=true","fetch_graph":"https://pith.science/api/pith-number/O6AZVFVZM2SF6H3VVC5PZJ5533/graph.json","fetch_events":"https://pith.science/api/pith-number/O6AZVFVZM2SF6H3VVC5PZJ5533/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O6AZVFVZM2SF6H3VVC5PZJ5533/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O6AZVFVZM2SF6H3VVC5PZJ5533/action/storage_attestation","attest_author":"https://pith.science/pith/O6AZVFVZM2SF6H3VVC5PZJ5533/action/author_attestation","sign_citation":"https://pith.science/pith/O6AZVFVZM2SF6H3VVC5PZJ5533/action/citation_signature","submit_replication":"https://pith.science/pith/O6AZVFVZM2SF6H3VVC5PZJ5533/action/replication_record"}},"created_at":"2026-07-05T11:14:31.941033+00:00","updated_at":"2026-07-05T11:14:31.941033+00:00"}