{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZGNXWQ4EWZASXMAJPKRVOYIW24","short_pith_number":"pith:ZGNXWQ4E","schema_version":"1.0","canonical_sha256":"c99b7b4384b6412bb0097aa3576116d706974ecd54e187840375043ae1de1504","source":{"kind":"arxiv","id":"2606.28406","version":1},"attestation_state":"computed","paper":{"title":"Can AI Draw Science? A Benchmark for Evaluating Scientific Figure Generation by Text-to-Image and Multimodal Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.GR"],"primary_cat":"cs.LG","authors_text":"Davie Chen","submitted_at":"2026-06-24T14:21:01Z","abstract_excerpt":"Text-to-image and multimodal generative models are increasingly used to produce scientific figures such as mechanism diagrams, experimental-design schematics, conceptual frameworks, and graphical abstracts. Yet existing image-generation benchmarks (e.g., GenEval, T2I-CompBench, DPG-Bench) evaluate natural images and measure compositionality, object counting, or photorealism. None of them measure what makes a generated scientific figure usable: correct and legible text labels, faithful depiction of entities and their relations, coherent diagrammatic structure, and adherence to disciplinary draw"},"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":"2606.28406","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-24T14:21:01Z","cross_cats_sorted":["cs.CV","cs.GR"],"title_canon_sha256":"094b1adcae30448c95d858a1d8aacaceb81b96a9949bc96e44999651a5750f76","abstract_canon_sha256":"21b5395d0b9d46bcf7e4787cf78029db1b94ca8a426ec3d9094486377286b9e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T00:15:13.233030Z","signature_b64":"uGTLfZARnFAgJGDBlbspREOReCGqpSyAEB4zKD/JAb5Weis4kS/4RkcL3yP5WJxCmFTvVq9diJqcSxod9CoSDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c99b7b4384b6412bb0097aa3576116d706974ecd54e187840375043ae1de1504","last_reissued_at":"2026-06-30T00:15:13.232622Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T00:15:13.232622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can AI Draw Science? A Benchmark for Evaluating Scientific Figure Generation by Text-to-Image and Multimodal Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.GR"],"primary_cat":"cs.LG","authors_text":"Davie Chen","submitted_at":"2026-06-24T14:21:01Z","abstract_excerpt":"Text-to-image and multimodal generative models are increasingly used to produce scientific figures such as mechanism diagrams, experimental-design schematics, conceptual frameworks, and graphical abstracts. Yet existing image-generation benchmarks (e.g., GenEval, T2I-CompBench, DPG-Bench) evaluate natural images and measure compositionality, object counting, or photorealism. None of them measure what makes a generated scientific figure usable: correct and legible text labels, faithful depiction of entities and their relations, coherent diagrammatic structure, and adherence to disciplinary draw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28406","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/2606.28406/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":"2606.28406","created_at":"2026-06-30T00:15:13.232687+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.28406v1","created_at":"2026-06-30T00:15:13.232687+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28406","created_at":"2026-06-30T00:15:13.232687+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZGNXWQ4EWZAS","created_at":"2026-06-30T00:15:13.232687+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZGNXWQ4EWZASXMAJ","created_at":"2026-06-30T00:15:13.232687+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZGNXWQ4E","created_at":"2026-06-30T00:15:13.232687+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZGNXWQ4EWZASXMAJPKRVOYIW24","json":"https://pith.science/pith/ZGNXWQ4EWZASXMAJPKRVOYIW24.json","graph_json":"https://pith.science/api/pith-number/ZGNXWQ4EWZASXMAJPKRVOYIW24/graph.json","events_json":"https://pith.science/api/pith-number/ZGNXWQ4EWZASXMAJPKRVOYIW24/events.json","paper":"https://pith.science/paper/ZGNXWQ4E"},"agent_actions":{"view_html":"https://pith.science/pith/ZGNXWQ4EWZASXMAJPKRVOYIW24","download_json":"https://pith.science/pith/ZGNXWQ4EWZASXMAJPKRVOYIW24.json","view_paper":"https://pith.science/paper/ZGNXWQ4E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.28406&json=true","fetch_graph":"https://pith.science/api/pith-number/ZGNXWQ4EWZASXMAJPKRVOYIW24/graph.json","fetch_events":"https://pith.science/api/pith-number/ZGNXWQ4EWZASXMAJPKRVOYIW24/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZGNXWQ4EWZASXMAJPKRVOYIW24/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZGNXWQ4EWZASXMAJPKRVOYIW24/action/storage_attestation","attest_author":"https://pith.science/pith/ZGNXWQ4EWZASXMAJPKRVOYIW24/action/author_attestation","sign_citation":"https://pith.science/pith/ZGNXWQ4EWZASXMAJPKRVOYIW24/action/citation_signature","submit_replication":"https://pith.science/pith/ZGNXWQ4EWZASXMAJPKRVOYIW24/action/replication_record"}},"created_at":"2026-06-30T00:15:13.232687+00:00","updated_at":"2026-06-30T00:15:13.232687+00:00"}