{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3YVZB2R4EEB3LDQ6TBYLAM67SK","short_pith_number":"pith:3YVZB2R4","schema_version":"1.0","canonical_sha256":"de2b90ea3c2103b58e1e9870b033df9292cc274b8b601fde9a4395ba708ea606","source":{"kind":"arxiv","id":"2605.15677","version":1},"attestation_state":"computed","paper":{"title":"VCG-Bench: Towards A Unified Visual-Centric Benchmark for Structured Generation and Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Gai Yuhang, Kaitao Lin, Liang Chen, Peijie Dong, Qiang Wang, Song Tang, Xiaowen Chu, Xiaoyan Su, Yuyao Zhai, Yuyu Luo, Zhenheng Tang","submitted_at":"2026-05-15T06:59:28Z","abstract_excerpt":"Despite the rapid advancements in Vision-Language Models (VLMs), a critical gap remains in their ability to handle structured, controllable diagrammatic tasks essential for professional workflows. Existing methods predominantly rely on pixel-based synthesis, which operates in probabilistic pixel spaces and is inherently limited in editability and fidelity. Instead, we propose a new Diagram-as-Code paradigm with symbolic logic that leverages mxGraph Extensible Markup Language (XML) for precise diagram generation and editing. We present VCG-Bench, a unified benchmark for visual-centric \\texttt{m"},"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":"2605.15677","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-15T06:59:28Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"4c758e5eeaaeebf0027371ac05f07c3d245f4c3557b823c8fcc534e4d85fbb3e","abstract_canon_sha256":"378adfd57f1c770f6bc3e1e3424e282977c94c6869361e31558f64cb7a0141c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:11.929017Z","signature_b64":"WkG5mTdcgN4fT1LxLPMYr0DYoWLv/JDtj+GFYWX+b9fI/vxy5RtI13dHAWmvLxpHbKYfedKPPhrdO6GAEnjDAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de2b90ea3c2103b58e1e9870b033df9292cc274b8b601fde9a4395ba708ea606","last_reissued_at":"2026-05-20T00:01:11.928348Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:11.928348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VCG-Bench: Towards A Unified Visual-Centric Benchmark for Structured Generation and Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Gai Yuhang, Kaitao Lin, Liang Chen, Peijie Dong, Qiang Wang, Song Tang, Xiaowen Chu, Xiaoyan Su, Yuyao Zhai, Yuyu Luo, Zhenheng Tang","submitted_at":"2026-05-15T06:59:28Z","abstract_excerpt":"Despite the rapid advancements in Vision-Language Models (VLMs), a critical gap remains in their ability to handle structured, controllable diagrammatic tasks essential for professional workflows. Existing methods predominantly rely on pixel-based synthesis, which operates in probabilistic pixel spaces and is inherently limited in editability and fidelity. Instead, we propose a new Diagram-as-Code paradigm with symbolic logic that leverages mxGraph Extensible Markup Language (XML) for precise diagram generation and editing. We present VCG-Bench, a unified benchmark for visual-centric \\texttt{m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15677","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/2605.15677/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T19:33:29.860529Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:21:56.056938Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"2f71d53b52db713791678a72afc82d9da8ed915bfb68d198022c591c2399cc8c"},"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":"2605.15677","created_at":"2026-05-20T00:01:11.928476+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15677v1","created_at":"2026-05-20T00:01:11.928476+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15677","created_at":"2026-05-20T00:01:11.928476+00:00"},{"alias_kind":"pith_short_12","alias_value":"3YVZB2R4EEB3","created_at":"2026-05-20T00:01:11.928476+00:00"},{"alias_kind":"pith_short_16","alias_value":"3YVZB2R4EEB3LDQ6","created_at":"2026-05-20T00:01:11.928476+00:00"},{"alias_kind":"pith_short_8","alias_value":"3YVZB2R4","created_at":"2026-05-20T00:01:11.928476+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/3YVZB2R4EEB3LDQ6TBYLAM67SK","json":"https://pith.science/pith/3YVZB2R4EEB3LDQ6TBYLAM67SK.json","graph_json":"https://pith.science/api/pith-number/3YVZB2R4EEB3LDQ6TBYLAM67SK/graph.json","events_json":"https://pith.science/api/pith-number/3YVZB2R4EEB3LDQ6TBYLAM67SK/events.json","paper":"https://pith.science/paper/3YVZB2R4"},"agent_actions":{"view_html":"https://pith.science/pith/3YVZB2R4EEB3LDQ6TBYLAM67SK","download_json":"https://pith.science/pith/3YVZB2R4EEB3LDQ6TBYLAM67SK.json","view_paper":"https://pith.science/paper/3YVZB2R4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15677&json=true","fetch_graph":"https://pith.science/api/pith-number/3YVZB2R4EEB3LDQ6TBYLAM67SK/graph.json","fetch_events":"https://pith.science/api/pith-number/3YVZB2R4EEB3LDQ6TBYLAM67SK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3YVZB2R4EEB3LDQ6TBYLAM67SK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3YVZB2R4EEB3LDQ6TBYLAM67SK/action/storage_attestation","attest_author":"https://pith.science/pith/3YVZB2R4EEB3LDQ6TBYLAM67SK/action/author_attestation","sign_citation":"https://pith.science/pith/3YVZB2R4EEB3LDQ6TBYLAM67SK/action/citation_signature","submit_replication":"https://pith.science/pith/3YVZB2R4EEB3LDQ6TBYLAM67SK/action/replication_record"}},"created_at":"2026-05-20T00:01:11.928476+00:00","updated_at":"2026-05-20T00:01:11.928476+00:00"}