{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5HBPQQP3NJUCT7DZG2XFI7P26Y","short_pith_number":"pith:5HBPQQP3","schema_version":"1.0","canonical_sha256":"e9c2f841fb6a6829fc7936ae547dfaf621cd92c4886b1fb349564d2b85947428","source":{"kind":"arxiv","id":"2508.09168","version":1},"attestation_state":"computed","paper":{"title":"SVGen: Interpretable Vector Graphics Generation with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Da Zhang, Feiyu Wang, Hao Sun, Junyu Gao, Xuelong Li, Yuandong Liu, Zhiyuan Zhao","submitted_at":"2025-08-06T15:00:24Z","abstract_excerpt":"Scalable Vector Graphics (SVG) is widely used in front-end development and UI/UX design due to its scalability, editability, and rendering efficiency. However, turning creative ideas into precise vector graphics remains a time-consuming challenge. To address this, we introduce SVG-1M, a large-scale dataset of high-quality SVGs paired with natural language descriptions. Through advanced data augmentation and annotation, we create well-aligned Text to SVG training pairs, including a subset with Chain of Thought annotations for enhanced semantic guidance. Based on this dataset, we propose SVGen, "},"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":"2508.09168","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-06T15:00:24Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"dd2793cf40cafc10cf7692f1ea9b443215fe94a904ccf1b464367c5cd3c834bc","abstract_canon_sha256":"52b602cae5e7943bfcddb26f6280d4ad5303a26a6f816dfbb203557b88671452"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:09.223029Z","signature_b64":"n5rK9Fxnmj+Ktm/ibiiCueyUmZeRlRy/QdjQY7KS81CX6UaORD1aiqAg5rSU64q4wznnBW1f49TU6FOt28ZbCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9c2f841fb6a6829fc7936ae547dfaf621cd92c4886b1fb349564d2b85947428","last_reissued_at":"2026-07-05T11:53:09.222467Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:09.222467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SVGen: Interpretable Vector Graphics Generation with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Da Zhang, Feiyu Wang, Hao Sun, Junyu Gao, Xuelong Li, Yuandong Liu, Zhiyuan Zhao","submitted_at":"2025-08-06T15:00:24Z","abstract_excerpt":"Scalable Vector Graphics (SVG) is widely used in front-end development and UI/UX design due to its scalability, editability, and rendering efficiency. However, turning creative ideas into precise vector graphics remains a time-consuming challenge. To address this, we introduce SVG-1M, a large-scale dataset of high-quality SVGs paired with natural language descriptions. Through advanced data augmentation and annotation, we create well-aligned Text to SVG training pairs, including a subset with Chain of Thought annotations for enhanced semantic guidance. Based on this dataset, we propose SVGen, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.09168","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/2508.09168/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":"2508.09168","created_at":"2026-07-05T11:53:09.222545+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.09168v1","created_at":"2026-07-05T11:53:09.222545+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.09168","created_at":"2026-07-05T11:53:09.222545+00:00"},{"alias_kind":"pith_short_12","alias_value":"5HBPQQP3NJUC","created_at":"2026-07-05T11:53:09.222545+00:00"},{"alias_kind":"pith_short_16","alias_value":"5HBPQQP3NJUCT7DZ","created_at":"2026-07-05T11:53:09.222545+00:00"},{"alias_kind":"pith_short_8","alias_value":"5HBPQQP3","created_at":"2026-07-05T11:53:09.222545+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25447","citing_title":"GeoSVG-RL: Geometry-Aware Reinforcement Learning for Layout-Constrained Text-to-SVG Diagram Generation","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5HBPQQP3NJUCT7DZG2XFI7P26Y","json":"https://pith.science/pith/5HBPQQP3NJUCT7DZG2XFI7P26Y.json","graph_json":"https://pith.science/api/pith-number/5HBPQQP3NJUCT7DZG2XFI7P26Y/graph.json","events_json":"https://pith.science/api/pith-number/5HBPQQP3NJUCT7DZG2XFI7P26Y/events.json","paper":"https://pith.science/paper/5HBPQQP3"},"agent_actions":{"view_html":"https://pith.science/pith/5HBPQQP3NJUCT7DZG2XFI7P26Y","download_json":"https://pith.science/pith/5HBPQQP3NJUCT7DZG2XFI7P26Y.json","view_paper":"https://pith.science/paper/5HBPQQP3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.09168&json=true","fetch_graph":"https://pith.science/api/pith-number/5HBPQQP3NJUCT7DZG2XFI7P26Y/graph.json","fetch_events":"https://pith.science/api/pith-number/5HBPQQP3NJUCT7DZG2XFI7P26Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5HBPQQP3NJUCT7DZG2XFI7P26Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5HBPQQP3NJUCT7DZG2XFI7P26Y/action/storage_attestation","attest_author":"https://pith.science/pith/5HBPQQP3NJUCT7DZG2XFI7P26Y/action/author_attestation","sign_citation":"https://pith.science/pith/5HBPQQP3NJUCT7DZG2XFI7P26Y/action/citation_signature","submit_replication":"https://pith.science/pith/5HBPQQP3NJUCT7DZG2XFI7P26Y/action/replication_record"}},"created_at":"2026-07-05T11:53:09.222545+00:00","updated_at":"2026-07-05T11:53:09.222545+00:00"}