{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YDB3USOXHF2NDUXRI4X2A5L272","short_pith_number":"pith:YDB3USOX","schema_version":"1.0","canonical_sha256":"c0c3ba49d73974d1d2f1472fa0757afeb04b393b5e42ae92f5c5bc39b865c306","source":{"kind":"arxiv","id":"2312.11556","version":4},"attestation_state":"computed","paper":{"title":"StarVector: Generating Scalable Vector Graphics Code from Images and Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Abhay Puri, Christopher Pal, David Vazquez, Issam H. Laradji, Juan A. Rodriguez, Marco Pedersoli, Pau Rodriguez, Sai Rajeswar, Shubham Agarwal","submitted_at":"2023-12-17T08:07:32Z","abstract_excerpt":"Scalable Vector Graphics (SVGs) are vital for modern image rendering due to their scalability and versatility. Previous SVG generation methods have focused on curve-based vectorization, lacking semantic understanding, often producing artifacts, and struggling with SVG primitives beyond path curves. To address these issues, we introduce StarVector, a multimodal large language model for SVG generation. It performs image vectorization by understanding image semantics and using SVG primitives for compact, precise outputs. Unlike traditional methods, StarVector works directly in the SVG code space,"},"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":"2312.11556","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-17T08:07:32Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"073d1e66b876e9881f8ab18d7b6a0f27404638bbbb7497a53076ac4219a8db19","abstract_canon_sha256":"e1f77627ea7ab7efd5fb5720778ec18add6933a17c983244fd885abf602d838a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:06.625647Z","signature_b64":"coHn8mjvfJLC8HwUXherCwNP7bQ9j3tooKTS6A+Vnp7Mt1/9YCSKdaM+dLzo+9dj5JC57Xc4OvWBCMYK9tIUCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0c3ba49d73974d1d2f1472fa0757afeb04b393b5e42ae92f5c5bc39b865c306","last_reissued_at":"2026-07-05T11:13:06.625050Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:06.625050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StarVector: Generating Scalable Vector Graphics Code from Images and Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Abhay Puri, Christopher Pal, David Vazquez, Issam H. Laradji, Juan A. Rodriguez, Marco Pedersoli, Pau Rodriguez, Sai Rajeswar, Shubham Agarwal","submitted_at":"2023-12-17T08:07:32Z","abstract_excerpt":"Scalable Vector Graphics (SVGs) are vital for modern image rendering due to their scalability and versatility. Previous SVG generation methods have focused on curve-based vectorization, lacking semantic understanding, often producing artifacts, and struggling with SVG primitives beyond path curves. To address these issues, we introduce StarVector, a multimodal large language model for SVG generation. It performs image vectorization by understanding image semantics and using SVG primitives for compact, precise outputs. Unlike traditional methods, StarVector works directly in the SVG code space,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.11556","kind":"arxiv","version":4},"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/2312.11556/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":"2312.11556","created_at":"2026-07-05T11:13:06.625135+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.11556v4","created_at":"2026-07-05T11:13:06.625135+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11556","created_at":"2026-07-05T11:13:06.625135+00:00"},{"alias_kind":"pith_short_12","alias_value":"YDB3USOXHF2N","created_at":"2026-07-05T11:13:06.625135+00:00"},{"alias_kind":"pith_short_16","alias_value":"YDB3USOXHF2NDUXR","created_at":"2026-07-05T11:13:06.625135+00:00"},{"alias_kind":"pith_short_8","alias_value":"YDB3USOX","created_at":"2026-07-05T11:13:06.625135+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24398","citing_title":"VectorArk: Learning Practical Image Vectorization with Rounded Polygon Representation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25447","citing_title":"GeoSVG-RL: Geometry-Aware Reinforcement Learning for Layout-Constrained Text-to-SVG Diagram Generation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2602.13294","citing_title":"VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstruction","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2603.13224","citing_title":"Visual-ERM: Reward Modeling for Visual Equivalence","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04172","citing_title":"GENFIG1: Visual Summaries of Scholarly Work as a Challenge for Vision-Language Models","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YDB3USOXHF2NDUXRI4X2A5L272","json":"https://pith.science/pith/YDB3USOXHF2NDUXRI4X2A5L272.json","graph_json":"https://pith.science/api/pith-number/YDB3USOXHF2NDUXRI4X2A5L272/graph.json","events_json":"https://pith.science/api/pith-number/YDB3USOXHF2NDUXRI4X2A5L272/events.json","paper":"https://pith.science/paper/YDB3USOX"},"agent_actions":{"view_html":"https://pith.science/pith/YDB3USOXHF2NDUXRI4X2A5L272","download_json":"https://pith.science/pith/YDB3USOXHF2NDUXRI4X2A5L272.json","view_paper":"https://pith.science/paper/YDB3USOX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.11556&json=true","fetch_graph":"https://pith.science/api/pith-number/YDB3USOXHF2NDUXRI4X2A5L272/graph.json","fetch_events":"https://pith.science/api/pith-number/YDB3USOXHF2NDUXRI4X2A5L272/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YDB3USOXHF2NDUXRI4X2A5L272/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YDB3USOXHF2NDUXRI4X2A5L272/action/storage_attestation","attest_author":"https://pith.science/pith/YDB3USOXHF2NDUXRI4X2A5L272/action/author_attestation","sign_citation":"https://pith.science/pith/YDB3USOXHF2NDUXRI4X2A5L272/action/citation_signature","submit_replication":"https://pith.science/pith/YDB3USOXHF2NDUXRI4X2A5L272/action/replication_record"}},"created_at":"2026-07-05T11:13:06.625135+00:00","updated_at":"2026-07-05T11:13:06.625135+00:00"}