{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SGBSTZTMCWMCO2FYSRQD2CFERC","short_pith_number":"pith:SGBSTZTM","schema_version":"1.0","canonical_sha256":"918329e66c15982768b894603d08a4889992f8bd60fc18a65541b6c537ad7732","source":{"kind":"arxiv","id":"2401.17093","version":1},"attestation_state":"computed","paper":{"title":"StrokeNUWA: Tokenizing Strokes for Vector Graphic Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chenfei Wu, Juntao Li, Lijuan Wang, Mingheng Ni, Nan Duan, Shengming Yin, Yu Liu, Zecheng Tang, Zekai Zhang, Zhengyuan Yang, Zicheng Liu","submitted_at":"2024-01-30T15:20:26Z","abstract_excerpt":"To leverage LLMs for visual synthesis, traditional methods convert raster image information into discrete grid tokens through specialized visual modules, while disrupting the model's ability to capture the true semantic representation of visual scenes. This paper posits that an alternative representation of images, vector graphics, can effectively surmount this limitation by enabling a more natural and semantically coherent segmentation of the image information. Thus, we introduce StrokeNUWA, a pioneering work exploring a better visual representation ''stroke tokens'' on vector graphics, which"},"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":"2401.17093","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-30T15:20:26Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"fdd3119ff19e08de0337a7c12c7a834dd0948e19dbbcc7206b69bdb95bae6730","abstract_canon_sha256":"d3ae2b726eefcb0a7c1da2fc9729043f79c377f150c1c183d267c05224c70711"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:39:19.217981Z","signature_b64":"oUihGqm2VPd9nmz9IxhjwrepPk+ILL2S+4vMDel+AHMbaZrBPd2xxTQ2dOvkfvIvEfd6vE2SFEmLiwnzWIZGBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"918329e66c15982768b894603d08a4889992f8bd60fc18a65541b6c537ad7732","last_reissued_at":"2026-07-05T07:39:19.217551Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:39:19.217551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StrokeNUWA: Tokenizing Strokes for Vector Graphic Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chenfei Wu, Juntao Li, Lijuan Wang, Mingheng Ni, Nan Duan, Shengming Yin, Yu Liu, Zecheng Tang, Zekai Zhang, Zhengyuan Yang, Zicheng Liu","submitted_at":"2024-01-30T15:20:26Z","abstract_excerpt":"To leverage LLMs for visual synthesis, traditional methods convert raster image information into discrete grid tokens through specialized visual modules, while disrupting the model's ability to capture the true semantic representation of visual scenes. This paper posits that an alternative representation of images, vector graphics, can effectively surmount this limitation by enabling a more natural and semantically coherent segmentation of the image information. Thus, we introduce StrokeNUWA, a pioneering work exploring a better visual representation ''stroke tokens'' on vector graphics, which"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.17093","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/2401.17093/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":"2401.17093","created_at":"2026-07-05T07:39:19.217609+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.17093v1","created_at":"2026-07-05T07:39:19.217609+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.17093","created_at":"2026-07-05T07:39:19.217609+00:00"},{"alias_kind":"pith_short_12","alias_value":"SGBSTZTMCWMC","created_at":"2026-07-05T07:39:19.217609+00:00"},{"alias_kind":"pith_short_16","alias_value":"SGBSTZTMCWMCO2FY","created_at":"2026-07-05T07:39:19.217609+00:00"},{"alias_kind":"pith_short_8","alias_value":"SGBSTZTM","created_at":"2026-07-05T07:39:19.217609+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.10437","citing_title":"SVGFusion: A VAE-Diffusion Transformer for Vector Graphic Generation","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17054","citing_title":"mEOL: Training-Free Instruction-Guided Multimodal Embedder for Vector Graphics and Image Retrieval","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SGBSTZTMCWMCO2FYSRQD2CFERC","json":"https://pith.science/pith/SGBSTZTMCWMCO2FYSRQD2CFERC.json","graph_json":"https://pith.science/api/pith-number/SGBSTZTMCWMCO2FYSRQD2CFERC/graph.json","events_json":"https://pith.science/api/pith-number/SGBSTZTMCWMCO2FYSRQD2CFERC/events.json","paper":"https://pith.science/paper/SGBSTZTM"},"agent_actions":{"view_html":"https://pith.science/pith/SGBSTZTMCWMCO2FYSRQD2CFERC","download_json":"https://pith.science/pith/SGBSTZTMCWMCO2FYSRQD2CFERC.json","view_paper":"https://pith.science/paper/SGBSTZTM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.17093&json=true","fetch_graph":"https://pith.science/api/pith-number/SGBSTZTMCWMCO2FYSRQD2CFERC/graph.json","fetch_events":"https://pith.science/api/pith-number/SGBSTZTMCWMCO2FYSRQD2CFERC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SGBSTZTMCWMCO2FYSRQD2CFERC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SGBSTZTMCWMCO2FYSRQD2CFERC/action/storage_attestation","attest_author":"https://pith.science/pith/SGBSTZTMCWMCO2FYSRQD2CFERC/action/author_attestation","sign_citation":"https://pith.science/pith/SGBSTZTMCWMCO2FYSRQD2CFERC/action/citation_signature","submit_replication":"https://pith.science/pith/SGBSTZTMCWMCO2FYSRQD2CFERC/action/replication_record"}},"created_at":"2026-07-05T07:39:19.217609+00:00","updated_at":"2026-07-05T07:39:19.217609+00:00"}