{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:H7ZHPPWSHHPGCHYF47N3BJRUEI","short_pith_number":"pith:H7ZHPPWS","schema_version":"1.0","canonical_sha256":"3ff277bed239de611f05e7dbb0a634223861e5e64017bb17d5b545b970532295","source":{"kind":"arxiv","id":"2502.01105","version":3},"attestation_state":"computed","paper":{"title":"LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Danze Chen, Mike Zheng Shou, Yiren Song","submitted_at":"2025-02-03T06:49:58Z","abstract_excerpt":"Generating cognitive-aligned layered SVGs remains challenging due to existing methods' tendencies toward either oversimplified single-layer outputs or optimization-induced shape redundancies. We propose LayerTracer, a diffusion transformer based framework that bridges this gap by learning designers' layered SVG creation processes from a novel dataset of sequential design operations. Our approach operates in two phases: First, a text-conditioned DiT generates multi-phase rasterized construction blueprints that simulate human design workflows. Second, layer-wise vectorization with path deduplica"},"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":"2502.01105","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-03T06:49:58Z","cross_cats_sorted":[],"title_canon_sha256":"61a5e3ab8a13da3952e8788db1f38385f07e80a938c7e9edd5a8cf2756fd978d","abstract_canon_sha256":"30b37ff4402cb2ca12470bcad4fd02990fafbe79a6672038a5d5e4dd06df1f08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:59.225569Z","signature_b64":"WiTMJ0gPjp1Z4Yhoca6p7fPCef+Ev23ooin1uH8rn5F01I5bWlWlKuhz1qmHsGkkmJQWn4DhSbHDz7760A7/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ff277bed239de611f05e7dbb0a634223861e5e64017bb17d5b545b970532295","last_reissued_at":"2026-07-05T11:52:59.225094Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:59.225094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Danze Chen, Mike Zheng Shou, Yiren Song","submitted_at":"2025-02-03T06:49:58Z","abstract_excerpt":"Generating cognitive-aligned layered SVGs remains challenging due to existing methods' tendencies toward either oversimplified single-layer outputs or optimization-induced shape redundancies. We propose LayerTracer, a diffusion transformer based framework that bridges this gap by learning designers' layered SVG creation processes from a novel dataset of sequential design operations. Our approach operates in two phases: First, a text-conditioned DiT generates multi-phase rasterized construction blueprints that simulate human design workflows. Second, layer-wise vectorization with path deduplica"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01105","kind":"arxiv","version":3},"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/2502.01105/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":"2502.01105","created_at":"2026-07-05T11:52:59.225152+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.01105v3","created_at":"2026-07-05T11:52:59.225152+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01105","created_at":"2026-07-05T11:52:59.225152+00:00"},{"alias_kind":"pith_short_12","alias_value":"H7ZHPPWSHHPG","created_at":"2026-07-05T11:52:59.225152+00:00"},{"alias_kind":"pith_short_16","alias_value":"H7ZHPPWSHHPGCHYF","created_at":"2026-07-05T11:52:59.225152+00:00"},{"alias_kind":"pith_short_8","alias_value":"H7ZHPPWS","created_at":"2026-07-05T11:52:59.225152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01399","citing_title":"PAI-Studio: Cinematic Video Background Replacement with Camera-Aware Motion","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22051","citing_title":"EasyVFX: Frequency-Driven Decoupling for Resource-Efficient VFX Generation","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20576","citing_title":"$\\Delta$ynamics: Language-Based Representation for Inferring Rigid-Body Dynamics From Videos","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12038","citing_title":"OmniHumanoid: Streaming Cross-Embodiment Video Generation with Paired-Free Adaptation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10319","citing_title":"LimeCross: Context-Conditioned Layered Image Editing with Structural Consistency","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01517","citing_title":"VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector Animation","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10940","citing_title":"AmodalSVG: Amodal Image Vectorization via Semantic Layer Peeling","ref_index":35,"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":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H7ZHPPWSHHPGCHYF47N3BJRUEI","json":"https://pith.science/pith/H7ZHPPWSHHPGCHYF47N3BJRUEI.json","graph_json":"https://pith.science/api/pith-number/H7ZHPPWSHHPGCHYF47N3BJRUEI/graph.json","events_json":"https://pith.science/api/pith-number/H7ZHPPWSHHPGCHYF47N3BJRUEI/events.json","paper":"https://pith.science/paper/H7ZHPPWS"},"agent_actions":{"view_html":"https://pith.science/pith/H7ZHPPWSHHPGCHYF47N3BJRUEI","download_json":"https://pith.science/pith/H7ZHPPWSHHPGCHYF47N3BJRUEI.json","view_paper":"https://pith.science/paper/H7ZHPPWS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.01105&json=true","fetch_graph":"https://pith.science/api/pith-number/H7ZHPPWSHHPGCHYF47N3BJRUEI/graph.json","fetch_events":"https://pith.science/api/pith-number/H7ZHPPWSHHPGCHYF47N3BJRUEI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H7ZHPPWSHHPGCHYF47N3BJRUEI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H7ZHPPWSHHPGCHYF47N3BJRUEI/action/storage_attestation","attest_author":"https://pith.science/pith/H7ZHPPWSHHPGCHYF47N3BJRUEI/action/author_attestation","sign_citation":"https://pith.science/pith/H7ZHPPWSHHPGCHYF47N3BJRUEI/action/citation_signature","submit_replication":"https://pith.science/pith/H7ZHPPWSHHPGCHYF47N3BJRUEI/action/replication_record"}},"created_at":"2026-07-05T11:52:59.225152+00:00","updated_at":"2026-07-05T11:52:59.225152+00:00"}