{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VGIJVMSBCCHO6C6I7JHL7ZIKCX","short_pith_number":"pith:VGIJVMSB","schema_version":"1.0","canonical_sha256":"a9909ab241108eef0bc8fa4ebfe50a15d781c729620f8a7a6abc20cb7dbcafb7","source":{"kind":"arxiv","id":"2505.22523","version":1},"attestation_state":"computed","paper":{"title":"PrismLayers: Open Data for High-Quality Multi-Layer Transparent Image Generative Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Zhang, Dong Chen, Heyang Jiang, Ji Li, Junwen Chen, Keiji Yanai, Keming Wu, Yanbin Wang, Yuhui Yuan","submitted_at":"2025-05-28T16:09:33Z","abstract_excerpt":"Generating high-quality, multi-layer transparent images from text prompts can unlock a new level of creative control, allowing users to edit each layer as effortlessly as editing text outputs from LLMs. However, the development of multi-layer generative models lags behind that of conventional text-to-image models due to the absence of a large, high-quality corpus of multi-layer transparent data. In this paper, we address this fundamental challenge by: (i) releasing the first open, ultra-high-fidelity PrismLayers (PrismLayersPro) dataset of 200K (20K) multilayer transparent images with accurate"},"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":"2505.22523","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-28T16:09:33Z","cross_cats_sorted":[],"title_canon_sha256":"a445db716ad7f9aa4c4918e8f41953933e913f79a906f5e02860dbdc25cf9320","abstract_canon_sha256":"c83ca7c9f84f1ff89bb761d9c0f234e8b98b9be3eed8ba43dc8520cd3c577f15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:25.972326Z","signature_b64":"65EKUkL8DT4SypOPxo7ONf45BXcfzTHmnV8ZIPT5ufc3nC+1sxInMyLw0ScJ+e0HHjs0YIHpgon7gS78XeXGAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9909ab241108eef0bc8fa4ebfe50a15d781c729620f8a7a6abc20cb7dbcafb7","last_reissued_at":"2026-07-05T11:11:25.971805Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:25.971805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PrismLayers: Open Data for High-Quality Multi-Layer Transparent Image Generative Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Zhang, Dong Chen, Heyang Jiang, Ji Li, Junwen Chen, Keiji Yanai, Keming Wu, Yanbin Wang, Yuhui Yuan","submitted_at":"2025-05-28T16:09:33Z","abstract_excerpt":"Generating high-quality, multi-layer transparent images from text prompts can unlock a new level of creative control, allowing users to edit each layer as effortlessly as editing text outputs from LLMs. However, the development of multi-layer generative models lags behind that of conventional text-to-image models due to the absence of a large, high-quality corpus of multi-layer transparent data. In this paper, we address this fundamental challenge by: (i) releasing the first open, ultra-high-fidelity PrismLayers (PrismLayersPro) dataset of 200K (20K) multilayer transparent images with accurate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22523","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/2505.22523/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":"2505.22523","created_at":"2026-07-05T11:11:25.971866+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.22523v1","created_at":"2026-07-05T11:11:25.971866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22523","created_at":"2026-07-05T11:11:25.971866+00:00"},{"alias_kind":"pith_short_12","alias_value":"VGIJVMSBCCHO","created_at":"2026-07-05T11:11:25.971866+00:00"},{"alias_kind":"pith_short_16","alias_value":"VGIJVMSBCCHO6C6I","created_at":"2026-07-05T11:11:25.971866+00:00"},{"alias_kind":"pith_short_8","alias_value":"VGIJVMSB","created_at":"2026-07-05T11:11:25.971866+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25568","citing_title":"Rethinking Scribble-Guided Image Editing: Generalization, Instruction Adherence, and Multi-Tasking","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27235","citing_title":"MRT: Masked Region Transformer for Layered Image Generation and Editing at Scale","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10319","citing_title":"LimeCross: Context-Conditioned Layered Image Editing with Structural Consistency","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VGIJVMSBCCHO6C6I7JHL7ZIKCX","json":"https://pith.science/pith/VGIJVMSBCCHO6C6I7JHL7ZIKCX.json","graph_json":"https://pith.science/api/pith-number/VGIJVMSBCCHO6C6I7JHL7ZIKCX/graph.json","events_json":"https://pith.science/api/pith-number/VGIJVMSBCCHO6C6I7JHL7ZIKCX/events.json","paper":"https://pith.science/paper/VGIJVMSB"},"agent_actions":{"view_html":"https://pith.science/pith/VGIJVMSBCCHO6C6I7JHL7ZIKCX","download_json":"https://pith.science/pith/VGIJVMSBCCHO6C6I7JHL7ZIKCX.json","view_paper":"https://pith.science/paper/VGIJVMSB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.22523&json=true","fetch_graph":"https://pith.science/api/pith-number/VGIJVMSBCCHO6C6I7JHL7ZIKCX/graph.json","fetch_events":"https://pith.science/api/pith-number/VGIJVMSBCCHO6C6I7JHL7ZIKCX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VGIJVMSBCCHO6C6I7JHL7ZIKCX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VGIJVMSBCCHO6C6I7JHL7ZIKCX/action/storage_attestation","attest_author":"https://pith.science/pith/VGIJVMSBCCHO6C6I7JHL7ZIKCX/action/author_attestation","sign_citation":"https://pith.science/pith/VGIJVMSBCCHO6C6I7JHL7ZIKCX/action/citation_signature","submit_replication":"https://pith.science/pith/VGIJVMSBCCHO6C6I7JHL7ZIKCX/action/replication_record"}},"created_at":"2026-07-05T11:11:25.971866+00:00","updated_at":"2026-07-05T11:11:25.971866+00:00"}