{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ISNPX6M5R4XLFYQGWKDFGG6Y22","short_pith_number":"pith:ISNPX6M5","schema_version":"1.0","canonical_sha256":"449afbf99d8f2eb2e206b286531bd8d6b941b8233c6808a2b1fd4b1a94234f77","source":{"kind":"arxiv","id":"2503.17934","version":1},"attestation_state":"computed","paper":{"title":"TransAnimate: Taming Layer Diffusion to Generate RGBA Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Xuewei Chen, Yiren Song, Zhimin Chen","submitted_at":"2025-03-23T04:27:46Z","abstract_excerpt":"Text-to-video generative models have made remarkable advancements in recent years. However, generating RGBA videos with alpha channels for transparency and visual effects remains a significant challenge due to the scarcity of suitable datasets and the complexity of adapting existing models for this purpose. To address these limitations, we present TransAnimate, an innovative framework that integrates RGBA image generation techniques with video generation modules, enabling the creation of dynamic and transparent videos. TransAnimate efficiently leverages pre-trained text-to-transparent image mo"},"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":"2503.17934","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-23T04:27:46Z","cross_cats_sorted":[],"title_canon_sha256":"f5c820152ac287897095c655ad625c4fe1f11f17c6569165d23124e42931d38b","abstract_canon_sha256":"5df030c054064d38e829124e349bfd4d7b31286491c6bce445c0019894458e56"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:37:58.983522Z","signature_b64":"TKDnxx5T4qRJG45+uzgYX2S1+uQsaBqMaMiBbYa7hgH4Y6oEWSmt65Qfj+DXUvWZh4Mu27X3lElvB5OqpEiPBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"449afbf99d8f2eb2e206b286531bd8d6b941b8233c6808a2b1fd4b1a94234f77","last_reissued_at":"2026-07-05T10:37:58.982930Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:37:58.982930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TransAnimate: Taming Layer Diffusion to Generate RGBA Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Xuewei Chen, Yiren Song, Zhimin Chen","submitted_at":"2025-03-23T04:27:46Z","abstract_excerpt":"Text-to-video generative models have made remarkable advancements in recent years. However, generating RGBA videos with alpha channels for transparency and visual effects remains a significant challenge due to the scarcity of suitable datasets and the complexity of adapting existing models for this purpose. To address these limitations, we present TransAnimate, an innovative framework that integrates RGBA image generation techniques with video generation modules, enabling the creation of dynamic and transparent videos. TransAnimate efficiently leverages pre-trained text-to-transparent image mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.17934","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/2503.17934/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":"2503.17934","created_at":"2026-07-05T10:37:58.982997+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.17934v1","created_at":"2026-07-05T10:37:58.982997+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.17934","created_at":"2026-07-05T10:37:58.982997+00:00"},{"alias_kind":"pith_short_12","alias_value":"ISNPX6M5R4XL","created_at":"2026-07-05T10:37:58.982997+00:00"},{"alias_kind":"pith_short_16","alias_value":"ISNPX6M5R4XLFYQG","created_at":"2026-07-05T10:37:58.982997+00:00"},{"alias_kind":"pith_short_8","alias_value":"ISNPX6M5","created_at":"2026-07-05T10:37:58.982997+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01399","citing_title":"PAI-Studio: Cinematic Video Background Replacement with Camera-Aware Motion","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17423","citing_title":"Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17019","citing_title":"StreamingEffect: Real-Time Human-Centric Video Effect Generation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12038","citing_title":"OmniHumanoid: Streaming Cross-Embodiment Video Generation with Paired-Free Adaptation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10319","citing_title":"LimeCross: Context-Conditioned Layered Image Editing with Structural Consistency","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ISNPX6M5R4XLFYQGWKDFGG6Y22","json":"https://pith.science/pith/ISNPX6M5R4XLFYQGWKDFGG6Y22.json","graph_json":"https://pith.science/api/pith-number/ISNPX6M5R4XLFYQGWKDFGG6Y22/graph.json","events_json":"https://pith.science/api/pith-number/ISNPX6M5R4XLFYQGWKDFGG6Y22/events.json","paper":"https://pith.science/paper/ISNPX6M5"},"agent_actions":{"view_html":"https://pith.science/pith/ISNPX6M5R4XLFYQGWKDFGG6Y22","download_json":"https://pith.science/pith/ISNPX6M5R4XLFYQGWKDFGG6Y22.json","view_paper":"https://pith.science/paper/ISNPX6M5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.17934&json=true","fetch_graph":"https://pith.science/api/pith-number/ISNPX6M5R4XLFYQGWKDFGG6Y22/graph.json","fetch_events":"https://pith.science/api/pith-number/ISNPX6M5R4XLFYQGWKDFGG6Y22/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ISNPX6M5R4XLFYQGWKDFGG6Y22/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ISNPX6M5R4XLFYQGWKDFGG6Y22/action/storage_attestation","attest_author":"https://pith.science/pith/ISNPX6M5R4XLFYQGWKDFGG6Y22/action/author_attestation","sign_citation":"https://pith.science/pith/ISNPX6M5R4XLFYQGWKDFGG6Y22/action/citation_signature","submit_replication":"https://pith.science/pith/ISNPX6M5R4XLFYQGWKDFGG6Y22/action/replication_record"}},"created_at":"2026-07-05T10:37:58.982997+00:00","updated_at":"2026-07-05T10:37:58.982997+00:00"}