{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2RFI4TQAYGG3C3NMLS2HZLLMSK","short_pith_number":"pith:2RFI4TQA","schema_version":"1.0","canonical_sha256":"d44a8e4e00c18db16dac5cb47cad6c9294f94ea4f7d19da2b8e281d5729fe0fe","source":{"kind":"arxiv","id":"2404.04478","version":1},"attestation_state":"computed","paper":{"title":"Diffusion-RWKV: Scaling RWKV-Like Architectures for Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changqian Yu, Debang Li, Junshi Huang, Mingyuan Fan, Zhengcong Fei","submitted_at":"2024-04-06T02:54:35Z","abstract_excerpt":"Transformers have catalyzed advancements in computer vision and natural language processing (NLP) fields. However, substantial computational complexity poses limitations for their application in long-context tasks, such as high-resolution image generation. This paper introduces a series of architectures adapted from the RWKV model used in the NLP, with requisite modifications tailored for diffusion model applied to image generation tasks, referred to as Diffusion-RWKV. Similar to the diffusion with Transformers, our model is designed to efficiently handle patchnified inputs in a sequence with "},"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":"2404.04478","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-06T02:54:35Z","cross_cats_sorted":[],"title_canon_sha256":"520af493373c28f0c45d2dab32deed0629afb7c625fafe9359fda6b110570969","abstract_canon_sha256":"c7ce5f59584fcfd91390e54cafab16725fac02a17e57b6b8b160e51dd56fde39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:17.337982Z","signature_b64":"Bc6yyBtpwvDt322L/Qc2qvjS5Dnw3dLq7zaWPOJydUMUplcr+Ne3FjTbYbVYDE3XJQrt/GRLUtlyLgflr4yIBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d44a8e4e00c18db16dac5cb47cad6c9294f94ea4f7d19da2b8e281d5729fe0fe","last_reissued_at":"2026-07-05T08:05:17.337431Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:17.337431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion-RWKV: Scaling RWKV-Like Architectures for Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changqian Yu, Debang Li, Junshi Huang, Mingyuan Fan, Zhengcong Fei","submitted_at":"2024-04-06T02:54:35Z","abstract_excerpt":"Transformers have catalyzed advancements in computer vision and natural language processing (NLP) fields. However, substantial computational complexity poses limitations for their application in long-context tasks, such as high-resolution image generation. This paper introduces a series of architectures adapted from the RWKV model used in the NLP, with requisite modifications tailored for diffusion model applied to image generation tasks, referred to as Diffusion-RWKV. Similar to the diffusion with Transformers, our model is designed to efficiently handle patchnified inputs in a sequence with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04478","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/2404.04478/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":"2404.04478","created_at":"2026-07-05T08:05:17.337497+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.04478v1","created_at":"2026-07-05T08:05:17.337497+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04478","created_at":"2026-07-05T08:05:17.337497+00:00"},{"alias_kind":"pith_short_12","alias_value":"2RFI4TQAYGG3","created_at":"2026-07-05T08:05:17.337497+00:00"},{"alias_kind":"pith_short_16","alias_value":"2RFI4TQAYGG3C3NM","created_at":"2026-07-05T08:05:17.337497+00:00"},{"alias_kind":"pith_short_8","alias_value":"2RFI4TQA","created_at":"2026-07-05T08:05:17.337497+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14926","citing_title":"SCRWKV: Ultra-Compact Structure-Calibrated Vision-RWKV for Topological Crack Segmentation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2601.22160","citing_title":"Screen, Cache, and Match: A Training-Free Causality-Consistent Reference Frame Framework for Human Animation","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2RFI4TQAYGG3C3NMLS2HZLLMSK","json":"https://pith.science/pith/2RFI4TQAYGG3C3NMLS2HZLLMSK.json","graph_json":"https://pith.science/api/pith-number/2RFI4TQAYGG3C3NMLS2HZLLMSK/graph.json","events_json":"https://pith.science/api/pith-number/2RFI4TQAYGG3C3NMLS2HZLLMSK/events.json","paper":"https://pith.science/paper/2RFI4TQA"},"agent_actions":{"view_html":"https://pith.science/pith/2RFI4TQAYGG3C3NMLS2HZLLMSK","download_json":"https://pith.science/pith/2RFI4TQAYGG3C3NMLS2HZLLMSK.json","view_paper":"https://pith.science/paper/2RFI4TQA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.04478&json=true","fetch_graph":"https://pith.science/api/pith-number/2RFI4TQAYGG3C3NMLS2HZLLMSK/graph.json","fetch_events":"https://pith.science/api/pith-number/2RFI4TQAYGG3C3NMLS2HZLLMSK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2RFI4TQAYGG3C3NMLS2HZLLMSK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2RFI4TQAYGG3C3NMLS2HZLLMSK/action/storage_attestation","attest_author":"https://pith.science/pith/2RFI4TQAYGG3C3NMLS2HZLLMSK/action/author_attestation","sign_citation":"https://pith.science/pith/2RFI4TQAYGG3C3NMLS2HZLLMSK/action/citation_signature","submit_replication":"https://pith.science/pith/2RFI4TQAYGG3C3NMLS2HZLLMSK/action/replication_record"}},"created_at":"2026-07-05T08:05:17.337497+00:00","updated_at":"2026-07-05T08:05:17.337497+00:00"}