{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4DX6ML67GIHWSSG7Z2AE4QE6OM","short_pith_number":"pith:4DX6ML67","schema_version":"1.0","canonical_sha256":"e0efe62fdf320f6948dfce804e409e732c863aa14725b01196b48f333d1f560d","source":{"kind":"arxiv","id":"2607.28611","version":1},"attestation_state":"computed","paper":{"title":"Chimera: Designing and Chinchilla-Scaling Hybrid Visual Diffusion Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chongjian Ge, Hailin Jin, Hanwen Jiang, Hao Tan, Jing Shi, Jiuxiang Gu, Shaoteng Liu, Tianyu Wang, Yicong Hong, Yiran Xu, Zefan Cai, Ziwen Chen","submitted_at":"2026-07-30T17:58:02Z","abstract_excerpt":"Visual generation increasingly requires high-resolution images, long videos, and multimodal context, making the quadratic cost of full attention prohibitive. We introduce Chimera, a hybrid visual diffusion backbone with a principled scaling recipe. Chimera processes text, image, and video tokens in one raster-ordered stream without positional embeddings. It combines Kimi Delta Attention (KDA) for long-context state tracking with O(N) complexity, interleaved Multi-head Latent Attention (MLA) for direct global interaction, and modality-aware short convolutions for local spatiotemporal context. S"},"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":"2607.28611","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T17:58:02Z","cross_cats_sorted":[],"title_canon_sha256":"ac11426954279e1bbd10779e1b4bc3b834673577e73e3bc8e39576f456249045","abstract_canon_sha256":"bf1ae45634e43aa2bbbd56ac470d5022e5e6cf769312a097aed929786edb0a25"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0efe62fdf320f6948dfce804e409e732c863aa14725b01196b48f333d1f560d","last_reissued_at":"2026-07-31T01:39:06.297955Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:39:06.297955Z"},"graph_snapshot":{"paper":{"title":"Chimera: Designing and Chinchilla-Scaling Hybrid Visual Diffusion Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chongjian Ge, Hailin Jin, Hanwen Jiang, Hao Tan, Jing Shi, Jiuxiang Gu, Shaoteng Liu, Tianyu Wang, Yicong Hong, Yiran Xu, Zefan Cai, Ziwen Chen","submitted_at":"2026-07-30T17:58:02Z","abstract_excerpt":"Visual generation increasingly requires high-resolution images, long videos, and multimodal context, making the quadratic cost of full attention prohibitive. We introduce Chimera, a hybrid visual diffusion backbone with a principled scaling recipe. Chimera processes text, image, and video tokens in one raster-ordered stream without positional embeddings. It combines Kimi Delta Attention (KDA) for long-context state tracking with O(N) complexity, interleaved Multi-head Latent Attention (MLA) for direct global interaction, and modality-aware short convolutions for local spatiotemporal context. S"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28611","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/2607.28611/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":"2607.28611","created_at":"2026-07-31T01:39:06.301178+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.28611v1","created_at":"2026-07-31T01:39:06.301178+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28611","created_at":"2026-07-31T01:39:06.301178+00:00"},{"alias_kind":"pith_short_12","alias_value":"4DX6ML67GIHW","created_at":"2026-07-31T01:39:06.301178+00:00"},{"alias_kind":"pith_short_16","alias_value":"4DX6ML67GIHWSSG7","created_at":"2026-07-31T01:39:06.301178+00:00"},{"alias_kind":"pith_short_8","alias_value":"4DX6ML67","created_at":"2026-07-31T01:39:06.301178+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4DX6ML67GIHWSSG7Z2AE4QE6OM","json":"https://pith.science/pith/4DX6ML67GIHWSSG7Z2AE4QE6OM.json","graph_json":"https://pith.science/api/pith-number/4DX6ML67GIHWSSG7Z2AE4QE6OM/graph.json","events_json":"https://pith.science/api/pith-number/4DX6ML67GIHWSSG7Z2AE4QE6OM/events.json","paper":"https://pith.science/paper/4DX6ML67"},"agent_actions":{"view_html":"https://pith.science/pith/4DX6ML67GIHWSSG7Z2AE4QE6OM","download_json":"https://pith.science/pith/4DX6ML67GIHWSSG7Z2AE4QE6OM.json","view_paper":"https://pith.science/paper/4DX6ML67","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.28611&json=true","fetch_graph":"https://pith.science/api/pith-number/4DX6ML67GIHWSSG7Z2AE4QE6OM/graph.json","fetch_events":"https://pith.science/api/pith-number/4DX6ML67GIHWSSG7Z2AE4QE6OM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4DX6ML67GIHWSSG7Z2AE4QE6OM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4DX6ML67GIHWSSG7Z2AE4QE6OM/action/storage_attestation","attest_author":"https://pith.science/pith/4DX6ML67GIHWSSG7Z2AE4QE6OM/action/author_attestation","sign_citation":"https://pith.science/pith/4DX6ML67GIHWSSG7Z2AE4QE6OM/action/citation_signature","submit_replication":"https://pith.science/pith/4DX6ML67GIHWSSG7Z2AE4QE6OM/action/replication_record"}},"created_at":"2026-07-31T01:39:06.301178+00:00","updated_at":"2026-07-31T01:39:06.301178+00:00"}