{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:4DX6ML67GIHWSSG7Z2AE4QE6OM","short_pith_number":"pith:4DX6ML67","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"},"canonical_sha256":"e0efe62fdf320f6948dfce804e409e732c863aa14725b01196b48f333d1f560d","source":{"kind":"arxiv","id":"2607.28611","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28611","created_at":"2026-07-31T01:39:06Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28611v1","created_at":"2026-07-31T01:39:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28611","created_at":"2026-07-31T01:39:06Z"},{"alias_kind":"pith_short_12","alias_value":"4DX6ML67GIHW","created_at":"2026-07-31T01:39:06Z"},{"alias_kind":"pith_short_16","alias_value":"4DX6ML67GIHWSSG7","created_at":"2026-07-31T01:39:06Z"},{"alias_kind":"pith_short_8","alias_value":"4DX6ML67","created_at":"2026-07-31T01:39:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:4DX6ML67GIHWSSG7Z2AE4QE6OM","target":"record","payload":{"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"},"canonical_sha256":"e0efe62fdf320f6948dfce804e409e732c863aa14725b01196b48f333d1f560d","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"},"source_kind":"arxiv","source_id":"2607.28611","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-31T01:39:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i5mWDAUnl2LYUWnEBXswaIyaVh0REt5DpSgGvsWct2tIMgIn+gg3lzXgQSKvo4A5+uCwMeHcLXhry3TrVGMMBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T22:17:04.295821Z"},"content_sha256":"ca6d2290cd62eee8c5f222bc95cb52588dcef21709826582b233c676357b2b24","schema_version":"1.0","event_id":"sha256:ca6d2290cd62eee8c5f222bc95cb52588dcef21709826582b233c676357b2b24"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:4DX6ML67GIHWSSG7Z2AE4QE6OM","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-31T01:39:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jOwR5TW1TD8wLYlZEt3geZkg4l6LtZh8VjgNvCtjwUmrNAGoviM7vSyL4qNNMfoA+fnvuUs5xq+wrUCP4fkFCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T22:17:04.296350Z"},"content_sha256":"176ad62e21d944311f9b6721899a39749e34fdddcc912dcbc33459f0bd4d5488","schema_version":"1.0","event_id":"sha256:176ad62e21d944311f9b6721899a39749e34fdddcc912dcbc33459f0bd4d5488"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4DX6ML67GIHWSSG7Z2AE4QE6OM/bundle.json","state_url":"https://pith.science/pith/4DX6ML67GIHWSSG7Z2AE4QE6OM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4DX6ML67GIHWSSG7Z2AE4QE6OM/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-01T22:17:04Z","links":{"resolver":"https://pith.science/pith/4DX6ML67GIHWSSG7Z2AE4QE6OM","bundle":"https://pith.science/pith/4DX6ML67GIHWSSG7Z2AE4QE6OM/bundle.json","state":"https://pith.science/pith/4DX6ML67GIHWSSG7Z2AE4QE6OM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4DX6ML67GIHWSSG7Z2AE4QE6OM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4DX6ML67GIHWSSG7Z2AE4QE6OM","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"bf1ae45634e43aa2bbbd56ac470d5022e5e6cf769312a097aed929786edb0a25","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T17:58:02Z","title_canon_sha256":"ac11426954279e1bbd10779e1b4bc3b834673577e73e3bc8e39576f456249045"},"schema_version":"1.0","source":{"id":"2607.28611","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28611","created_at":"2026-07-31T01:39:06Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28611v1","created_at":"2026-07-31T01:39:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28611","created_at":"2026-07-31T01:39:06Z"},{"alias_kind":"pith_short_12","alias_value":"4DX6ML67GIHW","created_at":"2026-07-31T01:39:06Z"},{"alias_kind":"pith_short_16","alias_value":"4DX6ML67GIHWSSG7","created_at":"2026-07-31T01:39:06Z"},{"alias_kind":"pith_short_8","alias_value":"4DX6ML67","created_at":"2026-07-31T01:39:06Z"}],"graph_snapshots":[{"event_id":"sha256:176ad62e21d944311f9b6721899a39749e34fdddcc912dcbc33459f0bd4d5488","target":"graph","created_at":"2026-07-31T01:39:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.28611/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T17:58:02Z","title":"Chimera: Designing and Chinchilla-Scaling Hybrid Visual Diffusion Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28611","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ca6d2290cd62eee8c5f222bc95cb52588dcef21709826582b233c676357b2b24","target":"record","created_at":"2026-07-31T01:39:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"bf1ae45634e43aa2bbbd56ac470d5022e5e6cf769312a097aed929786edb0a25","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T17:58:02Z","title_canon_sha256":"ac11426954279e1bbd10779e1b4bc3b834673577e73e3bc8e39576f456249045"},"schema_version":"1.0","source":{"id":"2607.28611","kind":"arxiv","version":1}},"canonical_sha256":"e0efe62fdf320f6948dfce804e409e732c863aa14725b01196b48f333d1f560d","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e0efe62fdf320f6948dfce804e409e732c863aa14725b01196b48f333d1f560d","first_computed_at":"2026-07-31T01:39:06.297955Z","kind":"pith_receipt","last_reissued_at":"2026-07-31T01:39:06.297955Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.28611","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca6d2290cd62eee8c5f222bc95cb52588dcef21709826582b233c676357b2b24","sha256:176ad62e21d944311f9b6721899a39749e34fdddcc912dcbc33459f0bd4d5488"],"state_sha256":"8b1d7979c682194b34f9802664bc18e2ca14e48af4c84a6e472b19f1ec80412f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kcj9UGNwpJ1kUOU0oBQQRFDFNPsJpe4D6GooN6wkuZEIzGioN8FHOCVwqNW4AKPtARAnqNxn80z/Xafz5LCMBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T22:17:04.302147Z","bundle_sha256":"6afe3f2cbcbcfd90354f0f05ae121472978b44c86dd28dfda59170bc3db326d8"}}