{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RY5QKCNSBOQJCSBSIZHJBOQQZ4","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":"5f5f13aeee914a3a658470e81283c22b486e3b551c8370a3ddf429808fb7cb49","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-04T10:24:06Z","title_canon_sha256":"42b01130f26e79358914f1bb3abcd0404a7ba8f4a1b6e1c7925f350c82a8580e"},"schema_version":"1.0","source":{"id":"2606.05981","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05981","created_at":"2026-06-05T01:15:29Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05981v1","created_at":"2026-06-05T01:15:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05981","created_at":"2026-06-05T01:15:29Z"},{"alias_kind":"pith_short_12","alias_value":"RY5QKCNSBOQJ","created_at":"2026-06-05T01:15:29Z"},{"alias_kind":"pith_short_16","alias_value":"RY5QKCNSBOQJCSBS","created_at":"2026-06-05T01:15:29Z"},{"alias_kind":"pith_short_8","alias_value":"RY5QKCNS","created_at":"2026-06-05T01:15:29Z"}],"graph_snapshots":[{"event_id":"sha256:2466a7ec2c380fe176a66abfb7df688d0bb535170b1d08d73783c7ea11c249ea","target":"graph","created_at":"2026-06-05T01:15:29Z","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/2606.05981/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Aggressive distillation of the diffusion U-Net inverts the per-frame bottleneck of real-time text-to-image pipelines: once the denoiser is a 4-step or 1-step distilled student, the text encoder becomes the critical path. This inversion is most acute in vision-aware edit diffusion, where the encoder is a multimodal large language model (MLLM). We study the case of a 0.39B distilled edit U-Net paired with a 2.13B MLLM text encoder (Qwen3-VL) and present a streaming pipeline targeted at this regime built around three engineering mechanisms: asymmetric side-stream / main-stream CUDA pipelining wit","authors_text":"Yoshiyuki Ootani","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-04T10:24:06Z","title":"Video-Rate Streaming Stylization on a Vision-Aware MLLM-Conditioned Edit Diffusion: Asymmetric Batched Inference on a Distilled UNet + MLLM Text Encoder"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05981","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":"sha256:9545ba69caafd9c0451da24a690ff47012193dfbb45ef841155288edd500d7b6","target":"record","created_at":"2026-06-05T01:15:29Z","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":"5f5f13aeee914a3a658470e81283c22b486e3b551c8370a3ddf429808fb7cb49","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-04T10:24:06Z","title_canon_sha256":"42b01130f26e79358914f1bb3abcd0404a7ba8f4a1b6e1c7925f350c82a8580e"},"schema_version":"1.0","source":{"id":"2606.05981","kind":"arxiv","version":1}},"canonical_sha256":"8e3b0509b20ba0914832464e90ba10cf145ca3d6f5e4b59d9acc2aa4703dc86b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e3b0509b20ba0914832464e90ba10cf145ca3d6f5e4b59d9acc2aa4703dc86b","first_computed_at":"2026-06-05T01:15:29.454184Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:29.454184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tPdFuZkODUtyAJC0ckekFegzaI7if1vD4iaFESsfH6M3C4hvgPRdLZMrcYNfikJyfLYKrcjDQgNE6NZZDAF5Aw==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:29.454677Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05981","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9545ba69caafd9c0451da24a690ff47012193dfbb45ef841155288edd500d7b6","sha256:2466a7ec2c380fe176a66abfb7df688d0bb535170b1d08d73783c7ea11c249ea"],"state_sha256":"3ab34f16a4b7694fa207e257d9bf90e79cce2e7a08a1f7b1d69aa75c9ab71b1c"}