{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UWGUOYEX7CZ6ENQYL6LV5JNDAQ","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":"b041efaac856257a4dce63fa6531914685cc9fa08e6f3af6e3020c56d037a079","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T03:12:23Z","title_canon_sha256":"981454e19d9729af6d3ec4fccbaf56c56832d3940ad93fd542ad333f15119001"},"schema_version":"1.0","source":{"id":"2606.01620","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01620","created_at":"2026-06-02T02:04:38Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01620v1","created_at":"2026-06-02T02:04:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01620","created_at":"2026-06-02T02:04:38Z"},{"alias_kind":"pith_short_12","alias_value":"UWGUOYEX7CZ6","created_at":"2026-06-02T02:04:38Z"},{"alias_kind":"pith_short_16","alias_value":"UWGUOYEX7CZ6ENQY","created_at":"2026-06-02T02:04:38Z"},{"alias_kind":"pith_short_8","alias_value":"UWGUOYEX","created_at":"2026-06-02T02:04:38Z"}],"graph_snapshots":[{"event_id":"sha256:68b8afaf5721f2e1e46a64bb0e057dc4acf2e95fbc2ece7a3352364898f9dbcc","target":"graph","created_at":"2026-06-02T02:04:38Z","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/2606.01620/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video diffusion models have significantly advanced portrait video generation, yet their high computational demands limit their use in interactive applications. This work presents a framework for streamable talking portrait video generation conditioned on speech audio and reference images. Designed meticulously for streaming scenarios, it features a causal video VAE for deep latent compression and an autoregressive latent denoising model. Our causal VAE integrates a variable number of reference images as guidance, allowing the network to focus on dynamic information rather than static appearanc","authors_text":"Baining Guo, Jiaolong Yang, Shoukang Hu, Sicheng Xu, Yichuan Wang, Yizhong Zhang, Yu Deng, Zhan Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T03:12:23Z","title":"Real-Time Generation of Streamable Talking Portrait Video with Reference-Guided Deep Compression VAEs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01620","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:aafa1aa5534e2d8f37680cc76ae4b486d9f88b61de4dec31ab23656f83ae135b","target":"record","created_at":"2026-06-02T02:04:38Z","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":"b041efaac856257a4dce63fa6531914685cc9fa08e6f3af6e3020c56d037a079","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T03:12:23Z","title_canon_sha256":"981454e19d9729af6d3ec4fccbaf56c56832d3940ad93fd542ad333f15119001"},"schema_version":"1.0","source":{"id":"2606.01620","kind":"arxiv","version":1}},"canonical_sha256":"a58d476097f8b3e236185f975ea5a3040492eb48fab92b24125a8ac157fd6946","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a58d476097f8b3e236185f975ea5a3040492eb48fab92b24125a8ac157fd6946","first_computed_at":"2026-06-02T02:04:38.259128Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:38.259128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gq4ngvWAxXPef57MDBFAIS4nsl4kq3N+re+ssrqt4iI1H586Om3LklMyeeQVRz/CYX5EVyj+UfSajd6DQqxxAA==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:38.259538Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.01620","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aafa1aa5534e2d8f37680cc76ae4b486d9f88b61de4dec31ab23656f83ae135b","sha256:68b8afaf5721f2e1e46a64bb0e057dc4acf2e95fbc2ece7a3352364898f9dbcc"],"state_sha256":"98628324009a65108e3f89f05200a2439d61269725c05e7a92f229526620ab1d"}