{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:UWGUOYEX7CZ6ENQYL6LV5JNDAQ","short_pith_number":"pith:UWGUOYEX","canonical_record":{"source":{"id":"2606.01620","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T03:12:23Z","cross_cats_sorted":[],"title_canon_sha256":"981454e19d9729af6d3ec4fccbaf56c56832d3940ad93fd542ad333f15119001","abstract_canon_sha256":"b041efaac856257a4dce63fa6531914685cc9fa08e6f3af6e3020c56d037a079"},"schema_version":"1.0"},"canonical_sha256":"a58d476097f8b3e236185f975ea5a3040492eb48fab92b24125a8ac157fd6946","source":{"kind":"arxiv","id":"2606.01620","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:UWGUOYEX7CZ6ENQYL6LV5JNDAQ","target":"record","payload":{"canonical_record":{"source":{"id":"2606.01620","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T03:12:23Z","cross_cats_sorted":[],"title_canon_sha256":"981454e19d9729af6d3ec4fccbaf56c56832d3940ad93fd542ad333f15119001","abstract_canon_sha256":"b041efaac856257a4dce63fa6531914685cc9fa08e6f3af6e3020c56d037a079"},"schema_version":"1.0"},"canonical_sha256":"a58d476097f8b3e236185f975ea5a3040492eb48fab92b24125a8ac157fd6946","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:38.259538Z","signature_b64":"Gq4ngvWAxXPef57MDBFAIS4nsl4kq3N+re+ssrqt4iI1H586Om3LklMyeeQVRz/CYX5EVyj+UfSajd6DQqxxAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a58d476097f8b3e236185f975ea5a3040492eb48fab92b24125a8ac157fd6946","last_reissued_at":"2026-06-02T02:04:38.259128Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:38.259128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.01620","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":"2026-06-02T02:04:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lWurWXYSPqtZtDKi0bkrUsvurzkYKjFyBIPFOw/a2WQoq4yY8AkbaDvm1u1vt3db858fV679q+Gh/7gEBgBhDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T01:36:00.295376Z"},"content_sha256":"aafa1aa5534e2d8f37680cc76ae4b486d9f88b61de4dec31ab23656f83ae135b","schema_version":"1.0","event_id":"sha256:aafa1aa5534e2d8f37680cc76ae4b486d9f88b61de4dec31ab23656f83ae135b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:UWGUOYEX7CZ6ENQYL6LV5JNDAQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Real-Time Generation of Streamable Talking Portrait Video with Reference-Guided Deep Compression VAEs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baining Guo, Jiaolong Yang, Shoukang Hu, Sicheng Xu, Yichuan Wang, Yizhong Zhang, Yu Deng, Zhan Chen","submitted_at":"2026-06-01T03:12:23Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01620","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/2606.01620/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":"2026-06-02T02:04:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zFRCu6kKQET4hiucoL0CmDBjYykv45L+XJN6O1wvW29/LSfRJr6/t1D8CadHLFAcAKQuDZp+LkU3Kkk904Q4AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T01:36:00.296140Z"},"content_sha256":"68b8afaf5721f2e1e46a64bb0e057dc4acf2e95fbc2ece7a3352364898f9dbcc","schema_version":"1.0","event_id":"sha256:68b8afaf5721f2e1e46a64bb0e057dc4acf2e95fbc2ece7a3352364898f9dbcc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UWGUOYEX7CZ6ENQYL6LV5JNDAQ/bundle.json","state_url":"https://pith.science/pith/UWGUOYEX7CZ6ENQYL6LV5JNDAQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UWGUOYEX7CZ6ENQYL6LV5JNDAQ/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":"2026-06-08T01:36:00Z","links":{"resolver":"https://pith.science/pith/UWGUOYEX7CZ6ENQYL6LV5JNDAQ","bundle":"https://pith.science/pith/UWGUOYEX7CZ6ENQYL6LV5JNDAQ/bundle.json","state":"https://pith.science/pith/UWGUOYEX7CZ6ENQYL6LV5JNDAQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UWGUOYEX7CZ6ENQYL6LV5JNDAQ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LnstnPrjD3Ifze3kBXEo1xCLK5NkuCKDKvg3DZgWCQkHTN5ilwkEqqr2JzgSs98gmzGXgUPHID4VNsXihJh1Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T01:36:00.299927Z","bundle_sha256":"f5a54d16debe8cab970df1da2f2a0ffa081ee4da29c572ee912243842779848c"}}