{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LS5SX7RNDAUNF5BI52HC65TBP5","short_pith_number":"pith:LS5SX7RN","schema_version":"1.0","canonical_sha256":"5cbb2bfe2d1828d2f428ee8e2f76617f72efe8f120dfc9a5d8fbb55058ac633b","source":{"kind":"arxiv","id":"2607.04443","version":1},"attestation_state":"computed","paper":{"title":"Wan-Streamer v0.2: Higher Resolution, Same Latency","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ang Wang, Bang Zhang, Baole Ai, Cheng Yu, Chen Liang, Chen-Wei Xie, Chongyang Zhong, Jingren Zhou, Jinwei Qi, Junjie He, Kai Zhu, Lianghua Huang, Mengyang Feng, Pandeng Li, Peng Zhang, Wei Wang, Wenyuan Zhang, Xinhua Cheng, Yitong Huang, Yu Liu, Yun Zheng, Yupeng Shi, Yuxiang Bao, Yuzheng Wang, Zhi-Fan Wu, Zoubin Bi","submitted_at":"2026-07-05T18:05:20Z","abstract_excerpt":"We present Wan-Streamer v0.2, a latency-preserving upgrade of the native-streaming, end-to-end audio-visual interaction model. v0.2 keeps the v0.1 modeling formulation, but raises the interactive output stream from 192x336 to 640x368 while preserving approximately 200 ms model-side signal-to-signal latency at 25 FPS. The higher-resolution stream supports scene-grounded mid-shot agents whose posture, gaze, hands, nearby objects, and local scene layout remain legible during real-time conversation. To support the larger visual stream without adding user-visible delay, v0.2 keeps the thinker as a "},"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":"2607.04443","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-05T18:05:20Z","cross_cats_sorted":["cs.AI","cs.GR","cs.LG"],"title_canon_sha256":"9c5c9edd3759ff39fadf01d2a47d1d8e70f44495ecde80cce9902fc7ec00c24b","abstract_canon_sha256":"977af8c130a7bdcae0359946943665a7f8ae4c999a1f6f8e24c584eed0c7bf92"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:19:19.631523Z","signature_b64":"Ut9FO3ZcqcGpnCvX/31Te8ioURgdNnm1KzK5241ZFFTATnpEOcvQW6j4MMhqFZimPkwARCANYOXmN2/AfDveCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cbb2bfe2d1828d2f428ee8e2f76617f72efe8f120dfc9a5d8fbb55058ac633b","last_reissued_at":"2026-07-07T02:19:19.630791Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:19:19.630791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Wan-Streamer v0.2: Higher Resolution, Same Latency","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ang Wang, Bang Zhang, Baole Ai, Cheng Yu, Chen Liang, Chen-Wei Xie, Chongyang Zhong, Jingren Zhou, Jinwei Qi, Junjie He, Kai Zhu, Lianghua Huang, Mengyang Feng, Pandeng Li, Peng Zhang, Wei Wang, Wenyuan Zhang, Xinhua Cheng, Yitong Huang, Yu Liu, Yun Zheng, Yupeng Shi, Yuxiang Bao, Yuzheng Wang, Zhi-Fan Wu, Zoubin Bi","submitted_at":"2026-07-05T18:05:20Z","abstract_excerpt":"We present Wan-Streamer v0.2, a latency-preserving upgrade of the native-streaming, end-to-end audio-visual interaction model. v0.2 keeps the v0.1 modeling formulation, but raises the interactive output stream from 192x336 to 640x368 while preserving approximately 200 ms model-side signal-to-signal latency at 25 FPS. The higher-resolution stream supports scene-grounded mid-shot agents whose posture, gaze, hands, nearby objects, and local scene layout remain legible during real-time conversation. To support the larger visual stream without adding user-visible delay, v0.2 keeps the thinker as a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04443","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/2607.04443/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":"2607.04443","created_at":"2026-07-07T02:19:19.630939+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.04443v1","created_at":"2026-07-07T02:19:19.630939+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04443","created_at":"2026-07-07T02:19:19.630939+00:00"},{"alias_kind":"pith_short_12","alias_value":"LS5SX7RNDAUN","created_at":"2026-07-07T02:19:19.630939+00:00"},{"alias_kind":"pith_short_16","alias_value":"LS5SX7RNDAUNF5BI","created_at":"2026-07-07T02:19:19.630939+00:00"},{"alias_kind":"pith_short_8","alias_value":"LS5SX7RN","created_at":"2026-07-07T02:19:19.630939+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/LS5SX7RNDAUNF5BI52HC65TBP5","json":"https://pith.science/pith/LS5SX7RNDAUNF5BI52HC65TBP5.json","graph_json":"https://pith.science/api/pith-number/LS5SX7RNDAUNF5BI52HC65TBP5/graph.json","events_json":"https://pith.science/api/pith-number/LS5SX7RNDAUNF5BI52HC65TBP5/events.json","paper":"https://pith.science/paper/LS5SX7RN"},"agent_actions":{"view_html":"https://pith.science/pith/LS5SX7RNDAUNF5BI52HC65TBP5","download_json":"https://pith.science/pith/LS5SX7RNDAUNF5BI52HC65TBP5.json","view_paper":"https://pith.science/paper/LS5SX7RN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.04443&json=true","fetch_graph":"https://pith.science/api/pith-number/LS5SX7RNDAUNF5BI52HC65TBP5/graph.json","fetch_events":"https://pith.science/api/pith-number/LS5SX7RNDAUNF5BI52HC65TBP5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LS5SX7RNDAUNF5BI52HC65TBP5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LS5SX7RNDAUNF5BI52HC65TBP5/action/storage_attestation","attest_author":"https://pith.science/pith/LS5SX7RNDAUNF5BI52HC65TBP5/action/author_attestation","sign_citation":"https://pith.science/pith/LS5SX7RNDAUNF5BI52HC65TBP5/action/citation_signature","submit_replication":"https://pith.science/pith/LS5SX7RNDAUNF5BI52HC65TBP5/action/replication_record"}},"created_at":"2026-07-07T02:19:19.630939+00:00","updated_at":"2026-07-07T02:19:19.630939+00:00"}