{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XELZR3XN2RZLRNDV6IXNVGNEMN","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":"31287a4a1a0bce569b192e84d0fbf4ca8c2c84f6e4c691488f716fd6e8c3b7a7","cross_cats_sorted":["cs.AI","cs.GR","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-23T18:01:03Z","title_canon_sha256":"e71a83a870e066c464089bd8c729029c0ffc2154ed4222a3544db3f6f24b9357"},"schema_version":"1.0","source":{"id":"2606.25041","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.25041","created_at":"2026-06-25T00:18:15Z"},{"alias_kind":"arxiv_version","alias_value":"2606.25041v1","created_at":"2026-06-25T00:18:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25041","created_at":"2026-06-25T00:18:15Z"},{"alias_kind":"pith_short_12","alias_value":"XELZR3XN2RZL","created_at":"2026-06-25T00:18:15Z"},{"alias_kind":"pith_short_16","alias_value":"XELZR3XN2RZLRNDV","created_at":"2026-06-25T00:18:15Z"},{"alias_kind":"pith_short_8","alias_value":"XELZR3XN","created_at":"2026-06-25T00:18:15Z"}],"graph_snapshots":[{"event_id":"sha256:de56e2933a88ef3bf84d19d796c50a24cd7875d558fc54cc319d4d41453d9fd8","target":"graph","created_at":"2026-06-25T00:18:15Z","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/2606.25041/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Wan-Streamer, a native-streaming, end-to-end interactive foundation model designed from the ground up for real-time, low-latency, full-duplex audio-visual interaction. Wan-Streamer seamlessly models language, audio, and video as both input and output within a single Transformer, where the sequence is represented as interleaved visual, audio, and text input tokens together with visual, audio, and text output tokens, coordinated by block-causal attention for incremental streaming. Unlike cascaded interactive systems that rely on separate VAD, ASR, language, TTS, audio-driven animation","authors_text":"Ang Wang, Bang Zhang, Baole Ai, Cheng Yu, Chen Liang, Chenwei 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, Zhifan Wu, Zoubin Bi","cross_cats":["cs.AI","cs.GR","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-23T18:01:03Z","title":"Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25041","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:bed6fbed0746ece41bb4ab8e06685c6ecf322e58f1dbcefb955f560a3bd2763f","target":"record","created_at":"2026-06-25T00:18:15Z","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":"31287a4a1a0bce569b192e84d0fbf4ca8c2c84f6e4c691488f716fd6e8c3b7a7","cross_cats_sorted":["cs.AI","cs.GR","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-23T18:01:03Z","title_canon_sha256":"e71a83a870e066c464089bd8c729029c0ffc2154ed4222a3544db3f6f24b9357"},"schema_version":"1.0","source":{"id":"2606.25041","kind":"arxiv","version":1}},"canonical_sha256":"b91798eeedd472b8b475f22eda99a4635eb0ee73aa8950fb18be9d367200dea7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b91798eeedd472b8b475f22eda99a4635eb0ee73aa8950fb18be9d367200dea7","first_computed_at":"2026-06-25T00:18:15.827798Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-25T00:18:15.827798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l8guWtrJciiqmgxDxJlAtgI7IzIeMv7YesigiL/XE6l2KJcrOE5vXJRXbfGDhz2d18c9rVd9Of0NGIU+WLCEDQ==","signature_status":"signed_v1","signed_at":"2026-06-25T00:18:15.828299Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.25041","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bed6fbed0746ece41bb4ab8e06685c6ecf322e58f1dbcefb955f560a3bd2763f","sha256:de56e2933a88ef3bf84d19d796c50a24cd7875d558fc54cc319d4d41453d9fd8"],"state_sha256":"8a6f2c76a339b5dfe8059eab69195563ae39ef17e2e6d865896b5bc671e268a0"}