{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FZIN6D5IB7GSEBAMFZAYZRVGM4","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":"6d82efe69f2f69b82126c425c6757aa6c7aabbb28984d20bba2ae366ecad1d3e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T09:07:15Z","title_canon_sha256":"f7ed18634fe121fb12078abf6243095b650157367c9f3763fc14e3eb50630ca3"},"schema_version":"1.0","source":{"id":"2606.07639","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07639","created_at":"2026-06-09T00:04:45Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07639v1","created_at":"2026-06-09T00:04:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07639","created_at":"2026-06-09T00:04:45Z"},{"alias_kind":"pith_short_12","alias_value":"FZIN6D5IB7GS","created_at":"2026-06-09T00:04:45Z"},{"alias_kind":"pith_short_16","alias_value":"FZIN6D5IB7GSEBAM","created_at":"2026-06-09T00:04:45Z"},{"alias_kind":"pith_short_8","alias_value":"FZIN6D5I","created_at":"2026-06-09T00:04:45Z"}],"graph_snapshots":[{"event_id":"sha256:809ff867b720c3f5214e6106aefcc5f8610ad4aaf5780693de219f799cbe346e","target":"graph","created_at":"2026-06-09T00:04:45Z","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/2606.07639/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video understanding is shifting from the offline paradigm -- taking a fully recorded video as input and producing a single answer after it ends -- toward real-time interaction, in which the model perceives new frames while still replying, revises its answer as new evidence appears, and remains silent when there is nothing to say. We present MOSS-Video-Preview to validate this paradigm. Our central claim is that perception must not be blocked by generation; its natural realization is a two-channel architecture. We argue that a cross-attention backbone is better suited to real-time vision-langua","authors_text":"Botian Jiang, Chenghao Liu, Chenghao Wang, Chenkun Tan, Hongkai Wang, Huazheng Zeng, Jijun Cheng, Pengfei Wang, Pengyu Wang, Qirui Zhou, Shanqing Gao, Shaojun Zhou, Wei Huang, Xiaomeng Qian, Xinghao Wang, Xingyang He, Xipeng Qiu, Yanxin Chen, Yixian Tian, Zhan Huang, Zhen Ye","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T09:07:15Z","title":"MOSS-Video-Preview: Toward Real-Time Video Understanding via Cross-Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07639","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":"sha256:581b8133f3dbededd95a252789e27c6b58b07199b4a4b6801ca0ba678ed4f205","target":"record","created_at":"2026-06-09T00:04:45Z","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":"6d82efe69f2f69b82126c425c6757aa6c7aabbb28984d20bba2ae366ecad1d3e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T09:07:15Z","title_canon_sha256":"f7ed18634fe121fb12078abf6243095b650157367c9f3763fc14e3eb50630ca3"},"schema_version":"1.0","source":{"id":"2606.07639","kind":"arxiv","version":1}},"canonical_sha256":"2e50df0fa80fcd22040c2e418cc6a6670dabb9b7d5cd0f3efd58bbc14d7c0981","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e50df0fa80fcd22040c2e418cc6a6670dabb9b7d5cd0f3efd58bbc14d7c0981","first_computed_at":"2026-06-09T00:04:45.521197Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T00:04:45.521197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XuknM2rBxhssDx0+OQIXVmqD1kqT0J5z4+VzMn/ocGwNZdQcYfxwqu7jCiOoABW/JHkONzC7ucQgv/XQ9lXQCQ==","signature_status":"signed_v1","signed_at":"2026-06-09T00:04:45.521596Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.07639","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:581b8133f3dbededd95a252789e27c6b58b07199b4a4b6801ca0ba678ed4f205","sha256:809ff867b720c3f5214e6106aefcc5f8610ad4aaf5780693de219f799cbe346e"],"state_sha256":"de23e8479aedff5097d64a4d7a8e79224d021fe942631789a46e5315bfe7f091"}