{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PGIX3K5A3UNML3I27TSJN6AYEN","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":"3ef30cd3494e7734d2c2bceec421c0e82b86bcc4ecf08e1111e57a15bc012fb7","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-07-07T17:49:41Z","title_canon_sha256":"f69dde350605d567fc41df7d4b7f7a3bb1e7916a1f4d1ba1578e29c0918b01f0"},"schema_version":"1.0","source":{"id":"2507.05240","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.05240","created_at":"2026-07-05T11:33:11Z"},{"alias_kind":"arxiv_version","alias_value":"2507.05240v1","created_at":"2026-07-05T11:33:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05240","created_at":"2026-07-05T11:33:11Z"},{"alias_kind":"pith_short_12","alias_value":"PGIX3K5A3UNM","created_at":"2026-07-05T11:33:11Z"},{"alias_kind":"pith_short_16","alias_value":"PGIX3K5A3UNML3I2","created_at":"2026-07-05T11:33:11Z"},{"alias_kind":"pith_short_8","alias_value":"PGIX3K5A","created_at":"2026-07-05T11:33:11Z"}],"graph_snapshots":[{"event_id":"sha256:5b9858b3be4fc12421958f59722ba7f0fc31546338efb00e2588a4099485b6e7","target":"graph","created_at":"2026-07-05T11:33:11Z","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/2507.05240/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-and-Language Navigation (VLN) in real-world settings requires agents to process continuous visual streams and generate actions with low latency grounded in language instructions. While Video-based Large Language Models (Video-LLMs) have driven recent progress, current VLN methods based on Video-LLM often face trade-offs among fine-grained visual understanding, long-term context modeling and computational efficiency. We introduce StreamVLN, a streaming VLN framework that employs a hybrid slow-fast context modeling strategy to support multi-modal reasoning over interleaved vision, languag","authors_text":"Chenming Zhu, Chenyang Wan, Hanqing Wang, Jiangmiao Pang, Meng Wei, Tai Wang, Wenzhe Cai, Xiaohan Mao, Xihui Liu, Xiqian Yu, Yilun Chen, Yuqiang Yang","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-07-07T17:49:41Z","title":"StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05240","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":"sha256:68c45e4bbe71b65ab3f15b996b424e3031e7a9b7061af2f580d8c1ced58ce553","target":"record","created_at":"2026-07-05T11:33:11Z","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":"3ef30cd3494e7734d2c2bceec421c0e82b86bcc4ecf08e1111e57a15bc012fb7","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-07-07T17:49:41Z","title_canon_sha256":"f69dde350605d567fc41df7d4b7f7a3bb1e7916a1f4d1ba1578e29c0918b01f0"},"schema_version":"1.0","source":{"id":"2507.05240","kind":"arxiv","version":1}},"canonical_sha256":"79917daba0dd1ac5ed1afce496f81823759426d70fae4338917caca219a88b3c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"79917daba0dd1ac5ed1afce496f81823759426d70fae4338917caca219a88b3c","first_computed_at":"2026-07-05T11:33:11.054777Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:11.054777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JiCmnegp4rr+YZBp20NgCJGfLxBbv0KHC4R8ff3D+eRcbJX2EhePssJdAWHSciVREiQpkkELHCDIsz3LDw1xDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:11.055224Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.05240","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68c45e4bbe71b65ab3f15b996b424e3031e7a9b7061af2f580d8c1ced58ce553","sha256:5b9858b3be4fc12421958f59722ba7f0fc31546338efb00e2588a4099485b6e7"],"state_sha256":"f1d609cff81bc7adc828d46080a7bd73fc82c09b9a7272fb550f405d347e1b30"}