{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:L6TZCUV5OYB5IU2FYWSKULNMAP","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":"3ebd3f97994f542faedd87b916c47a52d9ad9ec014840e5c72b83bfe2b9e88e3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-28T11:42:55Z","title_canon_sha256":"9ec0558fda28c89f92226d6623f8176a296421042660202c89698ab372648b11"},"schema_version":"1.0","source":{"id":"2606.29350","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.29350","created_at":"2026-06-30T01:18:02Z"},{"alias_kind":"arxiv_version","alias_value":"2606.29350v1","created_at":"2026-06-30T01:18:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29350","created_at":"2026-06-30T01:18:02Z"},{"alias_kind":"pith_short_12","alias_value":"L6TZCUV5OYB5","created_at":"2026-06-30T01:18:02Z"},{"alias_kind":"pith_short_16","alias_value":"L6TZCUV5OYB5IU2F","created_at":"2026-06-30T01:18:02Z"},{"alias_kind":"pith_short_8","alias_value":"L6TZCUV5","created_at":"2026-06-30T01:18:02Z"}],"graph_snapshots":[{"event_id":"sha256:9c21b06c4a8ad8a62302d701d4351dd6c1a043adb933291bc79ec57fecedaf99","target":"graph","created_at":"2026-06-30T01:18:02Z","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/2606.29350/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models and vision-language action models endow the robot with unprecedented capabilities. However, the input of video and high-resolution images yields a massive number of visual tokens, leading to extremely high inference latency and severely hindering the robot's real-time control. To break through this computational bottleneck, we propose ST-Merge, a plug-and-play, training-free framework that efficiently fuses redundant tokens directly during the visual encoding phase. By explicitly constructing 3D spatiotemporal coordinates, it employs a multi-queue parallel matching and w","authors_text":"Gang Zhou, Jindong Wang, Junzhou Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-28T11:42:55Z","title":"Fast Enough to Act: Spatio-Temporal Visual Token Merging for Low-Latency Robotic VLMs and VLAs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29350","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":"sha256:97e282e9d081dc6b582e3862cac23e1d28b7a11fecca7abd39c29bc1b3800a02","target":"record","created_at":"2026-06-30T01:18:02Z","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":"3ebd3f97994f542faedd87b916c47a52d9ad9ec014840e5c72b83bfe2b9e88e3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-28T11:42:55Z","title_canon_sha256":"9ec0558fda28c89f92226d6623f8176a296421042660202c89698ab372648b11"},"schema_version":"1.0","source":{"id":"2606.29350","kind":"arxiv","version":1}},"canonical_sha256":"5fa79152bd7603d45345c5a4aa2dac03e9554f5e0dc8878e4a9de747f10d5399","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5fa79152bd7603d45345c5a4aa2dac03e9554f5e0dc8878e4a9de747f10d5399","first_computed_at":"2026-06-30T01:18:02.385752Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:18:02.385752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GqHeNAI+/f7dER0oRSsR0tyzejgD7iPwaoHCybYPSwUqT1aC3u43v+D5EGcxKQ6iwApq2zZ8fY65wH71bze9BQ==","signature_status":"signed_v1","signed_at":"2026-06-30T01:18:02.386241Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.29350","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97e282e9d081dc6b582e3862cac23e1d28b7a11fecca7abd39c29bc1b3800a02","sha256:9c21b06c4a8ad8a62302d701d4351dd6c1a043adb933291bc79ec57fecedaf99"],"state_sha256":"3adfa87fc7b110f818ec5048c8c2d3f71a809de5aa070c84fcd92cea01423c58"}