{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XMYN34CC5MTNE7D2EOYAAZA62Q","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":"b21d3b1ade17b8730879640b9150582000fdd022ec9c831b48d21e1bb64f70ac","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-08T15:46:03Z","title_canon_sha256":"4a63c5b611948f8c86e6b6f2a2bdba96eeeec16e02bb64bea656fdecdd653af9"},"schema_version":"1.0","source":{"id":"2603.07690","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.07690","created_at":"2026-06-23T02:12:47Z"},{"alias_kind":"arxiv_version","alias_value":"2603.07690v3","created_at":"2026-06-23T02:12:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.07690","created_at":"2026-06-23T02:12:47Z"},{"alias_kind":"pith_short_12","alias_value":"XMYN34CC5MTN","created_at":"2026-06-23T02:12:47Z"},{"alias_kind":"pith_short_16","alias_value":"XMYN34CC5MTNE7D2","created_at":"2026-06-23T02:12:47Z"},{"alias_kind":"pith_short_8","alias_value":"XMYN34CC","created_at":"2026-06-23T02:12:47Z"}],"graph_snapshots":[{"event_id":"sha256:b838b75a818705404bfc85c615e815a851d1890f159e565aee9c0dabbdd40cfc","target":"graph","created_at":"2026-06-23T02:12:47Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"FrameVGGT achieves favorable accuracy-memory trade-offs under bounded memory while maintaining more stable geometry over long streams."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That token-level retention fragments within-frame evidence and that summarizing segments with lightweight key-space prototypes preserves the redundant multi-view support needed for coherent geometric reasoning."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"FrameVGGT replaces token-level KV retention with frame-level segments and prototypes to bound memory while preserving geometric coherence in streaming VGGT."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"FrameVGGT organizes each frame's KV contribution as a coherent segment summarized by key-space prototypes to bound memory while preserving multi-view geometric support in streaming VGGT."}],"snapshot_sha256":"940aeae480cac530028440f743e52d7db1fbd99b466bc554a886ab8d6d93ffe1"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"f2db97f0649de34b3fc64622a7e590bd1af6371145185fe36c91be8afe041cbc"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2603.07690/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Streaming Visual Geometry Transformers such as StreamVGGT enable strong online 3D perception, but their KV-cache grows unbounded over long streams, limiting practical deployment. We study bounded-memory streaming geometry from the perspective of memory organization: unlike language modeling, where useful information can often be compressed at token level, geometry-driven inference relies on coherent and mutually compatible observations across views. Under fixed memory budgets, retaining history as isolated entries can progressively fragment the geometric context needed for stable long-horizon ","authors_text":"Takeshi Oishi, Zhisong Xu","cross_cats":[],"headline":"FrameVGGT organizes each frame's KV contribution as a coherent segment summarized by key-space prototypes to bound memory while preserving multi-view geometric support in streaming VGGT.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-08T15:46:03Z","title":"FrameVGGT: Coherence-Preserving Memory for Bounded Streaming Geometry"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.07690","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-15T14:38:34.411159Z","id":"d6ea017a-ab35-4d2d-a978-005b4ef1762a","model_set":{"reader":"grok-4.3"},"one_line_summary":"FrameVGGT replaces token-level KV retention with frame-level segments and prototypes to bound memory while preserving geometric coherence in streaming VGGT.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"FrameVGGT organizes each frame's KV contribution as a coherent segment summarized by key-space prototypes to bound memory while preserving multi-view geometric support in streaming VGGT.","strongest_claim":"FrameVGGT achieves favorable accuracy-memory trade-offs under bounded memory while maintaining more stable geometry over long streams.","weakest_assumption":"That token-level retention fragments within-frame evidence and that summarizing segments with lightweight key-space prototypes preserves the redundant multi-view support needed for coherent geometric reasoning."}},"verdict_id":"d6ea017a-ab35-4d2d-a978-005b4ef1762a"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fa60fa84a9e8c950e80f7ab440980baa5c2ac659cd4aedc4b406c7de9b8c8096","target":"record","created_at":"2026-06-23T02:12:47Z","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":"b21d3b1ade17b8730879640b9150582000fdd022ec9c831b48d21e1bb64f70ac","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-08T15:46:03Z","title_canon_sha256":"4a63c5b611948f8c86e6b6f2a2bdba96eeeec16e02bb64bea656fdecdd653af9"},"schema_version":"1.0","source":{"id":"2603.07690","kind":"arxiv","version":3}},"canonical_sha256":"bb30ddf042eb26d27c7a23b000641ed43c95a1e26f297dbea76ee92631467b00","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb30ddf042eb26d27c7a23b000641ed43c95a1e26f297dbea76ee92631467b00","first_computed_at":"2026-06-23T02:12:47.605307Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:12:47.605307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bSIjdAWwzgspCCIhfMEQ7akWbALugmVkiLefEUpnFh6Dfhkw17/VoQArUqjPJe42DwU8smk2QvVId9dgNKpiDw==","signature_status":"signed_v1","signed_at":"2026-06-23T02:12:47.605799Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.07690","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fa60fa84a9e8c950e80f7ab440980baa5c2ac659cd4aedc4b406c7de9b8c8096","sha256:b838b75a818705404bfc85c615e815a851d1890f159e565aee9c0dabbdd40cfc"],"state_sha256":"b42a03f4136843d747d6a17f24928374515940e583ad5c54b18ce3b393c3b86d"}