{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XMYN34CC5MTNE7D2EOYAAZA62Q","short_pith_number":"pith:XMYN34CC","schema_version":"1.0","canonical_sha256":"bb30ddf042eb26d27c7a23b000641ed43c95a1e26f297dbea76ee92631467b00","source":{"kind":"arxiv","id":"2603.07690","version":3},"attestation_state":"computed","paper":{"title":"FrameVGGT: Coherence-Preserving Memory for Bounded Streaming Geometry","license":"http://creativecommons.org/licenses/by/4.0/","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.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Takeshi Oishi, Zhisong Xu","submitted_at":"2026-03-08T15:46:03Z","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":true},"canonical_record":{"source":{"id":"2603.07690","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-08T15:46:03Z","cross_cats_sorted":[],"title_canon_sha256":"4a63c5b611948f8c86e6b6f2a2bdba96eeeec16e02bb64bea656fdecdd653af9","abstract_canon_sha256":"b21d3b1ade17b8730879640b9150582000fdd022ec9c831b48d21e1bb64f70ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:12:47.605799Z","signature_b64":"bSIjdAWwzgspCCIhfMEQ7akWbALugmVkiLefEUpnFh6Dfhkw17/VoQArUqjPJe42DwU8smk2QvVId9dgNKpiDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb30ddf042eb26d27c7a23b000641ed43c95a1e26f297dbea76ee92631467b00","last_reissued_at":"2026-06-23T02:12:47.605307Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:12:47.605307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FrameVGGT: Coherence-Preserving Memory for Bounded Streaming Geometry","license":"http://creativecommons.org/licenses/by/4.0/","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.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Takeshi Oishi, Zhisong Xu","submitted_at":"2026-03-08T15:46:03Z","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 "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"FrameVGGT achieves favorable accuracy-memory trade-offs under bounded memory while maintaining more stable geometry over long streams.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","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.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"FrameVGGT replaces token-level KV retention with frame-level segments and prototypes to bound memory while preserving geometric coherence in streaming VGGT.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","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.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"940aeae480cac530028440f743e52d7db1fbd99b466bc554a886ab8d6d93ffe1"},"source":{"id":"2603.07690","kind":"arxiv","version":3},"verdict":{"id":"d6ea017a-ab35-4d2d-a978-005b4ef1762a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T14:38:34.411159Z","strongest_claim":"FrameVGGT achieves favorable accuracy-memory trade-offs under bounded memory while maintaining more stable geometry over long streams.","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","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.","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."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.07690/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"f2db97f0649de34b3fc64622a7e590bd1af6371145185fe36c91be8afe041cbc"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2603.07690","created_at":"2026-06-23T02:12:47.605377+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.07690v3","created_at":"2026-06-23T02:12:47.605377+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.07690","created_at":"2026-06-23T02:12:47.605377+00:00"},{"alias_kind":"pith_short_12","alias_value":"XMYN34CC5MTN","created_at":"2026-06-23T02:12:47.605377+00:00"},{"alias_kind":"pith_short_16","alias_value":"XMYN34CC5MTNE7D2","created_at":"2026-06-23T02:12:47.605377+00:00"},{"alias_kind":"pith_short_8","alias_value":"XMYN34CC","created_at":"2026-06-23T02:12:47.605377+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2606.27071","citing_title":"PanoImager: Geometry-Guided Novel View Synthesis and Reconstruction from Sparse Panoramic Views","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2606.29738","citing_title":"MyGO-Splat: Multi-Objective Closed-Loop Geometric Feedback for RGB-Only Gaussian SLAM","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23892","citing_title":"Good Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry Transformers","ref_index":99,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XMYN34CC5MTNE7D2EOYAAZA62Q","json":"https://pith.science/pith/XMYN34CC5MTNE7D2EOYAAZA62Q.json","graph_json":"https://pith.science/api/pith-number/XMYN34CC5MTNE7D2EOYAAZA62Q/graph.json","events_json":"https://pith.science/api/pith-number/XMYN34CC5MTNE7D2EOYAAZA62Q/events.json","paper":"https://pith.science/paper/XMYN34CC"},"agent_actions":{"view_html":"https://pith.science/pith/XMYN34CC5MTNE7D2EOYAAZA62Q","download_json":"https://pith.science/pith/XMYN34CC5MTNE7D2EOYAAZA62Q.json","view_paper":"https://pith.science/paper/XMYN34CC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.07690&json=true","fetch_graph":"https://pith.science/api/pith-number/XMYN34CC5MTNE7D2EOYAAZA62Q/graph.json","fetch_events":"https://pith.science/api/pith-number/XMYN34CC5MTNE7D2EOYAAZA62Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XMYN34CC5MTNE7D2EOYAAZA62Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XMYN34CC5MTNE7D2EOYAAZA62Q/action/storage_attestation","attest_author":"https://pith.science/pith/XMYN34CC5MTNE7D2EOYAAZA62Q/action/author_attestation","sign_citation":"https://pith.science/pith/XMYN34CC5MTNE7D2EOYAAZA62Q/action/citation_signature","submit_replication":"https://pith.science/pith/XMYN34CC5MTNE7D2EOYAAZA62Q/action/replication_record"}},"created_at":"2026-06-23T02:12:47.605377+00:00","updated_at":"2026-06-23T02:12:47.605377+00:00"}