{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RPLBO3KV7R4FQMCCK76ZYIYMT4","short_pith_number":"pith:RPLBO3KV","schema_version":"1.0","canonical_sha256":"8bd6176d55fc7858304257fd9c230c9f337357f73d12a0e7ca7a923db767a8e7","source":{"kind":"arxiv","id":"2605.31124","version":1},"attestation_state":"computed","paper":{"title":"QVGGT: Post-Training Quantized Visual Geometry Grounded Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hesong Wang, Huan Wang, Zhizhen Pan","submitted_at":"2026-05-29T10:32:52Z","abstract_excerpt":"Estimating 3D attributes directly from images has advanced rapidly with the Visual Geometry Grounded Transformer (VGGT), which predicts camera parameters, depth maps, and point clouds in a single forward pass. However, its 1.2B-parameter scale severely limits deployment on resource-constrained platforms such as UAVs and mobile AR devices. To address this limitation, we introduce QVGGT, a tailored quantization framework designed to compress VGGT. Our approach starts from the observation that transformer blocks within VGGT exhibit heterogeneous sensitivity to quantization. We thus analyze per-bl"},"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":false},"canonical_record":{"source":{"id":"2605.31124","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-29T10:32:52Z","cross_cats_sorted":[],"title_canon_sha256":"3f958877b035542f70b401eaf78d4f0a4e3fab29d389e62eb5cd22fe8f98c2c5","abstract_canon_sha256":"4a16be2454c87e57025a9cf6aeb53109d06960237335b7bb55eeb835ae0f47b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:59.380743Z","signature_b64":"09ETbj9UPdw849gx91hsO8v4JCHN1h8nv7Dyd5vRV7gxWaiTdFdUy+J9toNQOziBfKsoL0vNiTRXfVccae6oCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bd6176d55fc7858304257fd9c230c9f337357f73d12a0e7ca7a923db767a8e7","last_reissued_at":"2026-06-01T01:03:59.380056Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:59.380056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QVGGT: Post-Training Quantized Visual Geometry Grounded Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hesong Wang, Huan Wang, Zhizhen Pan","submitted_at":"2026-05-29T10:32:52Z","abstract_excerpt":"Estimating 3D attributes directly from images has advanced rapidly with the Visual Geometry Grounded Transformer (VGGT), which predicts camera parameters, depth maps, and point clouds in a single forward pass. However, its 1.2B-parameter scale severely limits deployment on resource-constrained platforms such as UAVs and mobile AR devices. To address this limitation, we introduce QVGGT, a tailored quantization framework designed to compress VGGT. Our approach starts from the observation that transformer blocks within VGGT exhibit heterogeneous sensitivity to quantization. We thus analyze per-bl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31124","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.31124/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":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"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":"2605.31124","created_at":"2026-06-01T01:03:59.380162+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.31124v1","created_at":"2026-06-01T01:03:59.380162+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31124","created_at":"2026-06-01T01:03:59.380162+00:00"},{"alias_kind":"pith_short_12","alias_value":"RPLBO3KV7R4F","created_at":"2026-06-01T01:03:59.380162+00:00"},{"alias_kind":"pith_short_16","alias_value":"RPLBO3KV7R4FQMCC","created_at":"2026-06-01T01:03:59.380162+00:00"},{"alias_kind":"pith_short_8","alias_value":"RPLBO3KV","created_at":"2026-06-01T01:03:59.380162+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RPLBO3KV7R4FQMCCK76ZYIYMT4","json":"https://pith.science/pith/RPLBO3KV7R4FQMCCK76ZYIYMT4.json","graph_json":"https://pith.science/api/pith-number/RPLBO3KV7R4FQMCCK76ZYIYMT4/graph.json","events_json":"https://pith.science/api/pith-number/RPLBO3KV7R4FQMCCK76ZYIYMT4/events.json","paper":"https://pith.science/paper/RPLBO3KV"},"agent_actions":{"view_html":"https://pith.science/pith/RPLBO3KV7R4FQMCCK76ZYIYMT4","download_json":"https://pith.science/pith/RPLBO3KV7R4FQMCCK76ZYIYMT4.json","view_paper":"https://pith.science/paper/RPLBO3KV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.31124&json=true","fetch_graph":"https://pith.science/api/pith-number/RPLBO3KV7R4FQMCCK76ZYIYMT4/graph.json","fetch_events":"https://pith.science/api/pith-number/RPLBO3KV7R4FQMCCK76ZYIYMT4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RPLBO3KV7R4FQMCCK76ZYIYMT4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RPLBO3KV7R4FQMCCK76ZYIYMT4/action/storage_attestation","attest_author":"https://pith.science/pith/RPLBO3KV7R4FQMCCK76ZYIYMT4/action/author_attestation","sign_citation":"https://pith.science/pith/RPLBO3KV7R4FQMCCK76ZYIYMT4/action/citation_signature","submit_replication":"https://pith.science/pith/RPLBO3KV7R4FQMCCK76ZYIYMT4/action/replication_record"}},"created_at":"2026-06-01T01:03:59.380162+00:00","updated_at":"2026-06-01T01:03:59.380162+00:00"}