{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6MIR5JPUDKQE43HD7FV6QEH2JC","short_pith_number":"pith:6MIR5JPU","schema_version":"1.0","canonical_sha256":"f3111ea5f41aa04e6ce3f96be810fa488db519134c281079ea1844cfb733ca0a","source":{"kind":"arxiv","id":"2601.20317","version":2},"attestation_state":"computed","paper":{"title":"VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Carol Jingyi Li, Ceyu Xu, Jiang Xu, Jintao Cheng, Jin Wu, Lin Jiang, Wei Zhang, Xingyu Liu, Yipu Zhang, Yuan Xie, Zeyu Li","submitted_at":"2026-01-28T07:21:32Z","abstract_excerpt":"3D reconstruction and view synthesis are fundamental to AR/VR, robotics, and digital twins. The Visual Geometry Grounded Transformer (VGGT) enables strong feed-forward 3D reconstruction while its billion-parameter scale limits on-device deployment. LLM-oriented quantization methods fail on VGGT due to saturated activation channels that resist low-bit quantization and diverse 3D semantics that impede calibration. VGGT further poses hardware challenges from multi-precision architecture support and long-sequence global attention with excessive memory demands. We propose VersaQ-3D, an algorithm-ar"},"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":"2601.20317","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2026-01-28T07:21:32Z","cross_cats_sorted":[],"title_canon_sha256":"83050196bd6ee3f75d025543e86e6b18f3380dd3ae04b32318cb59b91b106503","abstract_canon_sha256":"5dce6c03fe254e91e0f94452e41215d0ccb228679483faaf13d4ccbc07b064f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-16T00:21:44.858777Z","signature_b64":"oztvdD0l64qKp7fO1Dgv1oPwEgvEAtYcS6WYHJ0nczAgBYbk7/ZrtgvdNT4xZVdidjqnsQqqc2D78u8lRWwWCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3111ea5f41aa04e6ce3f96be810fa488db519134c281079ea1844cfb733ca0a","last_reissued_at":"2026-07-16T00:21:44.857871Z","signature_status":"signed_v1","first_computed_at":"2026-07-16T00:21:44.857871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Carol Jingyi Li, Ceyu Xu, Jiang Xu, Jintao Cheng, Jin Wu, Lin Jiang, Wei Zhang, Xingyu Liu, Yipu Zhang, Yuan Xie, Zeyu Li","submitted_at":"2026-01-28T07:21:32Z","abstract_excerpt":"3D reconstruction and view synthesis are fundamental to AR/VR, robotics, and digital twins. The Visual Geometry Grounded Transformer (VGGT) enables strong feed-forward 3D reconstruction while its billion-parameter scale limits on-device deployment. LLM-oriented quantization methods fail on VGGT due to saturated activation channels that resist low-bit quantization and diverse 3D semantics that impede calibration. VGGT further poses hardware challenges from multi-precision architecture support and long-sequence global attention with excessive memory demands. We propose VersaQ-3D, an algorithm-ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.20317","kind":"arxiv","version":2},"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/2601.20317/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":"2601.20317","created_at":"2026-07-16T00:21:44.858298+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.20317v2","created_at":"2026-07-16T00:21:44.858298+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.20317","created_at":"2026-07-16T00:21:44.858298+00:00"},{"alias_kind":"pith_short_12","alias_value":"6MIR5JPUDKQE","created_at":"2026-07-16T00:21:44.858298+00:00"},{"alias_kind":"pith_short_16","alias_value":"6MIR5JPUDKQE43HD","created_at":"2026-07-16T00:21:44.858298+00:00"},{"alias_kind":"pith_short_8","alias_value":"6MIR5JPU","created_at":"2026-07-16T00:21:44.858298+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.15828","citing_title":"Not All Tasks Quantize Equally: Fisher-Guided Quantization for Visual Geometry Transformer","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15828","citing_title":"Not All Tasks Quantize Equally: Fisher-Guided Quantization for Visual Geometry Transformer","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6MIR5JPUDKQE43HD7FV6QEH2JC","json":"https://pith.science/pith/6MIR5JPUDKQE43HD7FV6QEH2JC.json","graph_json":"https://pith.science/api/pith-number/6MIR5JPUDKQE43HD7FV6QEH2JC/graph.json","events_json":"https://pith.science/api/pith-number/6MIR5JPUDKQE43HD7FV6QEH2JC/events.json","paper":"https://pith.science/paper/6MIR5JPU"},"agent_actions":{"view_html":"https://pith.science/pith/6MIR5JPUDKQE43HD7FV6QEH2JC","download_json":"https://pith.science/pith/6MIR5JPUDKQE43HD7FV6QEH2JC.json","view_paper":"https://pith.science/paper/6MIR5JPU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.20317&json=true","fetch_graph":"https://pith.science/api/pith-number/6MIR5JPUDKQE43HD7FV6QEH2JC/graph.json","fetch_events":"https://pith.science/api/pith-number/6MIR5JPUDKQE43HD7FV6QEH2JC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6MIR5JPUDKQE43HD7FV6QEH2JC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6MIR5JPUDKQE43HD7FV6QEH2JC/action/storage_attestation","attest_author":"https://pith.science/pith/6MIR5JPUDKQE43HD7FV6QEH2JC/action/author_attestation","sign_citation":"https://pith.science/pith/6MIR5JPUDKQE43HD7FV6QEH2JC/action/citation_signature","submit_replication":"https://pith.science/pith/6MIR5JPUDKQE43HD7FV6QEH2JC/action/replication_record"}},"created_at":"2026-07-16T00:21:44.858298+00:00","updated_at":"2026-07-16T00:21:44.858298+00:00"}