{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NM7MPVXDDP4Y3OVQJCAUZ2YQ2D","short_pith_number":"pith:NM7MPVXD","schema_version":"1.0","canonical_sha256":"6b3ec7d6e31bf98dbab048814ceb10d0e396fbd9a4c0ca09c1f1d30f9d2ee253","source":{"kind":"arxiv","id":"2308.04352","version":1},"attestation_state":"computed","paper":{"title":"3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qing Li, Siyuan Huang, Xiaojian Ma, Yixin Chen, Zhidong Deng, Ziyu Zhu","submitted_at":"2023-08-08T15:59:17Z","abstract_excerpt":"3D vision-language grounding (3D-VL) is an emerging field that aims to connect the 3D physical world with natural language, which is crucial for achieving embodied intelligence. Current 3D-VL models rely heavily on sophisticated modules, auxiliary losses, and optimization tricks, which calls for a simple and unified model. In this paper, we propose 3D-VisTA, a pre-trained Transformer for 3D Vision and Text Alignment that can be easily adapted to various downstream tasks. 3D-VisTA simply utilizes self-attention layers for both single-modal modeling and multi-modal fusion without any sophisticat"},"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":"2308.04352","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-08T15:59:17Z","cross_cats_sorted":[],"title_canon_sha256":"d4fad566b5ca4cb69974537f1bb2ede4b7888f9c765e128b75af2bd994e607b5","abstract_canon_sha256":"6f3713e082bc4ccf8ee79099849dd9f42f25c1865feeacc68871fb7faf546acf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:39:26.426995Z","signature_b64":"Heka8JeDh4yxUzsMiKitFW000ReE4uL5rEQUfI1BTEowT45epiwL+nh5Lsb+zOCIJukldtbhBvLndkA1qzh/Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b3ec7d6e31bf98dbab048814ceb10d0e396fbd9a4c0ca09c1f1d30f9d2ee253","last_reissued_at":"2026-07-05T06:39:26.426521Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:39:26.426521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qing Li, Siyuan Huang, Xiaojian Ma, Yixin Chen, Zhidong Deng, Ziyu Zhu","submitted_at":"2023-08-08T15:59:17Z","abstract_excerpt":"3D vision-language grounding (3D-VL) is an emerging field that aims to connect the 3D physical world with natural language, which is crucial for achieving embodied intelligence. Current 3D-VL models rely heavily on sophisticated modules, auxiliary losses, and optimization tricks, which calls for a simple and unified model. In this paper, we propose 3D-VisTA, a pre-trained Transformer for 3D Vision and Text Alignment that can be easily adapted to various downstream tasks. 3D-VisTA simply utilizes self-attention layers for both single-modal modeling and multi-modal fusion without any sophisticat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.04352","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/2308.04352/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":"2308.04352","created_at":"2026-07-05T06:39:26.426608+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.04352v1","created_at":"2026-07-05T06:39:26.426608+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.04352","created_at":"2026-07-05T06:39:26.426608+00:00"},{"alias_kind":"pith_short_12","alias_value":"NM7MPVXDDP4Y","created_at":"2026-07-05T06:39:26.426608+00:00"},{"alias_kind":"pith_short_16","alias_value":"NM7MPVXDDP4Y3OVQ","created_at":"2026-07-05T06:39:26.426608+00:00"},{"alias_kind":"pith_short_8","alias_value":"NM7MPVXD","created_at":"2026-07-05T06:39:26.426608+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/NM7MPVXDDP4Y3OVQJCAUZ2YQ2D","json":"https://pith.science/pith/NM7MPVXDDP4Y3OVQJCAUZ2YQ2D.json","graph_json":"https://pith.science/api/pith-number/NM7MPVXDDP4Y3OVQJCAUZ2YQ2D/graph.json","events_json":"https://pith.science/api/pith-number/NM7MPVXDDP4Y3OVQJCAUZ2YQ2D/events.json","paper":"https://pith.science/paper/NM7MPVXD"},"agent_actions":{"view_html":"https://pith.science/pith/NM7MPVXDDP4Y3OVQJCAUZ2YQ2D","download_json":"https://pith.science/pith/NM7MPVXDDP4Y3OVQJCAUZ2YQ2D.json","view_paper":"https://pith.science/paper/NM7MPVXD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.04352&json=true","fetch_graph":"https://pith.science/api/pith-number/NM7MPVXDDP4Y3OVQJCAUZ2YQ2D/graph.json","fetch_events":"https://pith.science/api/pith-number/NM7MPVXDDP4Y3OVQJCAUZ2YQ2D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NM7MPVXDDP4Y3OVQJCAUZ2YQ2D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NM7MPVXDDP4Y3OVQJCAUZ2YQ2D/action/storage_attestation","attest_author":"https://pith.science/pith/NM7MPVXDDP4Y3OVQJCAUZ2YQ2D/action/author_attestation","sign_citation":"https://pith.science/pith/NM7MPVXDDP4Y3OVQJCAUZ2YQ2D/action/citation_signature","submit_replication":"https://pith.science/pith/NM7MPVXDDP4Y3OVQJCAUZ2YQ2D/action/replication_record"}},"created_at":"2026-07-05T06:39:26.426608+00:00","updated_at":"2026-07-05T06:39:26.426608+00:00"}