{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M7AODW3MXFN6RKSTJH6LLRB3AB","short_pith_number":"pith:M7AODW3M","schema_version":"1.0","canonical_sha256":"67c0e1db6cb95be8aa5349fcb5c43b007cad418c570ef43748f9331d67a71ca0","source":{"kind":"arxiv","id":"2411.16856","version":3},"attestation_state":"computed","paper":{"title":"SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shangchen Zhou, Tengfei Wang, Xingang Pan, Yongwei Chen, Yushi Lan","submitted_at":"2024-11-25T19:00:05Z","abstract_excerpt":"Autoregressive models have demonstrated remarkable success across various fields, from large language models (LLMs) to large multimodal models (LMMs) and 2D content generation, moving closer to artificial general intelligence (AGI). Despite these advances, applying autoregressive approaches to 3D object generation and understanding remains largely unexplored. This paper introduces Scale AutoRegressive 3D (SAR3D), a novel framework that leverages a multi-scale 3D vector-quantized variational autoencoder (VQVAE) to tokenize 3D objects for efficient autoregressive generation and detailed understa"},"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":"2411.16856","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T19:00:05Z","cross_cats_sorted":[],"title_canon_sha256":"d85db0db8a2b7cace4481f623010f6d9480e22b784af5461378763d70aa62762","abstract_canon_sha256":"c10ea24b2a2ff538057d3f0d2231f5952fd917c4037f1378f840601a39b20d5c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:37:38.584202Z","signature_b64":"cisYPktEJmGRXpNy/wk5Q6MpDjPvaV79u2Bmj5iYH0Cdxr/9UIfGAMijuxVOt1dL03GlnTIfPIddauNkp1VECA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67c0e1db6cb95be8aa5349fcb5c43b007cad418c570ef43748f9331d67a71ca0","last_reissued_at":"2026-07-05T10:37:38.583673Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:37:38.583673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shangchen Zhou, Tengfei Wang, Xingang Pan, Yongwei Chen, Yushi Lan","submitted_at":"2024-11-25T19:00:05Z","abstract_excerpt":"Autoregressive models have demonstrated remarkable success across various fields, from large language models (LLMs) to large multimodal models (LMMs) and 2D content generation, moving closer to artificial general intelligence (AGI). Despite these advances, applying autoregressive approaches to 3D object generation and understanding remains largely unexplored. This paper introduces Scale AutoRegressive 3D (SAR3D), a novel framework that leverages a multi-scale 3D vector-quantized variational autoencoder (VQVAE) to tokenize 3D objects for efficient autoregressive generation and detailed understa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16856","kind":"arxiv","version":3},"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/2411.16856/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":"2411.16856","created_at":"2026-07-05T10:37:38.583740+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.16856v3","created_at":"2026-07-05T10:37:38.583740+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16856","created_at":"2026-07-05T10:37:38.583740+00:00"},{"alias_kind":"pith_short_12","alias_value":"M7AODW3MXFN6","created_at":"2026-07-05T10:37:38.583740+00:00"},{"alias_kind":"pith_short_16","alias_value":"M7AODW3MXFN6RKST","created_at":"2026-07-05T10:37:38.583740+00:00"},{"alias_kind":"pith_short_8","alias_value":"M7AODW3M","created_at":"2026-07-05T10:37:38.583740+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.21798","citing_title":"CG-MLLM: Captioning and Generating 3D content via Multi-modal Large Language Models","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M7AODW3MXFN6RKSTJH6LLRB3AB","json":"https://pith.science/pith/M7AODW3MXFN6RKSTJH6LLRB3AB.json","graph_json":"https://pith.science/api/pith-number/M7AODW3MXFN6RKSTJH6LLRB3AB/graph.json","events_json":"https://pith.science/api/pith-number/M7AODW3MXFN6RKSTJH6LLRB3AB/events.json","paper":"https://pith.science/paper/M7AODW3M"},"agent_actions":{"view_html":"https://pith.science/pith/M7AODW3MXFN6RKSTJH6LLRB3AB","download_json":"https://pith.science/pith/M7AODW3MXFN6RKSTJH6LLRB3AB.json","view_paper":"https://pith.science/paper/M7AODW3M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.16856&json=true","fetch_graph":"https://pith.science/api/pith-number/M7AODW3MXFN6RKSTJH6LLRB3AB/graph.json","fetch_events":"https://pith.science/api/pith-number/M7AODW3MXFN6RKSTJH6LLRB3AB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M7AODW3MXFN6RKSTJH6LLRB3AB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M7AODW3MXFN6RKSTJH6LLRB3AB/action/storage_attestation","attest_author":"https://pith.science/pith/M7AODW3MXFN6RKSTJH6LLRB3AB/action/author_attestation","sign_citation":"https://pith.science/pith/M7AODW3MXFN6RKSTJH6LLRB3AB/action/citation_signature","submit_replication":"https://pith.science/pith/M7AODW3MXFN6RKSTJH6LLRB3AB/action/replication_record"}},"created_at":"2026-07-05T10:37:38.583740+00:00","updated_at":"2026-07-05T10:37:38.583740+00:00"}