{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6XTUCQNZXUEC4T6Q2MWL3ONEGU","short_pith_number":"pith:6XTUCQNZ","schema_version":"1.0","canonical_sha256":"f5e74141b9bd082e4fd0d32cbdb9a43524c7a760d3b931b7aaab62768197c9a4","source":{"kind":"arxiv","id":"2505.24245","version":1},"attestation_state":"computed","paper":{"title":"LTM3D: Bridging Token Spaces for Conditional 3D Generation with Auto-Regressive Diffusion Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hao Pan, Jiahao Li, Lei Chu, Xin Kang, Xuejin Chen, Yan Lu, Yue Gao, Zihan Zheng","submitted_at":"2025-05-30T06:08:45Z","abstract_excerpt":"We present LTM3D, a Latent Token space Modeling framework for conditional 3D shape generation that integrates the strengths of diffusion and auto-regressive (AR) models. While diffusion-based methods effectively model continuous latent spaces and AR models excel at capturing inter-token dependencies, combining these paradigms for 3D shape generation remains a challenge. To address this, LTM3D features a Conditional Distribution Modeling backbone, leveraging a masked autoencoder and a diffusion model to enhance token dependency learning. Additionally, we introduce Prefix Learning, which aligns "},"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":"2505.24245","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T06:08:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7a0e12900b35aeb971b8f0534f8ac9288bcd6e2da5605b49d4ba1f6fe9e5e2b4","abstract_canon_sha256":"bce410d288a923eeaaeb56680cd6ba27bda5790bb07aeb7cdaa6f9006913f266"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:44.987964Z","signature_b64":"LmLglQRKuVj4d9Pq3KNKq72WD9Vc2CsxQ9UBv1FcqQ8/5+Xk11l/SwWZ17Uhv/0DJyF/yZ4Eq2XZm7UAlh5rAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5e74141b9bd082e4fd0d32cbdb9a43524c7a760d3b931b7aaab62768197c9a4","last_reissued_at":"2026-07-05T11:12:44.987403Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:44.987403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LTM3D: Bridging Token Spaces for Conditional 3D Generation with Auto-Regressive Diffusion Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hao Pan, Jiahao Li, Lei Chu, Xin Kang, Xuejin Chen, Yan Lu, Yue Gao, Zihan Zheng","submitted_at":"2025-05-30T06:08:45Z","abstract_excerpt":"We present LTM3D, a Latent Token space Modeling framework for conditional 3D shape generation that integrates the strengths of diffusion and auto-regressive (AR) models. While diffusion-based methods effectively model continuous latent spaces and AR models excel at capturing inter-token dependencies, combining these paradigms for 3D shape generation remains a challenge. To address this, LTM3D features a Conditional Distribution Modeling backbone, leveraging a masked autoencoder and a diffusion model to enhance token dependency learning. Additionally, we introduce Prefix Learning, which aligns "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24245","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/2505.24245/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":"2505.24245","created_at":"2026-07-05T11:12:44.987467+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.24245v1","created_at":"2026-07-05T11:12:44.987467+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24245","created_at":"2026-07-05T11:12:44.987467+00:00"},{"alias_kind":"pith_short_12","alias_value":"6XTUCQNZXUEC","created_at":"2026-07-05T11:12:44.987467+00:00"},{"alias_kind":"pith_short_16","alias_value":"6XTUCQNZXUEC4T6Q","created_at":"2026-07-05T11:12:44.987467+00:00"},{"alias_kind":"pith_short_8","alias_value":"6XTUCQNZ","created_at":"2026-07-05T11:12:44.987467+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/6XTUCQNZXUEC4T6Q2MWL3ONEGU","json":"https://pith.science/pith/6XTUCQNZXUEC4T6Q2MWL3ONEGU.json","graph_json":"https://pith.science/api/pith-number/6XTUCQNZXUEC4T6Q2MWL3ONEGU/graph.json","events_json":"https://pith.science/api/pith-number/6XTUCQNZXUEC4T6Q2MWL3ONEGU/events.json","paper":"https://pith.science/paper/6XTUCQNZ"},"agent_actions":{"view_html":"https://pith.science/pith/6XTUCQNZXUEC4T6Q2MWL3ONEGU","download_json":"https://pith.science/pith/6XTUCQNZXUEC4T6Q2MWL3ONEGU.json","view_paper":"https://pith.science/paper/6XTUCQNZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.24245&json=true","fetch_graph":"https://pith.science/api/pith-number/6XTUCQNZXUEC4T6Q2MWL3ONEGU/graph.json","fetch_events":"https://pith.science/api/pith-number/6XTUCQNZXUEC4T6Q2MWL3ONEGU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6XTUCQNZXUEC4T6Q2MWL3ONEGU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6XTUCQNZXUEC4T6Q2MWL3ONEGU/action/storage_attestation","attest_author":"https://pith.science/pith/6XTUCQNZXUEC4T6Q2MWL3ONEGU/action/author_attestation","sign_citation":"https://pith.science/pith/6XTUCQNZXUEC4T6Q2MWL3ONEGU/action/citation_signature","submit_replication":"https://pith.science/pith/6XTUCQNZXUEC4T6Q2MWL3ONEGU/action/replication_record"}},"created_at":"2026-07-05T11:12:44.987467+00:00","updated_at":"2026-07-05T11:12:44.987467+00:00"}