{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UNAPRGEWQBWDK5IBXRGUTJ76AL","short_pith_number":"pith:UNAPRGEW","schema_version":"1.0","canonical_sha256":"a340f89896806c357501bc4d49a7fe02def5fc7907ec29bbb264d0dd94a0a09e","source":{"kind":"arxiv","id":"2601.21798","version":2},"attestation_state":"computed","paper":{"title":"CG-MLLM: Captioning and Generating 3D content via Multi-modal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chi Wang, Donglin Huang, Guangkai Xu, Hao Chen, Junming Huang, Letian Li, Qiang Dai, Weiwei Xu","submitted_at":"2026-01-29T14:42:46Z","abstract_excerpt":"Large Language Models(LLMs) have revolutionized text generation and multimodal perception,but their capabilities in 3D content generation remain underexplored. Existing methods compromise by producing either low-resolution meshes or coarse structural proxies, failing to capture finegrained geometry natively. In this paper, we propose CG-MLLM, a novel Multi-modal Large Language Model (MLLM) capable of 3D captioning and high-resolution 3D generation in a single framework. Leveraging the Mixture-ofTransformer architecture, CG-MLLM decouples disparate modeling needs, where the Token-level Autoregr"},"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":"2601.21798","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-29T14:42:46Z","cross_cats_sorted":[],"title_canon_sha256":"f073bf0a05cd1d9ce1ecbbb70af9e8ce83bfa7d6c42045f93b9ff62f8b553dff","abstract_canon_sha256":"beb9f610219ca2f8924efe60ad7b7d203ba68a2e74f070d77d918be578516b72"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:32.816898Z","signature_b64":"GibR09NW6PHhj44ZpezR+44TqAKJPkNpodL8eusZjBJyedq+OD5vGbg+kpXaGiJFDvz3iwi8DcUlCc2wo9DXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a340f89896806c357501bc4d49a7fe02def5fc7907ec29bbb264d0dd94a0a09e","last_reissued_at":"2026-05-20T00:00:32.816208Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:32.816208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CG-MLLM: Captioning and Generating 3D content via Multi-modal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chi Wang, Donglin Huang, Guangkai Xu, Hao Chen, Junming Huang, Letian Li, Qiang Dai, Weiwei Xu","submitted_at":"2026-01-29T14:42:46Z","abstract_excerpt":"Large Language Models(LLMs) have revolutionized text generation and multimodal perception,but their capabilities in 3D content generation remain underexplored. Existing methods compromise by producing either low-resolution meshes or coarse structural proxies, failing to capture finegrained geometry natively. In this paper, we propose CG-MLLM, a novel Multi-modal Large Language Model (MLLM) capable of 3D captioning and high-resolution 3D generation in a single framework. Leveraging the Mixture-ofTransformer architecture, CG-MLLM decouples disparate modeling needs, where the Token-level Autoregr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.21798","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/2601.21798/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":"2601.21798","created_at":"2026-05-20T00:00:32.816299+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.21798v2","created_at":"2026-05-20T00:00:32.816299+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21798","created_at":"2026-05-20T00:00:32.816299+00:00"},{"alias_kind":"pith_short_12","alias_value":"UNAPRGEWQBWD","created_at":"2026-05-20T00:00:32.816299+00:00"},{"alias_kind":"pith_short_16","alias_value":"UNAPRGEWQBWDK5IB","created_at":"2026-05-20T00:00:32.816299+00:00"},{"alias_kind":"pith_short_8","alias_value":"UNAPRGEW","created_at":"2026-05-20T00:00:32.816299+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.16745","citing_title":"EVA01: Unified Native 3D Understanding and Generation via Mixture-of-Transformers","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UNAPRGEWQBWDK5IBXRGUTJ76AL","json":"https://pith.science/pith/UNAPRGEWQBWDK5IBXRGUTJ76AL.json","graph_json":"https://pith.science/api/pith-number/UNAPRGEWQBWDK5IBXRGUTJ76AL/graph.json","events_json":"https://pith.science/api/pith-number/UNAPRGEWQBWDK5IBXRGUTJ76AL/events.json","paper":"https://pith.science/paper/UNAPRGEW"},"agent_actions":{"view_html":"https://pith.science/pith/UNAPRGEWQBWDK5IBXRGUTJ76AL","download_json":"https://pith.science/pith/UNAPRGEWQBWDK5IBXRGUTJ76AL.json","view_paper":"https://pith.science/paper/UNAPRGEW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.21798&json=true","fetch_graph":"https://pith.science/api/pith-number/UNAPRGEWQBWDK5IBXRGUTJ76AL/graph.json","fetch_events":"https://pith.science/api/pith-number/UNAPRGEWQBWDK5IBXRGUTJ76AL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UNAPRGEWQBWDK5IBXRGUTJ76AL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UNAPRGEWQBWDK5IBXRGUTJ76AL/action/storage_attestation","attest_author":"https://pith.science/pith/UNAPRGEWQBWDK5IBXRGUTJ76AL/action/author_attestation","sign_citation":"https://pith.science/pith/UNAPRGEWQBWDK5IBXRGUTJ76AL/action/citation_signature","submit_replication":"https://pith.science/pith/UNAPRGEWQBWDK5IBXRGUTJ76AL/action/replication_record"}},"created_at":"2026-05-20T00:00:32.816299+00:00","updated_at":"2026-05-20T00:00:32.816299+00:00"}