{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:UNAPRGEWQBWDK5IBXRGUTJ76AL","short_pith_number":"pith:UNAPRGEW","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"},"canonical_sha256":"a340f89896806c357501bc4d49a7fe02def5fc7907ec29bbb264d0dd94a0a09e","source":{"kind":"arxiv","id":"2601.21798","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.21798","created_at":"2026-05-20T00:00:32Z"},{"alias_kind":"arxiv_version","alias_value":"2601.21798v2","created_at":"2026-05-20T00:00:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21798","created_at":"2026-05-20T00:00:32Z"},{"alias_kind":"pith_short_12","alias_value":"UNAPRGEWQBWD","created_at":"2026-05-20T00:00:32Z"},{"alias_kind":"pith_short_16","alias_value":"UNAPRGEWQBWDK5IB","created_at":"2026-05-20T00:00:32Z"},{"alias_kind":"pith_short_8","alias_value":"UNAPRGEW","created_at":"2026-05-20T00:00:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:UNAPRGEWQBWDK5IBXRGUTJ76AL","target":"record","payload":{"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"},"canonical_sha256":"a340f89896806c357501bc4d49a7fe02def5fc7907ec29bbb264d0dd94a0a09e","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"},"source_kind":"arxiv","source_id":"2601.21798","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:00:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lwOzSDN7JObOIMk9Jwr+o7ueEHRd3HUBdTVulr1Xt/m1As+z8PrLMeWzaydmPIjBh+MMzG2wKkt0jNnYqn6YDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T21:20:13.249476Z"},"content_sha256":"6172c4265b49027596142995014547545cb94bdc4fdc97d3639fb398d7ca9f51","schema_version":"1.0","event_id":"sha256:6172c4265b49027596142995014547545cb94bdc4fdc97d3639fb398d7ca9f51"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:UNAPRGEWQBWDK5IBXRGUTJ76AL","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:00:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xo/PjbXm7AkExhqwc4RoT1lrsez4CDjfkEF63JIAR20+rx2pRcOwUgFktj5ozBO4Yj7iHGXsNG7bQcxCdqFpDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T21:20:13.249883Z"},"content_sha256":"76fa7a8e7c7fbc43e1b6b3918b818fc5cd7a74d1e78fa95e97364cf6cae4b1c5","schema_version":"1.0","event_id":"sha256:76fa7a8e7c7fbc43e1b6b3918b818fc5cd7a74d1e78fa95e97364cf6cae4b1c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UNAPRGEWQBWDK5IBXRGUTJ76AL/bundle.json","state_url":"https://pith.science/pith/UNAPRGEWQBWDK5IBXRGUTJ76AL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UNAPRGEWQBWDK5IBXRGUTJ76AL/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-21T21:20:13Z","links":{"resolver":"https://pith.science/pith/UNAPRGEWQBWDK5IBXRGUTJ76AL","bundle":"https://pith.science/pith/UNAPRGEWQBWDK5IBXRGUTJ76AL/bundle.json","state":"https://pith.science/pith/UNAPRGEWQBWDK5IBXRGUTJ76AL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UNAPRGEWQBWDK5IBXRGUTJ76AL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UNAPRGEWQBWDK5IBXRGUTJ76AL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"beb9f610219ca2f8924efe60ad7b7d203ba68a2e74f070d77d918be578516b72","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-29T14:42:46Z","title_canon_sha256":"f073bf0a05cd1d9ce1ecbbb70af9e8ce83bfa7d6c42045f93b9ff62f8b553dff"},"schema_version":"1.0","source":{"id":"2601.21798","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.21798","created_at":"2026-05-20T00:00:32Z"},{"alias_kind":"arxiv_version","alias_value":"2601.21798v2","created_at":"2026-05-20T00:00:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21798","created_at":"2026-05-20T00:00:32Z"},{"alias_kind":"pith_short_12","alias_value":"UNAPRGEWQBWD","created_at":"2026-05-20T00:00:32Z"},{"alias_kind":"pith_short_16","alias_value":"UNAPRGEWQBWDK5IB","created_at":"2026-05-20T00:00:32Z"},{"alias_kind":"pith_short_8","alias_value":"UNAPRGEW","created_at":"2026-05-20T00:00:32Z"}],"graph_snapshots":[{"event_id":"sha256:76fa7a8e7c7fbc43e1b6b3918b818fc5cd7a74d1e78fa95e97364cf6cae4b1c5","target":"graph","created_at":"2026-05-20T00:00:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2601.21798/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chi Wang, Donglin Huang, Guangkai Xu, Hao Chen, Junming Huang, Letian Li, Qiang Dai, Weiwei Xu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-29T14:42:46Z","title":"CG-MLLM: Captioning and Generating 3D content via Multi-modal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.21798","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6172c4265b49027596142995014547545cb94bdc4fdc97d3639fb398d7ca9f51","target":"record","created_at":"2026-05-20T00:00:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"beb9f610219ca2f8924efe60ad7b7d203ba68a2e74f070d77d918be578516b72","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-29T14:42:46Z","title_canon_sha256":"f073bf0a05cd1d9ce1ecbbb70af9e8ce83bfa7d6c42045f93b9ff62f8b553dff"},"schema_version":"1.0","source":{"id":"2601.21798","kind":"arxiv","version":2}},"canonical_sha256":"a340f89896806c357501bc4d49a7fe02def5fc7907ec29bbb264d0dd94a0a09e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a340f89896806c357501bc4d49a7fe02def5fc7907ec29bbb264d0dd94a0a09e","first_computed_at":"2026-05-20T00:00:32.816208Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:32.816208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GibR09NW6PHhj44ZpezR+44TqAKJPkNpodL8eusZjBJyedq+OD5vGbg+kpXaGiJFDvz3iwi8DcUlCc2wo9DXCQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:32.816898Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.21798","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6172c4265b49027596142995014547545cb94bdc4fdc97d3639fb398d7ca9f51","sha256:76fa7a8e7c7fbc43e1b6b3918b818fc5cd7a74d1e78fa95e97364cf6cae4b1c5"],"state_sha256":"35f6d448b68786074d442d81991b65dd4a9547d6fb84753a78d84cb560ec4249"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JXNRXY0EFqV52JiRqdfsX66D8TaTEEsMZqm7Mcz+UsZjkz8sNNEHRM2php77r0lv2ygIDnjkx0xKQEFxEg5QBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T21:20:13.252385Z","bundle_sha256":"a930024622a983991a16a80d1d709585485b8d9e66c34fd0114c4c087c35adaf"}}