{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:P26KD62LMFG3FYFU2MGEKBQZVZ","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":"1b4241e172502782c0933b3213c0827c01df7196e560cb1144dce30251f4b1de","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.GR","submitted_at":"2025-07-11T12:00:10Z","title_canon_sha256":"06a4561c42b678b0f10a42a00c9fc9391982b49b108c588e871b79e9b7e52b99"},"schema_version":"1.0","source":{"id":"2507.08513","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.08513","created_at":"2026-07-05T11:42:32Z"},{"alias_kind":"arxiv_version","alias_value":"2507.08513v2","created_at":"2026-07-05T11:42:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08513","created_at":"2026-07-05T11:42:32Z"},{"alias_kind":"pith_short_12","alias_value":"P26KD62LMFG3","created_at":"2026-07-05T11:42:32Z"},{"alias_kind":"pith_short_16","alias_value":"P26KD62LMFG3FYFU","created_at":"2026-07-05T11:42:32Z"},{"alias_kind":"pith_short_8","alias_value":"P26KD62L","created_at":"2026-07-05T11:42:32Z"}],"graph_snapshots":[{"event_id":"sha256:ef87c4c18125e2d79bb246fbe86cd6564d91750203bdddf8e9b38d06c0400662","target":"graph","created_at":"2026-07-05T11:42:32Z","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/2507.08513/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) struggle with accurately capturing camera-object relations, especially for object orientation, camera viewpoint, and camera shots. This stems from the fact that existing MLLMs are trained on images with limited diverse camera-object relations and corresponding textual descriptions. To address this, we propose a synthetic generation pipeline to create large-scale 3D visual instruction datasets. Our framework takes 3D assets as input and uses rendering and diffusion-based image generation models to create photorealistic images preserving precise camera-ob","authors_text":"Albert Y. C. Chen, Cheng-Hao Kuo, Daniel Aliaga, Liu He, Lu Xia, Min Sun, Sankalp Dayal, Shashwat Verma, Xiao Zeng, Yizhi Song","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.GR","submitted_at":"2025-07-11T12:00:10Z","title":"Advancing Multimodal LLMs by Large-Scale 3D Visual Instruction Dataset Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08513","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":"sha256:269db8e8cc084643b463018e4eb93ea93cf278a77b9ed4a1bfd90ea244e4c2c0","target":"record","created_at":"2026-07-05T11:42:32Z","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":"1b4241e172502782c0933b3213c0827c01df7196e560cb1144dce30251f4b1de","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.GR","submitted_at":"2025-07-11T12:00:10Z","title_canon_sha256":"06a4561c42b678b0f10a42a00c9fc9391982b49b108c588e871b79e9b7e52b99"},"schema_version":"1.0","source":{"id":"2507.08513","kind":"arxiv","version":2}},"canonical_sha256":"7ebca1fb4b614db2e0b4d30c450619ae605528d9be8ed72ff525095c3fb1a402","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ebca1fb4b614db2e0b4d30c450619ae605528d9be8ed72ff525095c3fb1a402","first_computed_at":"2026-07-05T11:42:32.335387Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:42:32.335387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZvRWMbxjxq5V3QvSY+vNDXqyCZUJWx51Y0axy/Z6zWbcS8/yvX1yvlPxQ1wC09eQvl7hY/OgoT/KEHtDgxJwAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:42:32.335879Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.08513","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:269db8e8cc084643b463018e4eb93ea93cf278a77b9ed4a1bfd90ea244e4c2c0","sha256:ef87c4c18125e2d79bb246fbe86cd6564d91750203bdddf8e9b38d06c0400662"],"state_sha256":"cc754ed67e999691b5b343e08e288397d591620b1d7b628708c9facc53a9a7ae"}