{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WFBHR2RX7IIKP5WOG2CRDKNRJO","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":"526196577fb067c15ea92f0363c56056090565a46a2f38b51db33d2c77cef47a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-18T09:05:26Z","title_canon_sha256":"4aa3259e48f8ad2746845356dcda26fb588dfdd906da3271f22ee5454db1471a"},"schema_version":"1.0","source":{"id":"2511.14271","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.14271","created_at":"2026-06-29T01:14:26Z"},{"alias_kind":"arxiv_version","alias_value":"2511.14271v2","created_at":"2026-06-29T01:14:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.14271","created_at":"2026-06-29T01:14:26Z"},{"alias_kind":"pith_short_12","alias_value":"WFBHR2RX7IIK","created_at":"2026-06-29T01:14:26Z"},{"alias_kind":"pith_short_16","alias_value":"WFBHR2RX7IIKP5WO","created_at":"2026-06-29T01:14:26Z"},{"alias_kind":"pith_short_8","alias_value":"WFBHR2RX","created_at":"2026-06-29T01:14:26Z"}],"graph_snapshots":[{"event_id":"sha256:4f22e9e36bc7db8d6e58448656a6eb5e0246ed7402f9c75668e41d0c23980e7c","target":"graph","created_at":"2026-06-29T01:14:26Z","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/2511.14271/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-3D generation has advanced rapidly, yet state-of-the-art models, encompassing both optimization-based and feed-forward architectures, still face two fundamental limitations. First, they struggle with coarse semantic alignment, often failing to capture fine-grained prompt details. Second, they lack robust 3D spatial understanding, leading to geometric inconsistencies and catastrophic failures in part assembly and spatial relationships. To address these challenges, we propose VLM3D, a general framework that repurposes large vision-language models (VLMs) as powerful, differentiable semant","authors_text":"He Sun, Weijian Luo, Weimin Bai, Wenzheng Chen, Yequan Wang, Yubo Li, Zeqiang Lai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-18T09:05:26Z","title":"Let Language Constrain Geometry: Vision-Language Models as Semantic and Spatial Critics for 3D Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.14271","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":"sha256:4ac692b53f79cb0e28bf5ea0ab1f5f929cc46d9c88ddd218a934f9dd3dab80b7","target":"record","created_at":"2026-06-29T01:14:26Z","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":"526196577fb067c15ea92f0363c56056090565a46a2f38b51db33d2c77cef47a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-18T09:05:26Z","title_canon_sha256":"4aa3259e48f8ad2746845356dcda26fb588dfdd906da3271f22ee5454db1471a"},"schema_version":"1.0","source":{"id":"2511.14271","kind":"arxiv","version":2}},"canonical_sha256":"b14278ea37fa10a7f6ce368511a9b14b94c4f1901ce2cc1623d00b6e3da5f8ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b14278ea37fa10a7f6ce368511a9b14b94c4f1901ce2cc1623d00b6e3da5f8ca","first_computed_at":"2026-06-29T01:14:26.491496Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-29T01:14:26.491496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sju/ncC/KE9g9ur2kiCzcjK/Aic1WChhXXOgzGQ3TIvZ0zJs1Ffp3vyoUB0mWWJNHh7vbN0LugUE92/6uFZBAQ==","signature_status":"signed_v1","signed_at":"2026-06-29T01:14:26.491986Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.14271","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ac692b53f79cb0e28bf5ea0ab1f5f929cc46d9c88ddd218a934f9dd3dab80b7","sha256:4f22e9e36bc7db8d6e58448656a6eb5e0246ed7402f9c75668e41d0c23980e7c"],"state_sha256":"1a6be32e3e9c39bef802c582c69b3c73e09bd11f339826d44b2eefbd45de3373"}