{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WFBHR2RX7IIKP5WOG2CRDKNRJO","short_pith_number":"pith:WFBHR2RX","schema_version":"1.0","canonical_sha256":"b14278ea37fa10a7f6ce368511a9b14b94c4f1901ce2cc1623d00b6e3da5f8ca","source":{"kind":"arxiv","id":"2511.14271","version":2},"attestation_state":"computed","paper":{"title":"Let Language Constrain Geometry: Vision-Language Models as Semantic and Spatial Critics for 3D Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"He Sun, Weijian Luo, Weimin Bai, Wenzheng Chen, Yequan Wang, Yubo Li, Zeqiang Lai","submitted_at":"2025-11-18T09:05:26Z","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"},"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":"2511.14271","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-18T09:05:26Z","cross_cats_sorted":[],"title_canon_sha256":"4aa3259e48f8ad2746845356dcda26fb588dfdd906da3271f22ee5454db1471a","abstract_canon_sha256":"526196577fb067c15ea92f0363c56056090565a46a2f38b51db33d2c77cef47a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:14:26.491986Z","signature_b64":"sju/ncC/KE9g9ur2kiCzcjK/Aic1WChhXXOgzGQ3TIvZ0zJs1Ffp3vyoUB0mWWJNHh7vbN0LugUE92/6uFZBAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b14278ea37fa10a7f6ce368511a9b14b94c4f1901ce2cc1623d00b6e3da5f8ca","last_reissued_at":"2026-06-29T01:14:26.491496Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:14:26.491496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Let Language Constrain Geometry: Vision-Language Models as Semantic and Spatial Critics for 3D Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"He Sun, Weijian Luo, Weimin Bai, Wenzheng Chen, Yequan Wang, Yubo Li, Zeqiang Lai","submitted_at":"2025-11-18T09:05:26Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.14271","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/2511.14271/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":"2511.14271","created_at":"2026-06-29T01:14:26.491549+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.14271v2","created_at":"2026-06-29T01:14:26.491549+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.14271","created_at":"2026-06-29T01:14:26.491549+00:00"},{"alias_kind":"pith_short_12","alias_value":"WFBHR2RX7IIK","created_at":"2026-06-29T01:14:26.491549+00:00"},{"alias_kind":"pith_short_16","alias_value":"WFBHR2RX7IIKP5WO","created_at":"2026-06-29T01:14:26.491549+00:00"},{"alias_kind":"pith_short_8","alias_value":"WFBHR2RX","created_at":"2026-06-29T01:14:26.491549+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/WFBHR2RX7IIKP5WOG2CRDKNRJO","json":"https://pith.science/pith/WFBHR2RX7IIKP5WOG2CRDKNRJO.json","graph_json":"https://pith.science/api/pith-number/WFBHR2RX7IIKP5WOG2CRDKNRJO/graph.json","events_json":"https://pith.science/api/pith-number/WFBHR2RX7IIKP5WOG2CRDKNRJO/events.json","paper":"https://pith.science/paper/WFBHR2RX"},"agent_actions":{"view_html":"https://pith.science/pith/WFBHR2RX7IIKP5WOG2CRDKNRJO","download_json":"https://pith.science/pith/WFBHR2RX7IIKP5WOG2CRDKNRJO.json","view_paper":"https://pith.science/paper/WFBHR2RX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.14271&json=true","fetch_graph":"https://pith.science/api/pith-number/WFBHR2RX7IIKP5WOG2CRDKNRJO/graph.json","fetch_events":"https://pith.science/api/pith-number/WFBHR2RX7IIKP5WOG2CRDKNRJO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WFBHR2RX7IIKP5WOG2CRDKNRJO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WFBHR2RX7IIKP5WOG2CRDKNRJO/action/storage_attestation","attest_author":"https://pith.science/pith/WFBHR2RX7IIKP5WOG2CRDKNRJO/action/author_attestation","sign_citation":"https://pith.science/pith/WFBHR2RX7IIKP5WOG2CRDKNRJO/action/citation_signature","submit_replication":"https://pith.science/pith/WFBHR2RX7IIKP5WOG2CRDKNRJO/action/replication_record"}},"created_at":"2026-06-29T01:14:26.491549+00:00","updated_at":"2026-06-29T01:14:26.491549+00:00"}