{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RZOWZ2QV4B5VVMMFGRUFG6YLSV","short_pith_number":"pith:RZOWZ2QV","schema_version":"1.0","canonical_sha256":"8e5d6cea15e07b5ab1853468537b0b956606426de4f2938b514e9cb5bcf96486","source":{"kind":"arxiv","id":"2412.03002","version":3},"attestation_state":"computed","paper":{"title":"AdvDreamer Unveils: Are Vision-Language Models Truly Ready for Real-World 3D Variations?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Caixin Kang, Hang Su, Hanqing Liu, Shouwei Ruan, Xiaoqi Wang, Xingxing Wei, Yao Huang, Yinpeng Dong","submitted_at":"2024-12-04T03:42:39Z","abstract_excerpt":"Vision Language Models (VLMs) have exhibited remarkable generalization capabilities, yet their robustness in dynamic real-world scenarios remains largely unexplored. To systematically evaluate VLMs' robustness to real-world 3D variations, we propose AdvDreamer, the first framework capable of generating physically reproducible Adversarial 3D Transformation (Adv-3DT) samples from single-view observations. In AdvDreamer, we integrate three key innovations: Firstly, to characterize real-world 3D variations with limited prior knowledge precisely, we design a zero-shot Monocular Pose Manipulation pi"},"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":"2412.03002","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T03:42:39Z","cross_cats_sorted":[],"title_canon_sha256":"02404c1e5177d0f92bd99a6b89e6cee8be2586aef96cf54a796c96c3172aabf6","abstract_canon_sha256":"e578113158887ee372b8b499dc0d96ba5478898488a77814923db93e8bd087be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:21.007326Z","signature_b64":"bax59UhejEe0jY1sDDJxDBSYXFmHlT0Dau+z4oGInLBD3+np6pfWLV9pb2KdoLD/AO+yoOmWgehgbrrRIZDLBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e5d6cea15e07b5ab1853468537b0b956606426de4f2938b514e9cb5bcf96486","last_reissued_at":"2026-07-05T10:27:21.006691Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:21.006691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AdvDreamer Unveils: Are Vision-Language Models Truly Ready for Real-World 3D Variations?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Caixin Kang, Hang Su, Hanqing Liu, Shouwei Ruan, Xiaoqi Wang, Xingxing Wei, Yao Huang, Yinpeng Dong","submitted_at":"2024-12-04T03:42:39Z","abstract_excerpt":"Vision Language Models (VLMs) have exhibited remarkable generalization capabilities, yet their robustness in dynamic real-world scenarios remains largely unexplored. To systematically evaluate VLMs' robustness to real-world 3D variations, we propose AdvDreamer, the first framework capable of generating physically reproducible Adversarial 3D Transformation (Adv-3DT) samples from single-view observations. In AdvDreamer, we integrate three key innovations: Firstly, to characterize real-world 3D variations with limited prior knowledge precisely, we design a zero-shot Monocular Pose Manipulation pi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03002","kind":"arxiv","version":3},"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/2412.03002/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":"2412.03002","created_at":"2026-07-05T10:27:21.006768+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.03002v3","created_at":"2026-07-05T10:27:21.006768+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03002","created_at":"2026-07-05T10:27:21.006768+00:00"},{"alias_kind":"pith_short_12","alias_value":"RZOWZ2QV4B5V","created_at":"2026-07-05T10:27:21.006768+00:00"},{"alias_kind":"pith_short_16","alias_value":"RZOWZ2QV4B5VVMMF","created_at":"2026-07-05T10:27:21.006768+00:00"},{"alias_kind":"pith_short_8","alias_value":"RZOWZ2QV","created_at":"2026-07-05T10:27:21.006768+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/RZOWZ2QV4B5VVMMFGRUFG6YLSV","json":"https://pith.science/pith/RZOWZ2QV4B5VVMMFGRUFG6YLSV.json","graph_json":"https://pith.science/api/pith-number/RZOWZ2QV4B5VVMMFGRUFG6YLSV/graph.json","events_json":"https://pith.science/api/pith-number/RZOWZ2QV4B5VVMMFGRUFG6YLSV/events.json","paper":"https://pith.science/paper/RZOWZ2QV"},"agent_actions":{"view_html":"https://pith.science/pith/RZOWZ2QV4B5VVMMFGRUFG6YLSV","download_json":"https://pith.science/pith/RZOWZ2QV4B5VVMMFGRUFG6YLSV.json","view_paper":"https://pith.science/paper/RZOWZ2QV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.03002&json=true","fetch_graph":"https://pith.science/api/pith-number/RZOWZ2QV4B5VVMMFGRUFG6YLSV/graph.json","fetch_events":"https://pith.science/api/pith-number/RZOWZ2QV4B5VVMMFGRUFG6YLSV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RZOWZ2QV4B5VVMMFGRUFG6YLSV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RZOWZ2QV4B5VVMMFGRUFG6YLSV/action/storage_attestation","attest_author":"https://pith.science/pith/RZOWZ2QV4B5VVMMFGRUFG6YLSV/action/author_attestation","sign_citation":"https://pith.science/pith/RZOWZ2QV4B5VVMMFGRUFG6YLSV/action/citation_signature","submit_replication":"https://pith.science/pith/RZOWZ2QV4B5VVMMFGRUFG6YLSV/action/replication_record"}},"created_at":"2026-07-05T10:27:21.006768+00:00","updated_at":"2026-07-05T10:27:21.006768+00:00"}