{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RZOWZ2QV4B5VVMMFGRUFG6YLSV","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":"e578113158887ee372b8b499dc0d96ba5478898488a77814923db93e8bd087be","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T03:42:39Z","title_canon_sha256":"02404c1e5177d0f92bd99a6b89e6cee8be2586aef96cf54a796c96c3172aabf6"},"schema_version":"1.0","source":{"id":"2412.03002","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.03002","created_at":"2026-07-05T10:27:21Z"},{"alias_kind":"arxiv_version","alias_value":"2412.03002v3","created_at":"2026-07-05T10:27:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03002","created_at":"2026-07-05T10:27:21Z"},{"alias_kind":"pith_short_12","alias_value":"RZOWZ2QV4B5V","created_at":"2026-07-05T10:27:21Z"},{"alias_kind":"pith_short_16","alias_value":"RZOWZ2QV4B5VVMMF","created_at":"2026-07-05T10:27:21Z"},{"alias_kind":"pith_short_8","alias_value":"RZOWZ2QV","created_at":"2026-07-05T10:27:21Z"}],"graph_snapshots":[{"event_id":"sha256:a9aef9fe4753e4a6f46810185c232775e46408a216f49c0f3963ce2dadfeeb88","target":"graph","created_at":"2026-07-05T10:27:21Z","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/2412.03002/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Caixin Kang, Hang Su, Hanqing Liu, Shouwei Ruan, Xiaoqi Wang, Xingxing Wei, Yao Huang, Yinpeng Dong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T03:42:39Z","title":"AdvDreamer Unveils: Are Vision-Language Models Truly Ready for Real-World 3D Variations?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03002","kind":"arxiv","version":3},"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":"sha256:01d8ac9b4c3c4f624b77eac5848138c7b632241f6014001ba471a3ffb5a4da97","target":"record","created_at":"2026-07-05T10:27:21Z","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":"e578113158887ee372b8b499dc0d96ba5478898488a77814923db93e8bd087be","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T03:42:39Z","title_canon_sha256":"02404c1e5177d0f92bd99a6b89e6cee8be2586aef96cf54a796c96c3172aabf6"},"schema_version":"1.0","source":{"id":"2412.03002","kind":"arxiv","version":3}},"canonical_sha256":"8e5d6cea15e07b5ab1853468537b0b956606426de4f2938b514e9cb5bcf96486","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e5d6cea15e07b5ab1853468537b0b956606426de4f2938b514e9cb5bcf96486","first_computed_at":"2026-07-05T10:27:21.006691Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:27:21.006691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bax59UhejEe0jY1sDDJxDBSYXFmHlT0Dau+z4oGInLBD3+np6pfWLV9pb2KdoLD/AO+yoOmWgehgbrrRIZDLBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:27:21.007326Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.03002","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:01d8ac9b4c3c4f624b77eac5848138c7b632241f6014001ba471a3ffb5a4da97","sha256:a9aef9fe4753e4a6f46810185c232775e46408a216f49c0f3963ce2dadfeeb88"],"state_sha256":"7820804a602e3d7f178f50263bdda6852b5bf7453cad87d641128e85de9013a4"}