{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5OZDLVNEHPUDD45225766OKOUY","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":"883b394715e9c03e3a88930bdfcc33688e5eadeb1edcf7d47cebe23797821ced","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-29T17:02:57Z","title_canon_sha256":"2c53e506dca5d44fd1d91e6725689aa4792c8463ce312111e0bd5de19377d370"},"schema_version":"1.0","source":{"id":"2506.23329","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23329","created_at":"2026-07-05T11:29:19Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23329v1","created_at":"2026-07-05T11:29:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23329","created_at":"2026-07-05T11:29:19Z"},{"alias_kind":"pith_short_12","alias_value":"5OZDLVNEHPUD","created_at":"2026-07-05T11:29:19Z"},{"alias_kind":"pith_short_16","alias_value":"5OZDLVNEHPUDD452","created_at":"2026-07-05T11:29:19Z"},{"alias_kind":"pith_short_8","alias_value":"5OZDLVNE","created_at":"2026-07-05T11:29:19Z"}],"graph_snapshots":[{"event_id":"sha256:21d1cf6a7cd268c745b3df57be1e1dd24454bae0ab75b843b35291279e36ab32","target":"graph","created_at":"2026-07-05T11:29:19Z","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/2506.23329/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) excel at descriptive tasks, but whether they truly understand scenes from visual observations remains uncertain. We introduce IR3D-Bench, a benchmark challenging VLMs to demonstrate understanding through active creation rather than passive recognition. Grounded in the analysis-by-synthesis paradigm, IR3D-Bench tasks Vision-Language Agents (VLAs) with actively using programming and rendering tools to recreate the underlying 3D structure of an input image, achieving agentic inverse rendering through tool use. This \"understanding-by-creating\" approach probes the tool","authors_text":"Brandon Y. Feng, Chenxin Li, Parker Liu, Sirui Han, Wuyang Li, Yipeng Wu, Yunlong Lin, Zhengxin Li, Zhenyuan Zhang, Zhiqin Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-29T17:02:57Z","title":"IR3D-Bench: Evaluating Vision-Language Model Scene Understanding as Agentic Inverse Rendering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23329","kind":"arxiv","version":1},"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":"sha256:9fe502898eda9b8ab3d693a525adb9b5f7ffaacade493d83d0e281e32343c92e","target":"record","created_at":"2026-07-05T11:29:19Z","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":"883b394715e9c03e3a88930bdfcc33688e5eadeb1edcf7d47cebe23797821ced","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-29T17:02:57Z","title_canon_sha256":"2c53e506dca5d44fd1d91e6725689aa4792c8463ce312111e0bd5de19377d370"},"schema_version":"1.0","source":{"id":"2506.23329","kind":"arxiv","version":1}},"canonical_sha256":"ebb235d5a43be831f3bad77fef394ea6308ec36f7bf01c0803117032261837a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ebb235d5a43be831f3bad77fef394ea6308ec36f7bf01c0803117032261837a5","first_computed_at":"2026-07-05T11:29:19.881288Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:19.881288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kdigriiU3+gzVcusZdk5K7noy7XhlotdHLzL/z7bXhIs9ejXgJ+sNOiFNBaLxrQYbDU3wnBXoNoJVb8ty9ZNBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:19.881807Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.23329","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9fe502898eda9b8ab3d693a525adb9b5f7ffaacade493d83d0e281e32343c92e","sha256:21d1cf6a7cd268c745b3df57be1e1dd24454bae0ab75b843b35291279e36ab32"],"state_sha256":"72d779f38e6841b484bbfac4c9ff1dda58a6677b10fb334bd8dca5dd6e06bfea"}