{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UYLXI5DIXFISTSLYSS4JYKBOGY","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":"d83f6795cbb823725f60c015053f6c4c1ccedcf1063241bc8e48ad5982d2e0c3","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-15T21:36:19Z","title_canon_sha256":"1b3f0a45f30189ffd3ac21383df79397d69ac4e4143547dd4721ed461c5608a9"},"schema_version":"1.0","source":{"id":"2501.09167","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.09167","created_at":"2026-07-05T10:01:42Z"},{"alias_kind":"arxiv_version","alias_value":"2501.09167v1","created_at":"2026-07-05T10:01:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09167","created_at":"2026-07-05T10:01:42Z"},{"alias_kind":"pith_short_12","alias_value":"UYLXI5DIXFIS","created_at":"2026-07-05T10:01:42Z"},{"alias_kind":"pith_short_16","alias_value":"UYLXI5DIXFISTSLY","created_at":"2026-07-05T10:01:42Z"},{"alias_kind":"pith_short_8","alias_value":"UYLXI5DI","created_at":"2026-07-05T10:01:42Z"}],"graph_snapshots":[{"event_id":"sha256:0caf0fadd5a0dc52b55f32c4ffb34bbf0288cbb68591c889faf2ead9ac10d97d","target":"graph","created_at":"2026-07-05T10:01:42Z","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/2501.09167/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision Language Models (VLMs) demonstrate significant potential as embodied AI agents for various mobility applications. However, a standardized, closed-loop benchmark for evaluating their spatial reasoning and sequential decision-making capabilities is lacking. To address this, we present MetaVQA: a comprehensive benchmark designed to assess and enhance VLMs' understanding of spatial relationships and scene dynamics through Visual Question Answering (VQA) and closed-loop simulations. MetaVQA leverages Set-of-Mark prompting and top-down view ground-truth annotations from nuScenes and Waymo dat","authors_text":"Bolei Zhou, Chenda Duan, Weizhen Wang, Yuxin Liu, Zhenghao Peng","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-15T21:36:19Z","title":"Embodied Scene Understanding for Vision Language Models via MetaVQA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09167","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:c0fc93098ea6a0c265f669a515915acf6a15652ddc5fbf4886ff2ed4b094e98d","target":"record","created_at":"2026-07-05T10:01:42Z","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":"d83f6795cbb823725f60c015053f6c4c1ccedcf1063241bc8e48ad5982d2e0c3","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-15T21:36:19Z","title_canon_sha256":"1b3f0a45f30189ffd3ac21383df79397d69ac4e4143547dd4721ed461c5608a9"},"schema_version":"1.0","source":{"id":"2501.09167","kind":"arxiv","version":1}},"canonical_sha256":"a617747468b95129c97894b89c282e36019471ad3605e3a28bd8b9d0b081562a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a617747468b95129c97894b89c282e36019471ad3605e3a28bd8b9d0b081562a","first_computed_at":"2026-07-05T10:01:42.920264Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:01:42.920264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pc8J/CdcLZL5nrOBhRBLZjkmSZ/D8zqlVe6/zY6+IdeiH3fhunP+qBPaPEmR1duB2YH1Musl0Y9OqsRBL2EvAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:01:42.920766Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.09167","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c0fc93098ea6a0c265f669a515915acf6a15652ddc5fbf4886ff2ed4b094e98d","sha256:0caf0fadd5a0dc52b55f32c4ffb34bbf0288cbb68591c889faf2ead9ac10d97d"],"state_sha256":"9d3bb1557c7f1dc79f9a2614e8ab026d47849e19f43e686871b67c2343b9f855"}