{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RQAUSEHMHQIXF2FJJVZLWIZJKW","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":"807ab6305d2336e18ae9a6899d532755ba0efa1f37f27e0cfe15ca3b81e711e1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-06T16:25:22Z","title_canon_sha256":"51bd22a192decdc40034bb96bec0fcc23d693def8c09ef4ef11f5e30d2d87574"},"schema_version":"1.0","source":{"id":"2506.06218","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06218","created_at":"2026-07-05T11:17:27Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06218v1","created_at":"2026-07-05T11:17:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06218","created_at":"2026-07-05T11:17:27Z"},{"alias_kind":"pith_short_12","alias_value":"RQAUSEHMHQIX","created_at":"2026-07-05T11:17:27Z"},{"alias_kind":"pith_short_16","alias_value":"RQAUSEHMHQIXF2FJ","created_at":"2026-07-05T11:17:27Z"},{"alias_kind":"pith_short_8","alias_value":"RQAUSEHM","created_at":"2026-07-05T11:17:27Z"}],"graph_snapshots":[{"event_id":"sha256:3fce83f14fc865445af5e5f39452daa04daead54deef89a4d2407bba65964ed6","target":"graph","created_at":"2026-07-05T11:17:27Z","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/2506.06218/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce STSBench, a scenario-based framework to benchmark the holistic understanding of vision-language models (VLMs) for autonomous driving. The framework automatically mines pre-defined traffic scenarios from any dataset using ground-truth annotations, provides an intuitive user interface for efficient human verification, and generates multiple-choice questions for model evaluation. Applied to the NuScenes dataset, we present STSnu, the first benchmark that evaluates the spatio-temporal reasoning capabilities of VLMs based on comprehensive 3D perception. Existing benchmarks typically ta","authors_text":"Christian Fruhwirth-Reisinger, David Schinagl, Du\\v{s}an Mali\\'c, Horst Possegger, Samuel Schulter, Wei Lin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-06T16:25:22Z","title":"STSBench: A Spatio-temporal Scenario Benchmark for Multi-modal Large Language Models in Autonomous Driving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06218","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:e2ecc923656a4ae1ab9479f86fea7449aee2d4de96ce340a11d6ed61a6396f7d","target":"record","created_at":"2026-07-05T11:17:27Z","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":"807ab6305d2336e18ae9a6899d532755ba0efa1f37f27e0cfe15ca3b81e711e1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-06T16:25:22Z","title_canon_sha256":"51bd22a192decdc40034bb96bec0fcc23d693def8c09ef4ef11f5e30d2d87574"},"schema_version":"1.0","source":{"id":"2506.06218","kind":"arxiv","version":1}},"canonical_sha256":"8c014910ec3c1172e8a94d72bb2329559ee01f51379b0cf62806c63e4c36ae4b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c014910ec3c1172e8a94d72bb2329559ee01f51379b0cf62806c63e4c36ae4b","first_computed_at":"2026-07-05T11:17:27.657552Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:27.657552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z3AKdo7amB4vlLo6UPe9mVjlYEJ80uS75HQ6osgRZA3bm9hz2WtsyFZSb1CBsyrUjSGJwMCCLTn56YuHLcG/Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:27.658058Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.06218","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e2ecc923656a4ae1ab9479f86fea7449aee2d4de96ce340a11d6ed61a6396f7d","sha256:3fce83f14fc865445af5e5f39452daa04daead54deef89a4d2407bba65964ed6"],"state_sha256":"50bfb60c73fa3817a31bf62a03d83a8a92a0e61066b1466995dac4acbd8f037a"}