{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RQAUSEHMHQIXF2FJJVZLWIZJKW","short_pith_number":"pith:RQAUSEHM","schema_version":"1.0","canonical_sha256":"8c014910ec3c1172e8a94d72bb2329559ee01f51379b0cf62806c63e4c36ae4b","source":{"kind":"arxiv","id":"2506.06218","version":1},"attestation_state":"computed","paper":{"title":"STSBench: A Spatio-temporal Scenario Benchmark for Multi-modal Large Language Models in Autonomous Driving","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christian Fruhwirth-Reisinger, David Schinagl, Du\\v{s}an Mali\\'c, Horst Possegger, Samuel Schulter, Wei Lin","submitted_at":"2025-06-06T16:25:22Z","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"},"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":"2506.06218","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-06T16:25:22Z","cross_cats_sorted":[],"title_canon_sha256":"51bd22a192decdc40034bb96bec0fcc23d693def8c09ef4ef11f5e30d2d87574","abstract_canon_sha256":"807ab6305d2336e18ae9a6899d532755ba0efa1f37f27e0cfe15ca3b81e711e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:27.658058Z","signature_b64":"Z3AKdo7amB4vlLo6UPe9mVjlYEJ80uS75HQ6osgRZA3bm9hz2WtsyFZSb1CBsyrUjSGJwMCCLTn56YuHLcG/Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c014910ec3c1172e8a94d72bb2329559ee01f51379b0cf62806c63e4c36ae4b","last_reissued_at":"2026-07-05T11:17:27.657552Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:27.657552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STSBench: A Spatio-temporal Scenario Benchmark for Multi-modal Large Language Models in Autonomous Driving","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christian Fruhwirth-Reisinger, David Schinagl, Du\\v{s}an Mali\\'c, Horst Possegger, Samuel Schulter, Wei Lin","submitted_at":"2025-06-06T16:25:22Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06218","kind":"arxiv","version":1},"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/2506.06218/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":"2506.06218","created_at":"2026-07-05T11:17:27.657613+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.06218v1","created_at":"2026-07-05T11:17:27.657613+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06218","created_at":"2026-07-05T11:17:27.657613+00:00"},{"alias_kind":"pith_short_12","alias_value":"RQAUSEHMHQIX","created_at":"2026-07-05T11:17:27.657613+00:00"},{"alias_kind":"pith_short_16","alias_value":"RQAUSEHMHQIXF2FJ","created_at":"2026-07-05T11:17:27.657613+00:00"},{"alias_kind":"pith_short_8","alias_value":"RQAUSEHM","created_at":"2026-07-05T11:17:27.657613+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07601","citing_title":"CARLA-GS: Decoupling Representation, Reasoning, and Physics Simulation for Autonomous Driving Corner-Case Synthesis","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2606.27660","citing_title":"MVPruner: Dynamic Token Pruning for Accelerating Multi-view Vision-Language Models in Autonomous Driving","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27660","citing_title":"MVPruner: Dynamic Token Pruning for Accelerating Multi-view Vision-Language Models in Autonomous Driving","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27038","citing_title":"TPS-Drive: Task-Guided Representation Purification for VLM-based Autonomous Driving","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RQAUSEHMHQIXF2FJJVZLWIZJKW","json":"https://pith.science/pith/RQAUSEHMHQIXF2FJJVZLWIZJKW.json","graph_json":"https://pith.science/api/pith-number/RQAUSEHMHQIXF2FJJVZLWIZJKW/graph.json","events_json":"https://pith.science/api/pith-number/RQAUSEHMHQIXF2FJJVZLWIZJKW/events.json","paper":"https://pith.science/paper/RQAUSEHM"},"agent_actions":{"view_html":"https://pith.science/pith/RQAUSEHMHQIXF2FJJVZLWIZJKW","download_json":"https://pith.science/pith/RQAUSEHMHQIXF2FJJVZLWIZJKW.json","view_paper":"https://pith.science/paper/RQAUSEHM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.06218&json=true","fetch_graph":"https://pith.science/api/pith-number/RQAUSEHMHQIXF2FJJVZLWIZJKW/graph.json","fetch_events":"https://pith.science/api/pith-number/RQAUSEHMHQIXF2FJJVZLWIZJKW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RQAUSEHMHQIXF2FJJVZLWIZJKW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RQAUSEHMHQIXF2FJJVZLWIZJKW/action/storage_attestation","attest_author":"https://pith.science/pith/RQAUSEHMHQIXF2FJJVZLWIZJKW/action/author_attestation","sign_citation":"https://pith.science/pith/RQAUSEHMHQIXF2FJJVZLWIZJKW/action/citation_signature","submit_replication":"https://pith.science/pith/RQAUSEHMHQIXF2FJJVZLWIZJKW/action/replication_record"}},"created_at":"2026-07-05T11:17:27.657613+00:00","updated_at":"2026-07-05T11:17:27.657613+00:00"}