{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BNSMCFEYLX6RSEGBJ7EFMNPIEL","short_pith_number":"pith:BNSMCFEY","schema_version":"1.0","canonical_sha256":"0b64c114985dfd1910c14fc85635e822e23641c2ac57da40e028cd4479314258","source":{"kind":"arxiv","id":"2502.02449","version":1},"attestation_state":"computed","paper":{"title":"TUMTraffic-VideoQA: A Benchmark for Unified Spatio-Temporal Video Understanding in Traffic Scenes","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alois C. Knoll, Hao Guo, Hu Cao, Jiajie Zhang, Konstantinos Larintzakis, Leah Strand, Mingyu Liu, Venkatnarayanan Lakshminarasimhan, Walter Zimmer, Xingcheng Zhou","submitted_at":"2025-02-04T16:14:40Z","abstract_excerpt":"We present TUMTraffic-VideoQA, a novel dataset and benchmark designed for spatio-temporal video understanding in complex roadside traffic scenarios. The dataset comprises 1,000 videos, featuring 85,000 multiple-choice QA pairs, 2,300 object captioning, and 5,700 object grounding annotations, encompassing diverse real-world conditions such as adverse weather and traffic anomalies. By incorporating tuple-based spatio-temporal object expressions, TUMTraffic-VideoQA unifies three essential tasks-multiple-choice video question answering, referred object captioning, and spatio-temporal object ground"},"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":"2502.02449","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-04T16:14:40Z","cross_cats_sorted":[],"title_canon_sha256":"f9162925974b9b3033a709f10b62d77eb4fc2df17d58de7a23799873745726b1","abstract_canon_sha256":"6576ecf4a45b414f2c1f6ffd9b4e009bebaa0fffde75a0b2b28661f04ab37e9f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:28.727693Z","signature_b64":"BZ5/pk+KqOgw9fZzXga9XyT4oYQ01KYhRis/nFfUoV9cV7inacQ17Wg0mmCjYNCx+pBkfMGl31IP+AddmkIWCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b64c114985dfd1910c14fc85635e822e23641c2ac57da40e028cd4479314258","last_reissued_at":"2026-07-05T10:09:28.727225Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:28.727225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TUMTraffic-VideoQA: A Benchmark for Unified Spatio-Temporal Video Understanding in Traffic Scenes","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alois C. Knoll, Hao Guo, Hu Cao, Jiajie Zhang, Konstantinos Larintzakis, Leah Strand, Mingyu Liu, Venkatnarayanan Lakshminarasimhan, Walter Zimmer, Xingcheng Zhou","submitted_at":"2025-02-04T16:14:40Z","abstract_excerpt":"We present TUMTraffic-VideoQA, a novel dataset and benchmark designed for spatio-temporal video understanding in complex roadside traffic scenarios. The dataset comprises 1,000 videos, featuring 85,000 multiple-choice QA pairs, 2,300 object captioning, and 5,700 object grounding annotations, encompassing diverse real-world conditions such as adverse weather and traffic anomalies. By incorporating tuple-based spatio-temporal object expressions, TUMTraffic-VideoQA unifies three essential tasks-multiple-choice video question answering, referred object captioning, and spatio-temporal object ground"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02449","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/2502.02449/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":"2502.02449","created_at":"2026-07-05T10:09:28.727284+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.02449v1","created_at":"2026-07-05T10:09:28.727284+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02449","created_at":"2026-07-05T10:09:28.727284+00:00"},{"alias_kind":"pith_short_12","alias_value":"BNSMCFEYLX6R","created_at":"2026-07-05T10:09:28.727284+00:00"},{"alias_kind":"pith_short_16","alias_value":"BNSMCFEYLX6RSEGB","created_at":"2026-07-05T10:09:28.727284+00:00"},{"alias_kind":"pith_short_8","alias_value":"BNSMCFEY","created_at":"2026-07-05T10:09:28.727284+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.25944","citing_title":"NuRisk: A Visual Question Answering Dataset for Agent-Level Risk Assessment in Autonomous Driving","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2511.13397","citing_title":"Descriptor: Distance-Annotated Traffic Perception Question Answering (DTPQA)","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22260","citing_title":"Towards Safe Mobility: A Unified Transportation Foundation Model enabled by Open-Ended Vision-Language Dataset","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08457","citing_title":"CrashSight: A Phase-Aware, Infrastructure-Centric Video Benchmark for Traffic Crash Scene Understanding and Reasoning","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BNSMCFEYLX6RSEGBJ7EFMNPIEL","json":"https://pith.science/pith/BNSMCFEYLX6RSEGBJ7EFMNPIEL.json","graph_json":"https://pith.science/api/pith-number/BNSMCFEYLX6RSEGBJ7EFMNPIEL/graph.json","events_json":"https://pith.science/api/pith-number/BNSMCFEYLX6RSEGBJ7EFMNPIEL/events.json","paper":"https://pith.science/paper/BNSMCFEY"},"agent_actions":{"view_html":"https://pith.science/pith/BNSMCFEYLX6RSEGBJ7EFMNPIEL","download_json":"https://pith.science/pith/BNSMCFEYLX6RSEGBJ7EFMNPIEL.json","view_paper":"https://pith.science/paper/BNSMCFEY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.02449&json=true","fetch_graph":"https://pith.science/api/pith-number/BNSMCFEYLX6RSEGBJ7EFMNPIEL/graph.json","fetch_events":"https://pith.science/api/pith-number/BNSMCFEYLX6RSEGBJ7EFMNPIEL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BNSMCFEYLX6RSEGBJ7EFMNPIEL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BNSMCFEYLX6RSEGBJ7EFMNPIEL/action/storage_attestation","attest_author":"https://pith.science/pith/BNSMCFEYLX6RSEGBJ7EFMNPIEL/action/author_attestation","sign_citation":"https://pith.science/pith/BNSMCFEYLX6RSEGBJ7EFMNPIEL/action/citation_signature","submit_replication":"https://pith.science/pith/BNSMCFEYLX6RSEGBJ7EFMNPIEL/action/replication_record"}},"created_at":"2026-07-05T10:09:28.727284+00:00","updated_at":"2026-07-05T10:09:28.727284+00:00"}