{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XYXGKQT7JVGI4W25I53AA5C7VS","short_pith_number":"pith:XYXGKQT7","schema_version":"1.0","canonical_sha256":"be2e65427f4d4c8e5b5d477600745fac82f3ac1b03ffa6c24064c5c7c20949dc","source":{"kind":"arxiv","id":"2507.14743","version":3},"attestation_state":"computed","paper":{"title":"InterAct-Video: Reasoning-Rich Video QA for Urban Traffic","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bharatesh Chakravarthi, Divesh Basina, Joseph Raj Vishal, Katha Naik, Manas Srinivas Gowda, Rutuja Patil, Yezhou Yang","submitted_at":"2025-07-19T20:30:43Z","abstract_excerpt":"Traffic monitoring is crucial for urban mobility, road safety, and intelligent transportation systems (ITS). Deep learning has advanced video-based traffic monitoring through video question answering (VideoQA) models, enabling structured insight extraction from traffic videos. However, existing VideoQA models struggle with the complexity of real-world traffic scenes, where multiple concurrent events unfold across spatiotemporal dimensions. To address these challenges, this paper introduces \\textbf{InterAct VideoQA}, a curated dataset designed to benchmark and enhance VideoQA models for traffic"},"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":"2507.14743","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-19T20:30:43Z","cross_cats_sorted":[],"title_canon_sha256":"137956c1e6fcf7ae35f34d4d8c188dbf2a1f6e14fd6a3507b9f83599ba6cfadc","abstract_canon_sha256":"dcc1ab88a565105106b62206a27fd4bd0e299303adfb8da33d85c8350c855f13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:51.083894Z","signature_b64":"mrOu8V4HVxQsZ8Bd4bnCvtei8vigg9IvfgKLonrXzNLSGaQyZqVTZNOahr88BvDDfvkBIydU+Bv7k0FiF826CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be2e65427f4d4c8e5b5d477600745fac82f3ac1b03ffa6c24064c5c7c20949dc","last_reissued_at":"2026-07-05T12:00:51.083404Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:51.083404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InterAct-Video: Reasoning-Rich Video QA for Urban Traffic","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bharatesh Chakravarthi, Divesh Basina, Joseph Raj Vishal, Katha Naik, Manas Srinivas Gowda, Rutuja Patil, Yezhou Yang","submitted_at":"2025-07-19T20:30:43Z","abstract_excerpt":"Traffic monitoring is crucial for urban mobility, road safety, and intelligent transportation systems (ITS). Deep learning has advanced video-based traffic monitoring through video question answering (VideoQA) models, enabling structured insight extraction from traffic videos. However, existing VideoQA models struggle with the complexity of real-world traffic scenes, where multiple concurrent events unfold across spatiotemporal dimensions. To address these challenges, this paper introduces \\textbf{InterAct VideoQA}, a curated dataset designed to benchmark and enhance VideoQA models for traffic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14743","kind":"arxiv","version":3},"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/2507.14743/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":"2507.14743","created_at":"2026-07-05T12:00:51.083460+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.14743v3","created_at":"2026-07-05T12:00:51.083460+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14743","created_at":"2026-07-05T12:00:51.083460+00:00"},{"alias_kind":"pith_short_12","alias_value":"XYXGKQT7JVGI","created_at":"2026-07-05T12:00:51.083460+00:00"},{"alias_kind":"pith_short_16","alias_value":"XYXGKQT7JVGI4W25","created_at":"2026-07-05T12:00:51.083460+00:00"},{"alias_kind":"pith_short_8","alias_value":"XYXGKQT7","created_at":"2026-07-05T12:00:51.083460+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.08457","citing_title":"CrashSight: A Phase-Aware, Infrastructure-Centric Video Benchmark for Traffic Crash Scene Understanding and Reasoning","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XYXGKQT7JVGI4W25I53AA5C7VS","json":"https://pith.science/pith/XYXGKQT7JVGI4W25I53AA5C7VS.json","graph_json":"https://pith.science/api/pith-number/XYXGKQT7JVGI4W25I53AA5C7VS/graph.json","events_json":"https://pith.science/api/pith-number/XYXGKQT7JVGI4W25I53AA5C7VS/events.json","paper":"https://pith.science/paper/XYXGKQT7"},"agent_actions":{"view_html":"https://pith.science/pith/XYXGKQT7JVGI4W25I53AA5C7VS","download_json":"https://pith.science/pith/XYXGKQT7JVGI4W25I53AA5C7VS.json","view_paper":"https://pith.science/paper/XYXGKQT7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.14743&json=true","fetch_graph":"https://pith.science/api/pith-number/XYXGKQT7JVGI4W25I53AA5C7VS/graph.json","fetch_events":"https://pith.science/api/pith-number/XYXGKQT7JVGI4W25I53AA5C7VS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XYXGKQT7JVGI4W25I53AA5C7VS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XYXGKQT7JVGI4W25I53AA5C7VS/action/storage_attestation","attest_author":"https://pith.science/pith/XYXGKQT7JVGI4W25I53AA5C7VS/action/author_attestation","sign_citation":"https://pith.science/pith/XYXGKQT7JVGI4W25I53AA5C7VS/action/citation_signature","submit_replication":"https://pith.science/pith/XYXGKQT7JVGI4W25I53AA5C7VS/action/replication_record"}},"created_at":"2026-07-05T12:00:51.083460+00:00","updated_at":"2026-07-05T12:00:51.083460+00:00"}