{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WO5CR3YTC5QZ5C47UXYGMV34NQ","short_pith_number":"pith:WO5CR3YT","schema_version":"1.0","canonical_sha256":"b3ba28ef1317619e8b9fa5f066577c6c37c2c42b326f4d408db682cb43eec85f","source":{"kind":"arxiv","id":"2606.22299","version":1},"attestation_state":"computed","paper":{"title":"Towards Accurate and Robust Surveillance Roadside IVD via Trackletized Audio-Visual Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CV","authors_text":"Bodong Zhang, Tolga Tasdizen, Xiaoya Tang, Xiwen Li","submitted_at":"2026-06-21T01:58:04Z","abstract_excerpt":"Idling Vehicle Detection (IVD) seeks to determine, at the final frame of a video clip, whether any vehicle is idling, meaning the vehicle is stationary with its engine running, using synchronized video from a remote surveillance camera and multichannel audio captured by spatially distributed wireless microphones along the roadside. Prior full-image, clip-level fusion approaches tend to overfit scene background and full-frame context, produce unstable temporal decisions, and lack an explicit spatial prior to align vehicles with microphones, which makes them brittle under domain shift and data i"},"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":"2606.22299","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-21T01:58:04Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"7fbb1808667d875144627885984af5b90cf8a09aba86587780ec8e5e9546e138","abstract_canon_sha256":"2b2064a56b8a5b67424f2ecbd2da0dc98c042493f1caf12643a38151630f0df8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:34.310582Z","signature_b64":"QKPmZB05IpXs0Zd99jCzgQneM/vYpvTQBEMowoCWSsjm8PP91bBYRlCuvZo9p55564oJ6B/ZspIucrXdrY3DDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3ba28ef1317619e8b9fa5f066577c6c37c2c42b326f4d408db682cb43eec85f","last_reissued_at":"2026-06-23T02:13:34.310215Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:34.310215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Accurate and Robust Surveillance Roadside IVD via Trackletized Audio-Visual Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CV","authors_text":"Bodong Zhang, Tolga Tasdizen, Xiaoya Tang, Xiwen Li","submitted_at":"2026-06-21T01:58:04Z","abstract_excerpt":"Idling Vehicle Detection (IVD) seeks to determine, at the final frame of a video clip, whether any vehicle is idling, meaning the vehicle is stationary with its engine running, using synchronized video from a remote surveillance camera and multichannel audio captured by spatially distributed wireless microphones along the roadside. Prior full-image, clip-level fusion approaches tend to overfit scene background and full-frame context, produce unstable temporal decisions, and lack an explicit spatial prior to align vehicles with microphones, which makes them brittle under domain shift and data i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22299","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/2606.22299/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":"2606.22299","created_at":"2026-06-23T02:13:34.310273+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.22299v1","created_at":"2026-06-23T02:13:34.310273+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22299","created_at":"2026-06-23T02:13:34.310273+00:00"},{"alias_kind":"pith_short_12","alias_value":"WO5CR3YTC5QZ","created_at":"2026-06-23T02:13:34.310273+00:00"},{"alias_kind":"pith_short_16","alias_value":"WO5CR3YTC5QZ5C47","created_at":"2026-06-23T02:13:34.310273+00:00"},{"alias_kind":"pith_short_8","alias_value":"WO5CR3YT","created_at":"2026-06-23T02:13:34.310273+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WO5CR3YTC5QZ5C47UXYGMV34NQ","json":"https://pith.science/pith/WO5CR3YTC5QZ5C47UXYGMV34NQ.json","graph_json":"https://pith.science/api/pith-number/WO5CR3YTC5QZ5C47UXYGMV34NQ/graph.json","events_json":"https://pith.science/api/pith-number/WO5CR3YTC5QZ5C47UXYGMV34NQ/events.json","paper":"https://pith.science/paper/WO5CR3YT"},"agent_actions":{"view_html":"https://pith.science/pith/WO5CR3YTC5QZ5C47UXYGMV34NQ","download_json":"https://pith.science/pith/WO5CR3YTC5QZ5C47UXYGMV34NQ.json","view_paper":"https://pith.science/paper/WO5CR3YT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.22299&json=true","fetch_graph":"https://pith.science/api/pith-number/WO5CR3YTC5QZ5C47UXYGMV34NQ/graph.json","fetch_events":"https://pith.science/api/pith-number/WO5CR3YTC5QZ5C47UXYGMV34NQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WO5CR3YTC5QZ5C47UXYGMV34NQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WO5CR3YTC5QZ5C47UXYGMV34NQ/action/storage_attestation","attest_author":"https://pith.science/pith/WO5CR3YTC5QZ5C47UXYGMV34NQ/action/author_attestation","sign_citation":"https://pith.science/pith/WO5CR3YTC5QZ5C47UXYGMV34NQ/action/citation_signature","submit_replication":"https://pith.science/pith/WO5CR3YTC5QZ5C47UXYGMV34NQ/action/replication_record"}},"created_at":"2026-06-23T02:13:34.310273+00:00","updated_at":"2026-06-23T02:13:34.310273+00:00"}