{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JFRAI3SV34XDJF5NUN4VJ6GQF2","short_pith_number":"pith:JFRAI3SV","schema_version":"1.0","canonical_sha256":"4962046e55df2e3497ada37954f8d02eb3a93f779c2712563adce1b1030eb312","source":{"kind":"arxiv","id":"2607.13569","version":1},"attestation_state":"computed","paper":{"title":"GHR-VLM: Making Zero-Shot Transit Video Analytics Realizable with Grounded Hybrid Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Kaicong Huang, Ruimin Ke, Weiheng Oh","submitted_at":"2026-07-15T08:09:05Z","abstract_excerpt":"Transit video understanding can provide valuable fine-grained data that conventional passenger counters and fare systems cannot capture. However, supervised video models require task-specific annotations, while applying vision-language models (VLMs) directly to long onboard videos is unreliable and costly. To leverage the complementary strengths of both approaches, we propose GHR-VLM, a visual grounded hybrid reasoning framework for zero-shot transit-bus video analytics. It is motivated by the observation that explicit visual grounding can improve VLM reasoning by converting long surveillance "},"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":"2607.13569","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-15T08:09:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3c23cd91766f07436191e6c0396f9426ac204acf54ea03d424b9224209c52054","abstract_canon_sha256":"cfd4cc283a6af53951eaac82289c3bbb436214be33f504506c36430f844740cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-16T01:22:54.741833Z","signature_b64":"64CDKYJZe8k6fovFtPsVn0ixAO6OLBi/G1ZX6PV/9fb1JNrc6mwehCbuBemrzXxJ2DwrbKX0GZXSr1nJsmRhDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4962046e55df2e3497ada37954f8d02eb3a93f779c2712563adce1b1030eb312","last_reissued_at":"2026-07-16T01:22:54.740964Z","signature_status":"signed_v1","first_computed_at":"2026-07-16T01:22:54.740964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GHR-VLM: Making Zero-Shot Transit Video Analytics Realizable with Grounded Hybrid Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Kaicong Huang, Ruimin Ke, Weiheng Oh","submitted_at":"2026-07-15T08:09:05Z","abstract_excerpt":"Transit video understanding can provide valuable fine-grained data that conventional passenger counters and fare systems cannot capture. However, supervised video models require task-specific annotations, while applying vision-language models (VLMs) directly to long onboard videos is unreliable and costly. To leverage the complementary strengths of both approaches, we propose GHR-VLM, a visual grounded hybrid reasoning framework for zero-shot transit-bus video analytics. It is motivated by the observation that explicit visual grounding can improve VLM reasoning by converting long surveillance "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.13569","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/2607.13569/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":"2607.13569","created_at":"2026-07-16T01:22:54.741429+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.13569v1","created_at":"2026-07-16T01:22:54.741429+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13569","created_at":"2026-07-16T01:22:54.741429+00:00"},{"alias_kind":"pith_short_12","alias_value":"JFRAI3SV34XD","created_at":"2026-07-16T01:22:54.741429+00:00"},{"alias_kind":"pith_short_16","alias_value":"JFRAI3SV34XDJF5N","created_at":"2026-07-16T01:22:54.741429+00:00"},{"alias_kind":"pith_short_8","alias_value":"JFRAI3SV","created_at":"2026-07-16T01:22:54.741429+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/JFRAI3SV34XDJF5NUN4VJ6GQF2","json":"https://pith.science/pith/JFRAI3SV34XDJF5NUN4VJ6GQF2.json","graph_json":"https://pith.science/api/pith-number/JFRAI3SV34XDJF5NUN4VJ6GQF2/graph.json","events_json":"https://pith.science/api/pith-number/JFRAI3SV34XDJF5NUN4VJ6GQF2/events.json","paper":"https://pith.science/paper/JFRAI3SV"},"agent_actions":{"view_html":"https://pith.science/pith/JFRAI3SV34XDJF5NUN4VJ6GQF2","download_json":"https://pith.science/pith/JFRAI3SV34XDJF5NUN4VJ6GQF2.json","view_paper":"https://pith.science/paper/JFRAI3SV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.13569&json=true","fetch_graph":"https://pith.science/api/pith-number/JFRAI3SV34XDJF5NUN4VJ6GQF2/graph.json","fetch_events":"https://pith.science/api/pith-number/JFRAI3SV34XDJF5NUN4VJ6GQF2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JFRAI3SV34XDJF5NUN4VJ6GQF2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JFRAI3SV34XDJF5NUN4VJ6GQF2/action/storage_attestation","attest_author":"https://pith.science/pith/JFRAI3SV34XDJF5NUN4VJ6GQF2/action/author_attestation","sign_citation":"https://pith.science/pith/JFRAI3SV34XDJF5NUN4VJ6GQF2/action/citation_signature","submit_replication":"https://pith.science/pith/JFRAI3SV34XDJF5NUN4VJ6GQF2/action/replication_record"}},"created_at":"2026-07-16T01:22:54.741429+00:00","updated_at":"2026-07-16T01:22:54.741429+00:00"}