{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4I23UPQHCUYVRCR7WKVVMF6WBF","short_pith_number":"pith:4I23UPQH","schema_version":"1.0","canonical_sha256":"e235ba3e071531588a3fb2ab5617d6095be351af95242419c7934ab302541623","source":{"kind":"arxiv","id":"2605.22185","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Multimodal Large Language Models for Safety-Critical Driving Video Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Henrique Pi\\~neiro Monteagudo, Leonardo Taccari, Tomaso Trinci","submitted_at":"2026-05-21T08:54:22Z","abstract_excerpt":"Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in general visual understanding. However, their application to safety-critical driving scenarios remains limited by an inability to accurately perceive and reason about rare high-stakes dynamic events, such as collisions or near-collisions. To address this, we introduce a pipeline that enhances MLLM perception by fusing downsampled video frames with synchronized high-frequency telematics data (IMU and GPS) and semantic insights from specialized computer vision models. Our pipeline generate"},"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":"2605.22185","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T08:54:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a29a8b8a5533780d790ee5e3927e46b91d1f67ef5fb276929dd65da514b7946e","abstract_canon_sha256":"3921389cd4d5939b1180f56a760eb53ed852f62202b876f6a50c5f3266b98ebb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:04:30.794058Z","signature_b64":"gd5mEeCxxf5GCMlYUTB0hWCe9c89kpsReCD6d73xkUXBw7QYNvXysY8SpKsTsGdXBxsw347UL697zjT8z0Z4BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e235ba3e071531588a3fb2ab5617d6095be351af95242419c7934ab302541623","last_reissued_at":"2026-05-22T01:04:30.793328Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:04:30.793328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Multimodal Large Language Models for Safety-Critical Driving Video Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Henrique Pi\\~neiro Monteagudo, Leonardo Taccari, Tomaso Trinci","submitted_at":"2026-05-21T08:54:22Z","abstract_excerpt":"Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in general visual understanding. However, their application to safety-critical driving scenarios remains limited by an inability to accurately perceive and reason about rare high-stakes dynamic events, such as collisions or near-collisions. To address this, we introduce a pipeline that enhances MLLM perception by fusing downsampled video frames with synchronized high-frequency telematics data (IMU and GPS) and semantic insights from specialized computer vision models. Our pipeline generate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22185","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/2605.22185/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":"2605.22185","created_at":"2026-05-22T01:04:30.793451+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.22185v1","created_at":"2026-05-22T01:04:30.793451+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22185","created_at":"2026-05-22T01:04:30.793451+00:00"},{"alias_kind":"pith_short_12","alias_value":"4I23UPQHCUYV","created_at":"2026-05-22T01:04:30.793451+00:00"},{"alias_kind":"pith_short_16","alias_value":"4I23UPQHCUYVRCR7","created_at":"2026-05-22T01:04:30.793451+00:00"},{"alias_kind":"pith_short_8","alias_value":"4I23UPQH","created_at":"2026-05-22T01:04:30.793451+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/4I23UPQHCUYVRCR7WKVVMF6WBF","json":"https://pith.science/pith/4I23UPQHCUYVRCR7WKVVMF6WBF.json","graph_json":"https://pith.science/api/pith-number/4I23UPQHCUYVRCR7WKVVMF6WBF/graph.json","events_json":"https://pith.science/api/pith-number/4I23UPQHCUYVRCR7WKVVMF6WBF/events.json","paper":"https://pith.science/paper/4I23UPQH"},"agent_actions":{"view_html":"https://pith.science/pith/4I23UPQHCUYVRCR7WKVVMF6WBF","download_json":"https://pith.science/pith/4I23UPQHCUYVRCR7WKVVMF6WBF.json","view_paper":"https://pith.science/paper/4I23UPQH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.22185&json=true","fetch_graph":"https://pith.science/api/pith-number/4I23UPQHCUYVRCR7WKVVMF6WBF/graph.json","fetch_events":"https://pith.science/api/pith-number/4I23UPQHCUYVRCR7WKVVMF6WBF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4I23UPQHCUYVRCR7WKVVMF6WBF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4I23UPQHCUYVRCR7WKVVMF6WBF/action/storage_attestation","attest_author":"https://pith.science/pith/4I23UPQHCUYVRCR7WKVVMF6WBF/action/author_attestation","sign_citation":"https://pith.science/pith/4I23UPQHCUYVRCR7WKVVMF6WBF/action/citation_signature","submit_replication":"https://pith.science/pith/4I23UPQHCUYVRCR7WKVVMF6WBF/action/replication_record"}},"created_at":"2026-05-22T01:04:30.793451+00:00","updated_at":"2026-05-22T01:04:30.793451+00:00"}