{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IZFSFNTTXFMWHUD5PV35JHEMC5","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"002290cd30d81e67f8900e9929750d502e6f76ac4ede8fb8c0ffc93e3e75126f","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T09:07:14Z","title_canon_sha256":"cdb9670a8b359ab628e91368eea59b9386204826c549ba7a92b2b29b7f926a29"},"schema_version":"1.0","source":{"id":"2605.16892","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16892","created_at":"2026-05-20T00:03:28Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16892v1","created_at":"2026-05-20T00:03:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16892","created_at":"2026-05-20T00:03:28Z"},{"alias_kind":"pith_short_12","alias_value":"IZFSFNTTXFMW","created_at":"2026-05-20T00:03:28Z"},{"alias_kind":"pith_short_16","alias_value":"IZFSFNTTXFMWHUD5","created_at":"2026-05-20T00:03:28Z"},{"alias_kind":"pith_short_8","alias_value":"IZFSFNTT","created_at":"2026-05-20T00:03:28Z"}],"graph_snapshots":[{"event_id":"sha256:0e2dba3ffc9c71d2fd7a4204c8ae7626db1556e5f585be023ae78e4e7701e6db","target":"graph","created_at":"2026-05-20T00:03:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"By conditioning risk assessment on explicit language-based scene representations, DriveSafe achieves significant gains over both zero-shot MLLMs and prior domain-specific baselines. Exhaustive experiments on the DRAMA benchmark demonstrate state-of-the-art performance."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That generating spatially grounded captions enriched with multimodal context (motion, spatial, and depth cues) will provide sufficient and accurate information to enable superior risk assessment compared to direct zero-shot use of MLLMs, as stated in the abstract's motivation and method overview."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"DriveSafe improves driving risk detection by first creating detailed language-based scene descriptions enriched with motion, spatial, and depth information, then assessing risks and suggesting actions, with an adapter fine-tuned on caption-risk pairs to achieve SOTA results on the DRAMA benchmark."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"DriveSafe improves driving risk assessment by conditioning it on explicit language-based scene representations."}],"snapshot_sha256":"8bd19c4765e92084a4b1a00d5494421d8705fa5f48a9b98b2c34c4b6367c59ca"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T22:01:19.544665Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T21:50:54.901400Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"cited_work_retraction","ran_at":"2026-05-19T20:52:41.618454Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T18:41:56.282464Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.360916Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.16892/integrity.json","findings":[],"snapshot_sha256":"361f440c94ddb65f7fd8d9f0cd90772f5ebd047455ca8f0233ecf3fdd6ca68aa","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Comprehensive situational awareness is essential for autonomous vehicles operating in safety-critical environments, as it enables the identification and mitigation of potential risks. Although recent Multimodal Large Language Models (MLLMs) have shown promise on general vision-language tasks, our findings indicate that zero-shot MLLMs still underperform compared to domain-specific methods in fine-grained, spatially grounded risk assessment. To address this gap, we propose DriveSafe, a framework for risk-aware scene understanding that leverages structured natural language descriptions. Specific","authors_text":"Avijit Dasgupta, C. V. Jawahar, Sainithin Artham, Shankar Gangisetty","cross_cats":["cs.AI","cs.CL"],"headline":"DriveSafe improves driving risk assessment by conditioning it on explicit language-based scene representations.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T09:07:14Z","title":"DriveSafe: A Framework for Risk Detection and Safety Suggestions in Driving Scenarios"},"references":{"count":44,"internal_anchors":0,"resolved_work":44,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Risk assessment, modelling and proactive safety manage- ment system in aviation: a literature review,","work_id":"a99bf928-949c-460f-ac84-e6e94abc8cf4","year":2015},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Risk management in the healthcare safety management system,","work_id":"294d6a14-476c-46cc-a3e9-eb2c6a556eaa","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Safety assessment of collaborative robotics through automated formal verifi- cation,","work_id":"08bff5a6-2050-4d81-a256-3a87d80aa60f","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Road traffic injuries fact sheet,","work_id":"89b2feab-8296-4bc0-aec9-b6c6b74c93f3","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Fatality statistics: State-by- state,","work_id":"89a636f8-aaa4-42bc-ae29-1e5cc38d10fa","year":2023}],"snapshot_sha256":"6a6d921ae9e47632f219c0b008fd443560f2cb8f5207f4f1009d794abe5c1dcc"},"source":{"id":"2605.16892","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T21:36:27.014475Z","id":"80ae91de-ecc4-459e-8a08-68497ce470fd","model_set":{"reader":"grok-4.3"},"one_line_summary":"DriveSafe improves driving risk detection by first creating detailed language-based scene descriptions enriched with motion, spatial, and depth information, then assessing risks and suggesting actions, with an adapter fine-tuned on caption-risk pairs to achieve SOTA results on the DRAMA benchmark.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"DriveSafe improves driving risk assessment by conditioning it on explicit language-based scene representations.","strongest_claim":"By conditioning risk assessment on explicit language-based scene representations, DriveSafe achieves significant gains over both zero-shot MLLMs and prior domain-specific baselines. Exhaustive experiments on the DRAMA benchmark demonstrate state-of-the-art performance.","weakest_assumption":"That generating spatially grounded captions enriched with multimodal context (motion, spatial, and depth cues) will provide sufficient and accurate information to enable superior risk assessment compared to direct zero-shot use of MLLMs, as stated in the abstract's motivation and method overview."}},"verdict_id":"80ae91de-ecc4-459e-8a08-68497ce470fd"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:330fef1eab92d06c9db8657b711f87fabe6b2009d3e2094ef39ee435d6faa81c","target":"record","created_at":"2026-05-20T00:03:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"002290cd30d81e67f8900e9929750d502e6f76ac4ede8fb8c0ffc93e3e75126f","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T09:07:14Z","title_canon_sha256":"cdb9670a8b359ab628e91368eea59b9386204826c549ba7a92b2b29b7f926a29"},"schema_version":"1.0","source":{"id":"2605.16892","kind":"arxiv","version":1}},"canonical_sha256":"464b22b673b95963d07d7d77d49c8c17429dcd8252abeb2d5176e4a64ab3e539","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"464b22b673b95963d07d7d77d49c8c17429dcd8252abeb2d5176e4a64ab3e539","first_computed_at":"2026-05-20T00:03:28.660082Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:28.660082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AR+IeJhkNSu7mVYKmMDvScwZ6jLCbEiOfhwGJLzy7zX+vkOwSwNWWN8eKqS6xmVF3BMoz0lF78oZ953erDEEAA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:28.660855Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16892","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:330fef1eab92d06c9db8657b711f87fabe6b2009d3e2094ef39ee435d6faa81c","sha256:0e2dba3ffc9c71d2fd7a4204c8ae7626db1556e5f585be023ae78e4e7701e6db"],"state_sha256":"7e585e99f6c1f08feb50b5c37a717e86d12bfb75b089ab2be3274b42c9615ad0"}