{"id":"254b6656659d79e018584388eaf61c8d5aa5a88523208b6c1e736f2e96a8efa0","title":"Jev with Foresight: Safe Language-Guided Autonomous Driving via a Language World Model","argument":"Authors Yansong Qu, Jiancong Chen, and Samuel Labi present Jev-AD, which pairs Jev—a typed decision model that answers predefined questions with probabilities—with a language world model that predicts how nearby vehicles move under each candidate action. Code converts those predictions into foreseen consequences for Jev to compare, rather than requiring it to infer consequences from coordinates. In simulated highway merging, the authors report that foresight lowers the same decision model’s collision rate from 26.0% to 2.4% at 0.25 seconds per decision; Jev-AD achieves passengers’ intent in 93% of free-form command trials. In 500 replayed real-world NGSIM episodes, they report a decrease from 48.2% to 2.8%, and say the world model foresees 93% of dangerous actions. These results suggest a way to make language-guided driving decisions by comparing predicted consequences, but the reported evaluations are simulations and replayed episodes, not evidence of performance in deployed vehicles.","topicIds":["intelligence-and-discovery"],"domain":"science","claimType":"attributed reading","limits":"The abstract reports results from simulated highway merging and replayed real-world NGSIM episodes; it does not report evaluation in deployed vehicles. The evidence provided is the paper’s arXiv page and abstract, not the full paper.","speaker":{"name":"Qu, Yansong, Chen, Jiancong, Labi, Samuel","roleAtSource":"Article author"},"source":{"title":"Jev with Foresight: Safe Language-Guided Autonomous Driving via a Language World Model","publisher":"arXiv cs.AI","format":"Article","url":"https://arxiv.org/abs/2611.05448","publishedAt":"2026-11-03","dateBasis":"Date basis not provided."},"evidence":[{"text":"The authors present Jev-AD, combining Jev, a typed decision model that answers predefined questions with probabilities, and a language world model that predicts nearby vehicles’ movement for candidate actions.","excerpt":"Jev, a typed decision model that answers predefined questions with probabilities, not generated text, with a language world model that predicts for every candidate action how nearby vehicles move over the next two seconds.","url":"https://arxiv.org/abs/2611.05448","relationship":"Source-stated"},{"text":"The authors say code turns the predictions into foreseen consequences for Jev to compare.","excerpt":"Code turns these predictions into foreseen consequences, which Jev compares instead of inferring them from coordinates.","url":"https://arxiv.org/abs/2611.05448","relationship":"Source-stated"},{"text":"In simulated highway merging, the authors report that foresight reduced the same decision model’s collision rate from 26.0% to 2.4% at 0.25 seconds per decision, and that Jev-AD achieved passenger intent in 93% of free-form command trials.","excerpt":"In simulated highway merging (500 car-episodes), this foresight lowers the same decision model's collision rate from 26.0% to 2.4% at 0.25 seconds per decision, and Jev-AD achieves the passenger's intent in 93% of free-form command trials.","url":"https://arxiv.org/abs/2611.05448","relationship":"Source-stated"},{"text":"For 500 replayed real-world NGSIM episodes, the authors report a collision-rate decrease from 48.2% to 2.8%, and say the world model foresaw 93% of dangerous actions.","excerpt":"In 500 replayed real-world NGSIM episodes, foresight lowers the collision rate from 48.2% to 2.8%, and the world model, learned from this traffic, foresees 93% of dangerous actions.","url":"https://arxiv.org/abs/2611.05448","relationship":"Source-stated"},{"text":"The reported evaluations are simulations and replayed episodes, so these results alone do not establish performance in deployed vehicles.","excerpt":"In simulated highway merging (500 car-episodes)","url":"https://arxiv.org/abs/2611.05448","relationship":"Escape Meridian interpretation"}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.05448","checkedAt":"2026-11-09T10:36:08.304Z","items":[],"note":"No suitable media was found by the supported page extraction."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"How would Jev-AD perform beyond the simulated highway-merging trials and replayed NGSIM episodes reported by the authors?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Jev with Foresight: Safe Language-Guided Autonomous Driving via a Language World Model","summary":"Authors Yansong Qu, Jiancong Chen, and Samuel Labi present Jev-AD, which pairs Jev—a typed decision model that answers predefined questions with probabilities—with a language world model that predicts how nearby vehicles move under each candidate action. Code converts those predictions into foreseen consequences for Jev to compare, rather than requiring it to infer consequences from coordinates. In simulated highway merging, the authors report that foresight lowers the same decision model’s collision rate from 26.0% to 2.4% at 0.25 seconds per decision; Jev-AD achieves passengers’ intent in 93% of free-form command trials. In 500 replayed real-world NGSIM episodes, they report a decrease from 48.2% to 2.8%, and say the world model foresees 93% of dangerous actions. These results suggest a way to make language-guided driving decisions by comparing predicted consequences, but the reported evaluations are simulations and replayed episodes, not evidence of performance in deployed vehicles.","question":"How would Jev-AD perform beyond the simulated highway-merging trials and replayed NGSIM episodes reported by the authors?","claims":[{"text":"The authors present Jev-AD, combining Jev, a typed decision model that answers predefined questions with probabilities, and a language world model that predicts nearby vehicles’ movement for candidate actions.","excerpt":"Jev, a typed decision model that answers predefined questions with probabilities, not generated text, with a language world model that predicts for every candidate action how nearby vehicles move over the next two seconds.","support":"source-stated"},{"text":"The authors say code turns the predictions into foreseen consequences for Jev to compare.","excerpt":"Code turns these predictions into foreseen consequences, which Jev compares instead of inferring them from coordinates.","support":"source-stated"},{"text":"In simulated highway merging, the authors report that foresight reduced the same decision model’s collision rate from 26.0% to 2.4% at 0.25 seconds per decision, and that Jev-AD achieved passenger intent in 93% of free-form command trials.","excerpt":"In simulated highway merging (500 car-episodes), this foresight lowers the same decision model's collision rate from 26.0% to 2.4% at 0.25 seconds per decision, and Jev-AD achieves the passenger's intent in 93% of free-form command trials.","support":"source-stated"},{"text":"For 500 replayed real-world NGSIM episodes, the authors report a collision-rate decrease from 48.2% to 2.8%, and say the world model foresaw 93% of dangerous actions.","excerpt":"In 500 replayed real-world NGSIM episodes, foresight lowers the collision rate from 48.2% to 2.8%, and the world model, learned from this traffic, foresees 93% of dangerous actions.","support":"source-stated"},{"text":"The reported evaluations are simulations and replayed episodes, so these results alone do not establish performance in deployed vehicles.","excerpt":"In simulated highway merging (500 car-episodes)","support":"interpretation"}],"limitations":["The abstract reports results from simulated highway merging and replayed real-world NGSIM episodes; it does not report evaluation in deployed vehicles.","The evidence provided is the paper’s arXiv page and abstract, not the full paper."],"mediaId":"3751b7ab91027357836e759c2a30b0bb5426588ed14393bc81faa8e33892d7dc","correctionReason":null,"id":"254b6656659d79e018584388eaf61c8d5aa5a88523208b6c1e736f2e96a8efa0","publicationId":"a77ee978-d673-4ffe-8288-83a2640f2469","version":1,"sourceUrl":"https://arxiv.org/abs/2611.05448","sourceTitle":"Jev with Foresight: Safe Language-Guided Autonomous Driving via a Language World Model","publisher":"arXiv cs.AI","publishedAt":null,"originalPublished":{"value":"2026-11-03","precision":"day","basis":"publisher_citation_date"},"firstObservedAt":"2026-11-05T05:00:25.040Z","createdAt":"2026-11-09T09:33:40.070Z","historical":true,"entityIds":["arxiv"],"topicIds":["intelligence-and-discovery"],"media":[{"id":"3751b7ab91027357836e759c2a30b0bb5426588ed14393bc81faa8e33892d7dc","kind":"article","url":"https://arxiv.org/abs/2611.05448","sourceUrl":"https://arxiv.org/abs/2611.05448","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-09T09:32:46.302Z","method":"acquired_source","contentType":"text/html"},"recommendationReason":"Recommended by Jev for understanding this source; checked by Luna."}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.05448","checkedAt":"2026-11-09T10:36:08.304Z","items":[],"note":"No suitable media was found by the supported page extraction."},"editorialDecision":{"outcome":"accept","reasonCodes":["material_development"],"rubricVersion":"stream-admission-v5","mediaId":"3751b7ab91027357836e759c2a30b0bb5426588ed14393bc81faa8e33892d7dc","confidence":0.91,"provider":"typesafe","model":"jev-1.13.0","inputHash":"f76f0f0d18f556d33a4278edfcb2dc1b68bde55d6362ec108a7450dde2df7004","decidedAt":"2026-11-09T09:32:48.289Z"},"provenance":{"textHash":"cd462862040fe9606def6c50b8868f163ec575c1bb2b997f2e8659c30b19e805","observationId":"0c6228cd11917ef857a7dfe97d9d7c60135950ffdf25d0d5fc2f00934129a456","retrievedAt":"2026-11-09T09:32:45.956Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"da2b27a3-c41d-4750-8601-af7492aebce5"},"reviewer":{"model":"gpt-6-luna","runId":"e7ee85d2-6aa4-4056-8505-a9438b8a5cf4"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-09T09:33:40.070Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Qu, Yansong","url":null,"kind":"unknown"},{"name":"Chen, Jiancong","url":null,"kind":"unknown"},{"name":"Labi, Samuel","url":null,"kind":"unknown"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Qu, Yansong","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Qu, Yansong","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05448","locator":"head/meta[name=author|citation_author]"},"assertionId":"5e57948d93849d7c254a9441801e207a99d17e1d912d369c96522bf413738256:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T10:36:08.304Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"5e57948d93849d7c254a9441801e207a99d17e1d912d369c96522bf413738256","sourceUrl":"https://arxiv.org/abs/2611.05448","contentSha256":"b8cab83cb8b28bd84cd3f6e8ebe71055ae40c50d2d622f735e7ca05363cf78a9","textHash":"cd462862040fe9606def6c50b8868f163ec575c1bb2b997f2e8659c30b19e805","observedAt":"2026-11-09T10:36:08.304Z"}},{"actor":{"name":"Chen, Jiancong","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Chen, Jiancong","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05448","locator":"head/meta[name=author|citation_author]"},"assertionId":"5e57948d93849d7c254a9441801e207a99d17e1d912d369c96522bf413738256:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T10:36:08.304Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"5e57948d93849d7c254a9441801e207a99d17e1d912d369c96522bf413738256","sourceUrl":"https://arxiv.org/abs/2611.05448","contentSha256":"b8cab83cb8b28bd84cd3f6e8ebe71055ae40c50d2d622f735e7ca05363cf78a9","textHash":"cd462862040fe9606def6c50b8868f163ec575c1bb2b997f2e8659c30b19e805","observedAt":"2026-11-09T10:36:08.304Z"}},{"actor":{"name":"Labi, Samuel","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Labi, Samuel","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05448","locator":"head/meta[name=author|citation_author]"},"assertionId":"5e57948d93849d7c254a9441801e207a99d17e1d912d369c96522bf413738256:participation:2","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T10:36:08.304Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"5e57948d93849d7c254a9441801e207a99d17e1d912d369c96522bf413738256","sourceUrl":"https://arxiv.org/abs/2611.05448","contentSha256":"b8cab83cb8b28bd84cd3f6e8ebe71055ae40c50d2d622f735e7ca05363cf78a9","textHash":"cd462862040fe9606def6c50b8868f163ec575c1bb2b997f2e8659c30b19e805","observedAt":"2026-11-09T10:36:08.304Z"}}],"participationCoverage":{"total":3,"returned":3,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":null,"sourceUrl":"https://arxiv.org/abs/2611.05448","snapshotId":"5e57948d93849d7c254a9441801e207a99d17e1d912d369c96522bf413738256","contentSha256":"b8cab83cb8b28bd84cd3f6e8ebe71055ae40c50d2d622f735e7ca05363cf78a9","textHash":"cd462862040fe9606def6c50b8868f163ec575c1bb2b997f2e8659c30b19e805","observedAt":"2026-11-09T10:36:08.304Z","basis":"publisher-page-metadata","sourceLinks":43,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/254b6656659d79e018584388eaf61c8d5aa5a88523208b6c1e736f2e96a8efa0/source"}},"canonicalUrl":"https://escapemeridian.com/readings/jev-with-foresight-safe-language-guided-autonomous-driving-via-254b6656","formats":{"html":"/readings/jev-with-foresight-safe-language-guided-autonomous-driving-via-254b6656","markdown":"/readings/jev-with-foresight-safe-language-guided-autonomous-driving-via-254b6656.md","json":"/readings/jev-with-foresight-safe-language-guided-autonomous-driving-via-254b6656.json"},"attribution":"Headline and summary by Escape Meridian, prepared by Luna from the attributed source. A source check is not independent confirmation of the source’s claims.","maintainedGuideLinks":[],"readerContext":{"version":"reader-context-v1","attribution":"Reference context selected by Escape Meridian; separate from source evidence. Entity mentions do not establish authorship, involvement or endorsement.","terms":[{"id":"term-world-model","name":"World model","explanation":"An AI system's internal model of how an environment behaves, used to predict what happens next or to plan.","referenceUrl":"https://arxiv.org/abs/1803.10122"}],"entities":[{"id":"jev","name":"Jev","kind":"model","context":"Jev is TypeSafe AI’s model for fast evaluation and routing decisions inside AI systems.","referenceUrls":["https://typesafe.ai/blog/introducing-system-one-models-and-jev","https://typesafe.ai/"],"path":"/entities/jev","json":"/entities/jev.json","markdown":"/entities/jev.md"},{"id":"arxiv","name":"arXiv","kind":"organization","context":"arXiv is a research manuscript repository where authors share papers that may not yet have been peer reviewed.","referenceUrls":["https://arxiv.org/","https://info.arxiv.org/help/api/index.html"],"path":"/entities/arxiv","json":"/entities/arxiv.json","markdown":"/entities/arxiv.md"},{"id":"the-world","name":"The World","kind":"organization","context":"The World is a public radio news program publishing international reporting on politics, society, labor and technology.","referenceUrls":["https://theworld.org/"],"path":"/entities/the-world","json":"/entities/the-world.json","markdown":"/entities/the-world.md"}]},"researchQuestions":[],"withdrawn":false,"references":{"schemaVersion":1,"target":{"type":"reading","id":"254b6656659d79e018584388eaf61c8d5aa5a88523208b6c1e736f2e96a8efa0","revision":"a77ee978-d673-4ffe-8288-83a2640f2469","revisionKind":"publication-id","title":"Jev with Foresight: Safe Language-Guided Autonomous Driving via a Language World Model","url":"https://escapemeridian.com/readings/jev-with-foresight-safe-language-guided-autonomous-driving-via-254b6656"},"source":{"type":"source","id":"https://arxiv.org/abs/2611.05448","revision":"cd462862040fe9606def6c50b8868f163ec575c1bb2b997f2e8659c30b19e805","revisionKind":"sha256-source-text","title":"Jev with Foresight: Safe Language-Guided Autonomous Driving via a Language World Model","url":"https://arxiv.org/abs/2611.05448"},"status":"available","items":[],"next":null,"scope":"Explicit citations in public readings and public file attachments to this reading. Shared topics are not citations. Other artifact types need an explicit reference adapter."},"revisions":[{"id":"254b6656659d79e018584388eaf61c8d5aa5a88523208b6c1e736f2e96a8efa0","title":"Jev with Foresight: Safe Language-Guided Autonomous Driving via a Language World Model","argument":"Authors Yansong Qu, Jiancong Chen, and Samuel Labi present Jev-AD, which pairs Jev—a typed decision model that answers predefined questions with probabilities—with a language world model that predicts how nearby vehicles move under each candidate action. Code converts those predictions into foreseen consequences for Jev to compare, rather than requiring it to infer consequences from coordinates. In simulated highway merging, the authors report that foresight lowers the same decision model’s collision rate from 26.0% to 2.4% at 0.25 seconds per decision; Jev-AD achieves passengers’ intent in 93% of free-form command trials. In 500 replayed real-world NGSIM episodes, they report a decrease from 48.2% to 2.8%, and say the world model foresees 93% of dangerous actions. These results suggest a way to make language-guided driving decisions by comparing predicted consequences, but the reported evaluations are simulations and replayed episodes, not evidence of performance in deployed vehicles.","topicIds":["intelligence-and-discovery"],"domain":"science","claimType":"attributed reading","limits":"The abstract reports results from simulated highway merging and replayed real-world NGSIM episodes; it does not report evaluation in deployed vehicles. The evidence provided is the paper’s arXiv page and abstract, not the full paper.","speaker":{"name":"Qu, Yansong, Chen, Jiancong, Labi, Samuel","roleAtSource":"Article author"},"source":{"title":"Jev with Foresight: Safe Language-Guided Autonomous Driving via a Language World Model","publisher":"arXiv cs.AI","format":"Article","url":"https://arxiv.org/abs/2611.05448","publishedAt":"2026-11-03","dateBasis":"Date basis not provided."},"evidence":[{"text":"The authors present Jev-AD, combining Jev, a typed decision model that answers predefined questions with probabilities, and a language world model that predicts nearby vehicles’ movement for candidate actions.","excerpt":"Jev, a typed decision model that answers predefined questions with probabilities, not generated text, with a language world model that predicts for every candidate action how nearby vehicles move over the next two seconds.","url":"https://arxiv.org/abs/2611.05448","relationship":"Source-stated"},{"text":"The authors say code turns the predictions into foreseen consequences for Jev to compare.","excerpt":"Code turns these predictions into foreseen consequences, which Jev compares instead of inferring them from coordinates.","url":"https://arxiv.org/abs/2611.05448","relationship":"Source-stated"},{"text":"In simulated highway merging, the authors report that foresight reduced the same decision model’s collision rate from 26.0% to 2.4% at 0.25 seconds per decision, and that Jev-AD achieved passenger intent in 93% of free-form command trials.","excerpt":"In simulated highway merging (500 car-episodes), this foresight lowers the same decision model's collision rate from 26.0% to 2.4% at 0.25 seconds per decision, and Jev-AD achieves the passenger's intent in 93% of free-form command trials.","url":"https://arxiv.org/abs/2611.05448","relationship":"Source-stated"},{"text":"For 500 replayed real-world NGSIM episodes, the authors report a collision-rate decrease from 48.2% to 2.8%, and say the world model foresaw 93% of dangerous actions.","excerpt":"In 500 replayed real-world NGSIM episodes, foresight lowers the collision rate from 48.2% to 2.8%, and the world model, learned from this traffic, foresees 93% of dangerous actions.","url":"https://arxiv.org/abs/2611.05448","relationship":"Source-stated"},{"text":"The reported evaluations are simulations and replayed episodes, so these results alone do not establish performance in deployed vehicles.","excerpt":"In simulated highway merging (500 car-episodes)","url":"https://arxiv.org/abs/2611.05448","relationship":"Escape Meridian interpretation"}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.05448","checkedAt":"2026-11-09T10:36:08.304Z","items":[],"note":"No suitable media was found by the supported page extraction."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"How would Jev-AD perform beyond the simulated highway-merging trials and replayed NGSIM episodes reported by the authors?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Jev with Foresight: Safe Language-Guided Autonomous Driving via a Language World Model","summary":"Authors Yansong Qu, Jiancong Chen, and Samuel Labi present Jev-AD, which pairs Jev—a typed decision model that answers predefined questions with probabilities—with a language world model that predicts how nearby vehicles move under each candidate action. Code converts those predictions into foreseen consequences for Jev to compare, rather than requiring it to infer consequences from coordinates. In simulated highway merging, the authors report that foresight lowers the same decision model’s collision rate from 26.0% to 2.4% at 0.25 seconds per decision; Jev-AD achieves passengers’ intent in 93% of free-form command trials. In 500 replayed real-world NGSIM episodes, they report a decrease from 48.2% to 2.8%, and say the world model foresees 93% of dangerous actions. These results suggest a way to make language-guided driving decisions by comparing predicted consequences, but the reported evaluations are simulations and replayed episodes, not evidence of performance in deployed vehicles.","question":"How would Jev-AD perform beyond the simulated highway-merging trials and replayed NGSIM episodes reported by the authors?","claims":[{"text":"The authors present Jev-AD, combining Jev, a typed decision model that answers predefined questions with probabilities, and a language world model that predicts nearby vehicles’ movement for candidate actions.","excerpt":"Jev, a typed decision model that answers predefined questions with probabilities, not generated text, with a language world model that predicts for every candidate action how nearby vehicles move over the next two seconds.","support":"source-stated"},{"text":"The authors say code turns the predictions into foreseen consequences for Jev to compare.","excerpt":"Code turns these predictions into foreseen consequences, which Jev compares instead of inferring them from coordinates.","support":"source-stated"},{"text":"In simulated highway merging, the authors report that foresight reduced the same decision model’s collision rate from 26.0% to 2.4% at 0.25 seconds per decision, and that Jev-AD achieved passenger intent in 93% of free-form command trials.","excerpt":"In simulated highway merging (500 car-episodes), this foresight lowers the same decision model's collision rate from 26.0% to 2.4% at 0.25 seconds per decision, and Jev-AD achieves the passenger's intent in 93% of free-form command trials.","support":"source-stated"},{"text":"For 500 replayed real-world NGSIM episodes, the authors report a collision-rate decrease from 48.2% to 2.8%, and say the world model foresaw 93% of dangerous actions.","excerpt":"In 500 replayed real-world NGSIM episodes, foresight lowers the collision rate from 48.2% to 2.8%, and the world model, learned from this traffic, foresees 93% of dangerous actions.","support":"source-stated"},{"text":"The reported evaluations are simulations and replayed episodes, so these results alone do not establish performance in deployed vehicles.","excerpt":"In simulated highway merging (500 car-episodes)","support":"interpretation"}],"limitations":["The abstract reports results from simulated highway merging and replayed real-world NGSIM episodes; it does not report evaluation in deployed vehicles.","The evidence provided is the paper’s arXiv page and abstract, not the full paper."],"mediaId":"3751b7ab91027357836e759c2a30b0bb5426588ed14393bc81faa8e33892d7dc","correctionReason":null,"id":"254b6656659d79e018584388eaf61c8d5aa5a88523208b6c1e736f2e96a8efa0","publicationId":"a77ee978-d673-4ffe-8288-83a2640f2469","version":1,"sourceUrl":"https://arxiv.org/abs/2611.05448","sourceTitle":"Jev with Foresight: Safe Language-Guided Autonomous Driving via a Language World Model","publisher":"arXiv cs.AI","publishedAt":null,"originalPublished":{"value":"2026-11-03","precision":"day","basis":"publisher_citation_date"},"firstObservedAt":"2026-11-05T05:00:25.040Z","createdAt":"2026-11-09T09:33:40.070Z","historical":true,"entityIds":["arxiv"],"topicIds":["intelligence-and-discovery"],"media":[{"id":"3751b7ab91027357836e759c2a30b0bb5426588ed14393bc81faa8e33892d7dc","kind":"article","url":"https://arxiv.org/abs/2611.05448","sourceUrl":"https://arxiv.org/abs/2611.05448","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-09T09:32:46.302Z","method":"acquired_source","contentType":"text/html"},"recommendationReason":"Recommended by Jev for understanding this source; checked by Luna."}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.05448","checkedAt":"2026-11-09T10:36:08.304Z","items":[],"note":"No suitable media was found by the supported page extraction."},"editorialDecision":{"outcome":"accept","reasonCodes":["material_development"],"rubricVersion":"stream-admission-v5","mediaId":"3751b7ab91027357836e759c2a30b0bb5426588ed14393bc81faa8e33892d7dc","confidence":0.91,"provider":"typesafe","model":"jev-1.13.0","inputHash":"f76f0f0d18f556d33a4278edfcb2dc1b68bde55d6362ec108a7450dde2df7004","decidedAt":"2026-11-09T09:32:48.289Z"},"provenance":{"textHash":"cd462862040fe9606def6c50b8868f163ec575c1bb2b997f2e8659c30b19e805","observationId":"0c6228cd11917ef857a7dfe97d9d7c60135950ffdf25d0d5fc2f00934129a456","retrievedAt":"2026-11-09T09:32:45.956Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"da2b27a3-c41d-4750-8601-af7492aebce5"},"reviewer":{"model":"gpt-6-luna","runId":"e7ee85d2-6aa4-4056-8505-a9438b8a5cf4"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-09T09:33:40.070Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Qu, Yansong","url":null,"kind":"unknown"},{"name":"Chen, Jiancong","url":null,"kind":"unknown"},{"name":"Labi, Samuel","url":null,"kind":"unknown"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Qu, Yansong","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Qu, Yansong","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05448","locator":"head/meta[name=author|citation_author]"},"assertionId":"5e57948d93849d7c254a9441801e207a99d17e1d912d369c96522bf413738256:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T10:36:08.304Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"5e57948d93849d7c254a9441801e207a99d17e1d912d369c96522bf413738256","sourceUrl":"https://arxiv.org/abs/2611.05448","contentSha256":"b8cab83cb8b28bd84cd3f6e8ebe71055ae40c50d2d622f735e7ca05363cf78a9","textHash":"cd462862040fe9606def6c50b8868f163ec575c1bb2b997f2e8659c30b19e805","observedAt":"2026-11-09T10:36:08.304Z"}},{"actor":{"name":"Chen, Jiancong","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Chen, Jiancong","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05448","locator":"head/meta[name=author|citation_author]"},"assertionId":"5e57948d93849d7c254a9441801e207a99d17e1d912d369c96522bf413738256:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T10:36:08.304Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"5e57948d93849d7c254a9441801e207a99d17e1d912d369c96522bf413738256","sourceUrl":"https://arxiv.org/abs/2611.05448","contentSha256":"b8cab83cb8b28bd84cd3f6e8ebe71055ae40c50d2d622f735e7ca05363cf78a9","textHash":"cd462862040fe9606def6c50b8868f163ec575c1bb2b997f2e8659c30b19e805","observedAt":"2026-11-09T10:36:08.304Z"}},{"actor":{"name":"Labi, Samuel","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Labi, Samuel","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05448","locator":"head/meta[name=author|citation_author]"},"assertionId":"5e57948d93849d7c254a9441801e207a99d17e1d912d369c96522bf413738256:participation:2","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T10:36:08.304Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"5e57948d93849d7c254a9441801e207a99d17e1d912d369c96522bf413738256","sourceUrl":"https://arxiv.org/abs/2611.05448","contentSha256":"b8cab83cb8b28bd84cd3f6e8ebe71055ae40c50d2d622f735e7ca05363cf78a9","textHash":"cd462862040fe9606def6c50b8868f163ec575c1bb2b997f2e8659c30b19e805","observedAt":"2026-11-09T10:36:08.304Z"}}],"participationCoverage":{"total":3,"returned":3,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":null,"sourceUrl":"https://arxiv.org/abs/2611.05448","snapshotId":"5e57948d93849d7c254a9441801e207a99d17e1d912d369c96522bf413738256","contentSha256":"b8cab83cb8b28bd84cd3f6e8ebe71055ae40c50d2d622f735e7ca05363cf78a9","textHash":"cd462862040fe9606def6c50b8868f163ec575c1bb2b997f2e8659c30b19e805","observedAt":"2026-11-09T10:36:08.304Z","basis":"publisher-page-metadata","sourceLinks":43,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/254b6656659d79e018584388eaf61c8d5aa5a88523208b6c1e736f2e96a8efa0/source"}}}],"audits":[{"publicationId":"a77ee978-d673-4ffe-8288-83a2640f2469","verdict":"uncertain","findings":[{"dimension":"attribution","status":"pass","explanation":"The reading correctly credits the arXiv authors Yansong Qu, Jiancong Chen and Samuel Labi. It keeps the performance results attributed to them ('the authors report', 'say') rather than presenting them as established facts.","excerpt":"Authors:Yansong Qu, Jiancong Chen, Samuel Labi"},{"dimension":"summary","status":"uncertain","explanation":"The numbers are faithful, but the reading drops the problem the authors set up. In the abstract, large language models used as drivers reason in generated text for seconds and infer consequences implicitly. Without that, a general reader cannot see why '0.25 seconds per decision' or 'probabilities, not generated text' matters. The reading also omits the two-second prediction window that defines 'foresight'. Smallest repair: add one opening sentence stating that motivation and restore 'over the next two seconds'. 'Typed decision model' and NGSIM also need term-library tooltips.","excerpt":"as driving agents they reason in generated text for seconds and must infer each action's consequences implicitly from the scene"},{"dimension":"date","status":"pass","explanation":"The displayed original publication date of 2026-11-03 matches the v1 submission date on the arXiv page. The later feed date of 2026-11-05 is correctly not used.","excerpt":"[Submitted on 3 Nov 2026]"},{"dimension":"support","status":"pass","explanation":"Each figure is quoted accurately from the abstract: 26.0% to 2.4%, 0.25 s per decision, 93% intent, 48.2% to 2.8%, and 93% of dangerous actions foreseen. The deployment caveat is labeled as interpretation and stays within the evidence. The question follows from the stated evaluation scope rather than leading the reader.","excerpt":"In 500 replayed real-world NGSIM episodes, foresight lowers the collision rate from 48.2% to 2.8%"},{"dimension":"media","status":"pass","explanation":"The selected media is the verified direct arXiv abstract page for this paper. That is the most direct way for a reader to reach the source.","excerpt":null}],"createdAt":"2026-11-09T09:33:40.070Z","model":"anthropic/claude-opus-5.5"}],"correctionUrl":"https://escapemeridian.com/corrections/"}