{"id":"https://openalex.org/W4417101611","doi":"https://doi.org/10.48550/arxiv.2508.01922","title":"Beyond Simulation: Benchmarking World Models for Planning and Causality in Autonomous Driving","display_name":"Beyond Simulation: Benchmarking World Models for Planning and Causality in Autonomous Driving","publication_year":2025,"publication_date":"2025-08-03","ids":{"openalex":"https://openalex.org/W4417101611","doi":"https://doi.org/10.48550/arxiv.2508.01922"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2508.01922","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.01922","pdf_url":"https://arxiv.org/pdf/2508.01922","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.01922","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063275464","display_name":"Hunter Schofield","orcid":"https://orcid.org/0000-0002-0647-1300"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Schofield, Hunter","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000554621","display_name":"Mohammed Elmahgiubi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elmahgiubi, Mohammed","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078758172","display_name":"Kasra Rezaee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rezaee, Kasra","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5071093853","display_name":"Jinjun Shan","orcid":"https://orcid.org/0000-0002-4911-6739"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shan, Jinjun","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5063275464"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.5081999897956848,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.5081999897956848,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.09769999980926514,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11942","display_name":"Transportation and Mobility Innovations","score":0.06530000269412994,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5742999911308289},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5618000030517578},{"id":"https://openalex.org/keywords/real-world-data","display_name":"Real world data","score":0.48809999227523804},{"id":"https://openalex.org/keywords/causality","display_name":"Causality (physics)","score":0.3156000077724457},{"id":"https://openalex.org/keywords/virtual-world","display_name":"Virtual world","score":0.28360000252723694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6186000108718872},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5742999911308289},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5618000030517578},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.48809999227523804},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.3594000041484833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3555000126361847},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.29179999232292175},{"id":"https://openalex.org/C3019565508","wikidata":"https://www.wikidata.org/wiki/Q444835","display_name":"Virtual world","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.25999999046325684},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25929999351501465},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2508.01922","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.01922","pdf_url":"https://arxiv.org/pdf/2508.01922","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2508.01922","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.01922","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.01922","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.01922","pdf_url":"https://arxiv.org/pdf/2508.01922","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"World":[0],"models":[1,22,39,136,169,179,190],"have":[2],"become":[3],"increasingly":[4],"popular":[5],"in":[6,102],"acting":[7],"as":[8,40,56,180],"learned":[9],"traffic":[10,18,41],"simulators.":[11],"Recent":[12],"work":[13],"has":[14],"explored":[15],"replacing":[16],"traditional":[17],"simulators":[19,42],"with":[20],"world":[21,38,54,77,93,107,168,178,189],"for":[23,51,59,182],"policy":[24,60,183],"training.":[25,61],"In":[26],"this":[27],"work,":[28],"we":[29,63,99,109,159],"explore":[30],"the":[31,46,65,69,84,92,104,111,123,145,152,165,175],"robustness":[32],"of":[33,132,167,177],"existing":[34],"metrics":[35,48,162],"to":[36,43,116,122,150,163,170],"evaluate":[37,174],"see":[44],"if":[45],"same":[47],"are":[49,86,100,120],"suitable":[50],"evaluating":[52,103],"a":[53,57,129],"model":[55,78,94],"pseudo-environment":[58],"Specifically,":[62],"analyze":[64,186],"metametric":[66],"employed":[67],"by":[68,91],"Waymo":[70],"Open":[71],"Sim-Agents":[72],"Challenge":[73],"(WOSAC)":[74],"and":[75,173,185],"compare":[76],"predictions":[79],"on":[80],"standard":[81,112],"scenarios":[82,133],"where":[83,134],"agents":[85,118],"fully":[87],"or":[88],"partially":[89],"controlled":[90],"(partial":[95],"replay).":[96],"Furthermore,":[97],"since":[98],"interested":[101],"ego":[105,124,146],"action-conditioned":[106],"model,":[108],"extend":[110],"WOSAC":[113],"evaluation":[114],"domain":[115],"include":[117],"that":[119],"causal":[121],"vehicle.":[125],"Our":[126],"evaluations":[127],"reveal":[128],"significant":[130],"number":[131],"top-ranking":[135],"perform":[137],"well":[138],"under":[139,191],"no":[140],"perturbation":[141],"but":[142],"fail":[143],"when":[144],"agent":[147],"is":[148],"forced":[149],"replay":[151],"original":[153],"trajectory.":[154],"To":[155],"address":[156],"these":[157,192],"cases,":[158],"propose":[160],"new":[161,193],"highlight":[164],"sensitivity":[166],"uncontrollable":[171],"objects":[172],"performance":[176],"pseudo-environments":[181],"training":[184],"some":[187],"state-of-the-art":[188],"metrics.":[194]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}