{"id":"https://openalex.org/W7138172320","doi":"https://doi.org/10.1609/aaai.v40i23.39022","title":"SpatialLogic-Bench: A Diagnostic Benchmark for Task-Oriented Spatiotemporal Reasoning","display_name":"SpatialLogic-Bench: A Diagnostic Benchmark for Task-Oriented Spatiotemporal Reasoning","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138172320","doi":"https://doi.org/10.1609/aaai.v40i23.39022"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i23.39022","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i23.39022","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i23.39022","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040461965","display_name":"Xiaoda Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoda Yang","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125731196","display_name":"Shenzhou Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I108688024","display_name":"Qingdao University","ror":"https://ror.org/021cj6z65","country_code":"CN","type":"education","lineage":["https://openalex.org/I108688024"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shenzhou Gao","raw_affiliation_strings":["Qingdao University"],"affiliations":[{"raw_affiliation_string":"Qingdao University","institution_ids":["https://openalex.org/I108688024"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129651826","display_name":"Can Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I108688024","display_name":"Qingdao University","ror":"https://ror.org/021cj6z65","country_code":"CN","type":"education","lineage":["https://openalex.org/I108688024"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Can Wang","raw_affiliation_strings":["Qingdao University"],"affiliations":[{"raw_affiliation_string":"Qingdao University","institution_ids":["https://openalex.org/I108688024"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087855708","display_name":"Jiahe Zhang","orcid":"https://orcid.org/0000-0003-3571-097X"},"institutions":[{"id":"https://openalex.org/I108688024","display_name":"Qingdao University","ror":"https://ror.org/021cj6z65","country_code":"CN","type":"education","lineage":["https://openalex.org/I108688024"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahe Zhang","raw_affiliation_strings":["Qingdao University"],"affiliations":[{"raw_affiliation_string":"Qingdao University","institution_ids":["https://openalex.org/I108688024"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013700946","display_name":"Menglan Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I108688024","display_name":"Qingdao University","ror":"https://ror.org/021cj6z65","country_code":"CN","type":"education","lineage":["https://openalex.org/I108688024"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Menglan Tang","raw_affiliation_strings":["Qingdao University"],"affiliations":[{"raw_affiliation_string":"Qingdao University","institution_ids":["https://openalex.org/I108688024"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jingyang Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I108688024","display_name":"Qingdao University","ror":"https://ror.org/021cj6z65","country_code":"CN","type":"education","lineage":["https://openalex.org/I108688024"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyang Xue","raw_affiliation_strings":["Qingdao University"],"affiliations":[{"raw_affiliation_string":"Qingdao University","institution_ids":["https://openalex.org/I108688024"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129676407","display_name":"Sheng Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sheng Liu","raw_affiliation_strings":["Karlsruher Institut f\u00fcr Technologie"],"affiliations":[{"raw_affiliation_string":"Karlsruher Institut f\u00fcr Technologie","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129722766","display_name":"Peijian Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I108688024","display_name":"Qingdao University","ror":"https://ror.org/021cj6z65","country_code":"CN","type":"education","lineage":["https://openalex.org/I108688024"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peijian Zhang","raw_affiliation_strings":["Qingdao University"],"affiliations":[{"raw_affiliation_string":"Qingdao University","institution_ids":["https://openalex.org/I108688024"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129677490","display_name":"Yao Mu","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Mu","raw_affiliation_strings":["Shanghai Jiaotong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiaotong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129719405","display_name":"Xiangyu Yue","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiangyu Yue","raw_affiliation_strings":["The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5040461965"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.47584187,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"23","first_page":"19441","last_page":"19449"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7132999897003174,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7132999897003174,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11431","display_name":"Action Observation and Synchronization","score":0.04450000077486038,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11904","display_name":"Spatial Cognition and Navigation","score":0.041099999099969864,"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/benchmark","display_name":"Benchmark (surveying)","score":0.7562999725341797},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6176000237464905},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6119999885559082},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5552999973297119},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4625000059604645},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.44940000772476196},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.35350000858306885},{"id":"https://openalex.org/keywords/spatial-intelligence","display_name":"Spatial intelligence","score":0.3504999876022339}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7562999725341797},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7243000268936157},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6176000237464905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6151999831199646},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6119999885559082},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5552999973297119},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5041000247001648},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4625000059604645},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.44940000772476196},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.35350000858306885},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.3504999876022339},{"id":"https://openalex.org/C162670838","wikidata":"https://www.wikidata.org/wiki/Q6057295","display_name":"Interval temporal logic","level":3,"score":0.33340001106262207},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2687999904155731},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C43971567","wikidata":"https://www.wikidata.org/wiki/Q3142865","display_name":"Logical reasoning","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i23.39022","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i23.39022","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i23.39022","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i23.39022","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5175595283508301,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"},{"score":0.4251064956188202,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-Language":[0],"Models":[1],"(VLMs)":[2],"have":[3],"made":[4],"significant":[5,154],"progress":[6],"in":[7,109,160,180],"static":[8,25],"perception,":[9,138],"but":[10],"their":[11,54],"ability":[12,55],"to":[13,46,56,70,83,87],"understand":[14],"dynamic":[15,33,189],"task-oriented":[16],"reasoning":[17,34,173],"remains":[18],"unclear.":[19],"Existing":[20],"benchmarks":[21],"mainly":[22],"focus":[23],"on":[24,157,167],"spatial":[26,190],"relationships":[27],"and":[28,53,90,112,183],"lack":[29],"systematic":[30],"assessment":[31],"of":[32,50],"capabilities.":[35,192],"To":[36,96],"this":[37],"end,":[38],"we":[39,101],"propose":[40],"SpatialLogic-Bench,":[41],"a":[42,103,122],"novel":[43],"benchmark":[44,61],"designed":[45],"evaluate":[47],"VLMs\u2019":[48],"understanding":[49],"spatiotemporal":[51],"logic":[52],"assess":[57],"task":[58,88,117],"progress.":[59,95],"The":[60],"assesses":[62],"two":[63],"critical":[64,178],"capabilities:":[65],"first,":[66],"fine-grained":[67,137],"visual":[68],"discrimination":[69],"accurately":[71],"perceive":[72],"subtle":[73],"physical":[74],"changes":[75,86],"between":[76,130],"state":[77],"frames;":[78],"second,":[79],"the":[80,135],"logical":[81,145],"capacity":[82],"connect":[84],"these":[85],"goals":[89],"judge":[91],"whether":[92],"they":[93],"indicate":[94],"mitigate":[97],"temporal":[98,168],"dependency":[99],"biases,":[100],"introduce":[102],"dual-task":[104],"paradigm,":[105],"presenting":[106],"image":[107],"pairs":[108],"both":[110],"chronological":[111,162],"reversed":[113],"orders":[114],"while":[115,139],"keeping":[116],"descriptions":[118],"consistent.":[119],"We":[120],"construct":[121],"multi-scale":[123],"evaluation":[124,148],"system":[125],"by":[126],"varying":[127],"time":[128],"intervals":[129,133,141],"frames:":[131],"smaller":[132],"test":[134],"model's":[136],"larger":[140],"demand":[142],"more":[143],"sophisticated":[144],"inference.":[146],"Empirical":[147],"reveals":[149],"that":[150],"most":[151],"VLMs":[152],"experience":[153],"performance":[155],"degradation":[156],"tasks":[158],"presented":[159],"inverse":[161],"order,":[163],"indicating":[164],"an":[165],"over-reliance":[166],"cues":[169],"rather":[170],"than":[171],"robust":[172],"abilities.":[174],"SpatialLogic-Bench":[175],"clearly":[176],"exposes":[177],"limitations":[179],"current":[181],"models":[182],"provides":[184],"valuable":[185],"guidance":[186],"for":[187],"improving":[188],"perception":[191]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2026-03-18T00:00:00"}
