{"id":"https://openalex.org/W7118343723","doi":"https://doi.org/10.48550/arxiv.2601.03038","title":"Validating Generalist Robots with Situation Calculus and STL Falsification","display_name":"Validating Generalist Robots with Situation Calculus and STL Falsification","publication_year":2026,"publication_date":"2026-01-06","ids":{"openalex":"https://openalex.org/W7118343723","doi":"https://doi.org/10.48550/arxiv.2601.03038"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2601.03038","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.03038","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2601.03038","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122222706","display_name":"Changwen Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Li, Changwen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122044258","display_name":"Rongjie Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Rongjie","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121975260","display_name":"Chih-Hong Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Chih-Hong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5122107345","display_name":"Jian Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jian","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5122222706"],"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/T10142","display_name":"Formal Methods in Verification","score":0.3391999900341034,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10142","display_name":"Formal Methods in Verification","score":0.3391999900341034,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.11180000007152557,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.10270000249147415,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.8644000291824341},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6396999955177307},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6377000212669373},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6212000250816345},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3402999937534332},{"id":"https://openalex.org/keywords/model-checking","display_name":"Model checking","score":0.3382999897003174}],"concepts":[{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.8644000291824341},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7639999985694885},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6396999955177307},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6377000212669373},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6212000250816345},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5300999879837036},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4961000084877014},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.37619999051094055},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3564999997615814},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3402999937534332},{"id":"https://openalex.org/C110251889","wikidata":"https://www.wikidata.org/wiki/Q1569697","display_name":"Model checking","level":2,"score":0.3382999897003174},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3192000091075897},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.302700012922287},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C22497172","wikidata":"https://www.wikidata.org/wiki/Q1559077","display_name":"Situation calculus","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2605000138282776},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.26030001044273376}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2601.03038","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.03038","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2601.03038","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.03038","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"score":0.7408414483070374,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generalist":[0],"robots":[1],"are":[2,88],"becoming":[3],"a":[4,41],"reality,":[5],"capable":[6],"of":[7,35],"interpreting":[8],"natural":[9],"language":[10],"instructions":[11],"and":[12,29,62],"executing":[13],"diverse":[14],"operations.":[15],"However,":[16],"their":[17],"validation":[18,37,43],"remains":[19],"challenging":[20],"because":[21],"each":[22],"task":[23],"induces":[24],"its":[25,115],"own":[26],"operational":[27],"context":[28],"correctness":[30],"specification,":[31],"exceeding":[32],"the":[33,54,60,83,110],"assumptions":[34],"traditional":[36],"methods.":[38],"We":[39],"propose":[40],"two-layer":[42],"framework":[44,104],"that":[45,102],"combines":[46],"abstract":[47,55],"reasoning":[48],"with":[49,78,93],"concrete":[50,84],"system":[51],"falsification.":[52],"At":[53,82],"layer,":[56,85],"situation":[57],"calculus":[58],"models":[59],"world":[61],"derives":[63],"weakest":[64],"preconditions,":[65],"enabling":[66],"constraint-aware":[67],"combinatorial":[68],"testing":[69],"to":[70],"systematically":[71],"generate":[72],"diverse,":[73],"semantically":[74],"valid":[75],"world-task":[76],"configurations":[77,87],"controllable":[79],"coverage":[80],"strength.":[81],"these":[86],"instantiated":[89],"for":[90,117],"simulation-based":[91],"falsification":[92],"STL":[94],"monitoring.":[95],"Experiments":[96],"on":[97],"tabletop":[98],"manipulation":[99],"tasks":[100],"show":[101],"our":[103],"effectively":[105],"uncovers":[106],"failure":[107],"cases":[108],"in":[109],"NVIDIA":[111],"GR00T":[112],"controller,":[113],"demonstrating":[114],"promise":[116],"validating":[118],"general-purpose":[119],"robot":[120],"autonomy.":[121]},"counts_by_year":[],"updated_date":"2026-01-08T20:10:11.968330","created_date":"2026-01-08T00:00:00"}
