{"id":"https://openalex.org/W7224018422","doi":"https://doi.org/10.48550/arxiv.2610.35730","title":"SPECOLA: A Tool for Specification Driven Robot Evaluation","display_name":"SPECOLA: A Tool for Specification Driven Robot Evaluation","publication_year":2026,"publication_date":"2026-10-26","ids":{"openalex":"https://openalex.org/W7224018422","doi":"https://doi.org/10.48550/arxiv.2610.35730"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.35730","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.35730","pdf_url":"https://arxiv.org/pdf/2610.35730","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.35730","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093679039","display_name":"Immanuel Ampomah Mensah","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mensah, Immanuel Ampomah","raw_affiliation_strings":["Cornell University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020074157","display_name":"Hadas Kress\u2010Gazit","orcid":"https://orcid.org/0000-0002-7754-1011","observed_orcids":["https://orcid.org/0000-0002-7754-1011"]},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kress-Gazit, Hadas","raw_affiliation_strings":["Cornell University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.8695999979972839,"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":0.8695999979972839,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.048500001430511475,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.02979999966919422,"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/robot-evaluation","display_name":"robot evaluation","score":0.6710000038146973},{"id":"https://openalex.org/keywords/simulation-benchmarking","display_name":"simulation benchmarking","score":0.7250000238418579},{"id":"https://openalex.org/keywords/signal-temporal-logic","display_name":"signal temporal logic","score":0.8920000195503235},{"id":"https://openalex.org/keywords/libero","display_name":"LIBERO","score":0.550000011920929}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7351999878883362},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.6927000284194946},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.6362000107765198},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5806000232696533},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5519000291824341},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.5443000197410583},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4415999948978424},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.37779998779296875},{"id":"https://openalex.org/C37789001","wikidata":"https://www.wikidata.org/wiki/Q782543","display_name":"Graphical user interface","level":2,"score":0.3723999857902527},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35569998621940613},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3456000089645386},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.3384999930858612},{"id":"https://openalex.org/C25016198","wikidata":"https://www.wikidata.org/wiki/Q781833","display_name":"Temporal logic","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3156999945640564},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3118000030517578},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C116253237","wikidata":"https://www.wikidata.org/wiki/Q1437424","display_name":"Formal specification","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2702000141143799},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C201677973","wikidata":"https://www.wikidata.org/wiki/Q1209840","display_name":"Specification language","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.35730","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.35730","pdf_url":"https://arxiv.org/pdf/2610.35730","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.35730","doi":"https://doi.org/10.48550/arxiv.2610.35730","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.35730","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.35730","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.35730","pdf_url":"https://arxiv.org/pdf/2610.35730","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224018422.pdf","grobid_xml":"https://content.openalex.org/works/W7224018422.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7170068690","https://openalex.org/W6921453465","https://openalex.org/W4387364760","https://openalex.org/W3177477589","https://openalex.org/W4410580354","https://openalex.org/W7139120219","https://openalex.org/W4409640588","https://openalex.org/W3176233416","https://openalex.org/W4415317041","https://openalex.org/W3096990961"],"abstract_inverted_index":{"Simulation":[0],"benchmarks":[1],"are":[2,198],"a":[3,28,62,79,92,108,139,144],"useful":[4],"way":[5],"to":[6,44,72,83,102,118],"measure":[7,19,76],"progress":[8],"in":[9,91,114],"robotics;":[10],"typically":[11],"they":[12],"provide":[13,143,159,168,184],"success":[14,23,42,55],"rate":[15,24],"as":[16],"the":[17,31,41,135,189],"dominant":[18],"of":[20],"performance.":[21],"However,":[22],"reports":[25],"only":[26],"whether":[27,54],"rollout":[29],"completed":[30],"task,":[32],"hiding":[33],"by":[34],"what":[35],"margin":[36],"it":[37,49,68,101],"succeeded,":[38],"how":[39,77],"sensitive":[40],"is":[43,82],"goal":[45],"parameter":[46],"changes,":[47],"requirements":[48],"may":[50],"have":[51],"violated,":[52],"and":[53,75,99,131,133,147,167,174,181,196],"persisted.":[56],"Signal":[57],"Temporal":[58],"Logic":[59],"(STL)":[60],"provides":[61,122],"formal":[63],"language":[64],"for":[65,110,125,150,163,170],"capturing":[66],"specifications;":[67],"can":[69],"be":[70],"used":[71],"define":[73],"requirements,":[74],"close":[78],"robot":[80,112],"behavior":[81],"satisfying":[84],"or":[85],"violating":[86],"them.":[87],"Using":[88],"STL":[89,119],"monitors":[90,137],"simulator,":[93],"however,":[94],"requires":[95],"exposing":[96],"simulator":[97,129],"state":[98],"mapping":[100],"specification-relevant":[103],"signals.":[104],"We":[105,142,158,183],"present":[106],"Specola,":[107],"tool":[109],"evaluating":[111],"behaviors":[113],"simulation":[115,172],"with":[116],"respect":[117],"specifications.":[120],"Specola":[121,193],"an":[123,160],"interface":[124,149,162],"writing":[126],"specifications":[127],"over":[128],"signals,":[130],"creates":[132],"manages":[134],"relevant":[136],"while":[138],"policy":[140,155],"executes.":[141],"Python":[145],"API":[146],"command-line":[148],"integrating":[151],"monitoring":[152],"into":[153],"existing":[154],"execution":[156],"loops.":[157],"adapter":[161],"connecting":[164],"new":[165],"simulators,":[166],"adapters":[169,197],"nine":[171],"environments":[173],"benchmarks,":[175],"including":[176],"LIBERO,":[177],"RoboCasa,":[178],"Isaac":[179],"Lab,":[180],"RoboDojo.":[182],"case":[185],"studies":[186],"that":[187,192],"illustrate":[188],"nuanced":[190],"evaluation":[191],"enables.":[194],"Code":[195],"available":[199],"at":[200],"https://github.com/specola-eval/specola.":[201]},"counts_by_year":[],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2026-10-28T00:00:00"}
