{"id":"https://openalex.org/W7162776864","doi":"https://doi.org/10.48550/arxiv.2605.29710","title":"PhAIL: A Real-Robot VLA Benchmark and Distributional Methodology","display_name":"PhAIL: A Real-Robot VLA Benchmark and Distributional Methodology","publication_year":2026,"publication_date":"2026-05-28","ids":{"openalex":"https://openalex.org/W7162776864","doi":"https://doi.org/10.48550/arxiv.2605.29710"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2605.29710","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.29710","pdf_url":"https://arxiv.org/pdf/2605.29710","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/2605.29710","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005562336","display_name":"Sergey Arkhangelskiy","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Arkhangelskiy, Sergey","raw_affiliation_strings":["Positronic Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Positronic Robotics","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5005562336"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9897000193595886,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9897000193595886,"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":0.007000000216066837,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0008999999845400453,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/vision-language-action-policies","display_name":"vision-language-action policies","score":0.9800000190734863},{"id":"https://openalex.org/keywords/bootstrap-confidence-intervals","display_name":"bootstrap confidence intervals","score":0.7139999866485596},{"id":"https://openalex.org/keywords/robotic-manipulation","display_name":"robotic manipulation","score":0.3479999899864197},{"id":"https://openalex.org/keywords/open-source-benchmark","display_name":"open-source benchmark","score":0.4359999895095825}],"concepts":[{"id":"https://openalex.org/C31691690","wikidata":"https://www.wikidata.org/wiki/Q1753979","display_name":"Timeout","level":2,"score":0.75},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7156999707221985},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.5878000259399414},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.5695000290870667},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.5285999774932861},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4950999915599823},{"id":"https://openalex.org/C103784038","wikidata":"https://www.wikidata.org/wiki/Q386228","display_name":"Cumulative distribution function","level":3,"score":0.47679999470710754},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4410000145435333},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4334999918937683},{"id":"https://openalex.org/C63002673","wikidata":"https://www.wikidata.org/wiki/Q2260590","display_name":"Scoring rule","level":2,"score":0.41370001435279846},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3882000148296356},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.37369999289512634},{"id":"https://openalex.org/C122048520","wikidata":"https://www.wikidata.org/wiki/Q2913954","display_name":"Percentile","level":2,"score":0.35420000553131104},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33970001339912415},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C2776292839","wikidata":"https://www.wikidata.org/wiki/Q5179217","display_name":"Coverage probability","level":3,"score":0.30649998784065247},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C143380155","wikidata":"https://www.wikidata.org/wiki/Q5160088","display_name":"Confidence region","level":3,"score":0.27570000290870667},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C2779190172","wikidata":"https://www.wikidata.org/wiki/Q4913888","display_name":"Binary data","level":3,"score":0.26429998874664307},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2612000107765198},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C65778772","wikidata":"https://www.wikidata.org/wiki/Q12345341","display_name":"Asymptotic distribution","level":3,"score":0.2563000023365021}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2605.29710","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.29710","pdf_url":"https://arxiv.org/pdf/2605.29710","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.2605.29710","doi":"https://doi.org/10.48550/arxiv.2605.29710","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29710","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:2605.29710","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.29710","pdf_url":"https://arxiv.org/pdf/2605.29710","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/W7162776864.pdf","grobid_xml":"https://content.openalex.org/works/W7162776864.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W4385430674","https://openalex.org/W4385430679","https://openalex.org/W4385473486","https://openalex.org/W4387764390","https://openalex.org/W4390635563","https://openalex.org/W4399695759","https://openalex.org/W4400612090","https://openalex.org/W4403752043","https://openalex.org/W4403819516","https://openalex.org/W4414079054","https://openalex.org/W4414079252","https://openalex.org/W4414674749","https://openalex.org/W4414898213","https://openalex.org/W4414901575","https://openalex.org/W4416055005","https://openalex.org/W6966800739","https://openalex.org/W7154467967","https://openalex.org/W7204808299"],"related_works":["https://openalex.org/W7163826799","https://openalex.org/W7163151374","https://openalex.org/W7138016593","https://openalex.org/W7161951754","https://openalex.org/W7214905502","https://openalex.org/W7214065221","https://openalex.org/W7171367839","https://openalex.org/W7155513687","https://openalex.org/W7222852268","https://openalex.org/W4417309052"],"abstract_inverted_index":{"Real-world":[0],"evaluation":[1,66,76],"of":[2,63],"vision-language-action":[3],"(VLA)":[4],"policies":[5],"still":[6],"rests":[7],"on":[8,52],"binary":[9],"success":[10],"rate":[11],"at":[12,133],"a":[13,53,64,90,105],"fixed":[14],"timeout":[15],"with":[16,78,93],"$N":[17,134],"\\le":[18,135],"25$":[19],"rollouts":[20,137],"per":[21,138,166],"condition,":[22],"almost":[23],"always":[24],"without":[25],"confidence":[26,95],"intervals":[27],"or":[28],"paired":[29],"statistical":[30],"comparison;":[31],"these":[32],"cohort":[33],"sizes":[34],"struggle":[35],"to":[36,98],"resolve":[37],"close":[38,125],"comparisons":[39,126],"reliably.":[40],"We":[41],"introduce":[42],"PhAIL":[43],"(Physical":[44],"AI":[45],"Leaderboard,":[46],"https://phail.ai),":[47],"an":[48],"open":[49],"real-robot":[50],"benchmark":[51],"Franka":[54],"FR3":[55],"(dataset,":[56],"per-rollout":[57],"artifacts,":[58],"and":[59,111],"end-to-end":[60],"reference":[61],"implementation)":[62],"distributional":[65],"methodology:":[67],"the":[68,75,119,147,171],"time-to-success":[69],"cumulative":[70],"distribution":[71],"function":[72],"(CDF)":[73],"as":[74],"primitive,":[77],"two":[79,124],"separated":[80],"jobs.":[81],"The":[82,102,158],"first":[83],"is":[84,104,162],"scoring":[85],"via":[86],"Human-Relative":[87],"Throughput":[88],"(HRT),":[89],"dimensionless":[91],"scalar":[92],"bootstrap":[94],"intervals,":[96],"anchored":[97],"same-fixture":[99],"human":[100,172],"teleoperation.":[101],"second":[103],"significance":[106],"test":[107,122],"(Kolmogorov-Smirnov,":[108],"computed":[109],"per-object":[110],"macro-averaged":[112,120],"across":[113],"objects).":[114],"On":[115],"four":[116],"publicly-available":[117],"VLAs,":[118],"KS":[121],"resolves":[123],"(GR00T":[127],"vs.":[128,131,151],"ACT,":[129],"OpenPI":[130],"ACT)":[132],"30$":[136],"(model,":[139],"object)":[140],"cell":[141],"where":[142],"binary-threshold":[143],"metrics":[144],"do":[145],"not;":[146],"closest":[148],"pair":[149],"(OpenPI":[150],"GR00T)":[152],"remains":[153],"unresolved":[154],"within":[155],"our":[156],"budget.":[157],"best":[159],"evaluated":[160],"VLA":[161],"$\\sim":[163],"7\\times$":[164],"slower":[165],"operation":[167],"(RMST":[168],"ratio)":[169],"than":[170],"reference.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-05-30T00:00:00"}