{"id":"https://openalex.org/W7225168674","doi":"https://doi.org/10.48550/arxiv.2611.03614","title":"Benchmark Prediction with Sparse and Unpaired Cached Responses","display_name":"Benchmark Prediction with Sparse and Unpaired Cached Responses","publication_year":2026,"publication_date":"2026-11-02","ids":{"openalex":"https://openalex.org/W7225168674","doi":"https://doi.org/10.48550/arxiv.2611.03614"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2611.03614","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.03614","pdf_url":"https://arxiv.org/pdf/2611.03614","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2611.03614","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091316872","display_name":"Hayden S. Helm","orcid":"https://orcid.org/0000-0001-9475-8100","observed_orcids":["https://orcid.org/0000-0001-9475-8100"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Helm, Hayden","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101463080","display_name":"Avijit Ghosh","orcid":"https://orcid.org/0000-0002-8540-3698","observed_orcids":["https://orcid.org/0000-0002-8540-3698"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ghosh, Avijit","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135879788","display_name":"Ben Johnson","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Johnson, Ben","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5031834098","display_name":"Carey E. Priebe","orcid":"https://orcid.org/0000-0002-0139-7201","observed_orcids":["https://orcid.org/0000-0002-0139-7201"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Priebe, Carey","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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/T10028","display_name":"Topic Modeling","score":0.7929999828338623,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7929999828338623,"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":0.023499999195337296,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.02070000022649765,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/generative-model-evaluation","display_name":"generative model evaluation","score":0.8420000076293945},{"id":"https://openalex.org/keywords/model-representation","display_name":"model representation","score":0.31200000643730164},{"id":"https://openalex.org/keywords/benchmark-suite","display_name":"benchmark suite","score":0.3959999978542328}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8925999999046326},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6610000133514404},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5795999765396118},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.553600013256073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.544700026512146},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.4350000023841858},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.38600000739097595},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38179999589920044},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3474000096321106},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.34470000863075256},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3215999901294708},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.3156999945640564},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.2703999876976013},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2603999972343445},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.2572000026702881}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2611.03614","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.03614","pdf_url":"https://arxiv.org/pdf/2611.03614","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.2611.03614","doi":"https://doi.org/10.48550/arxiv.2611.03614","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.03614","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:2611.03614","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.03614","pdf_url":"https://arxiv.org/pdf/2611.03614","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":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225168674.pdf","grobid_xml":"https://content.openalex.org/works/W7225168674.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7160836797","https://openalex.org/W4417134733","https://openalex.org/W7128536746","https://openalex.org/W7133348120","https://openalex.org/W7162397470","https://openalex.org/W7165785310","https://openalex.org/W7117129718","https://openalex.org/W7225084720","https://openalex.org/W7197010394","https://openalex.org/W7148865587"],"abstract_inverted_index":{"Evaluating":[0],"a":[1,32,62],"generative":[2,81],"model":[3],"on":[4,21,70,139],"all":[5,8],"queries":[6,30,94],"from":[7,31,122],"available":[9],"benchmark":[10,109,140,145],"tasks":[11,25],"is":[12,96,113],"prohibitively":[13],"expensive.":[14],"As":[15],"such,":[16],"models":[17,68,82],"are":[18,47],"often":[19],"evaluated":[20],"different":[22,27],"subsets":[23,28],"of":[24,29,38,64,67,127],"and/or":[26],"given":[33],"task.":[34],"The":[35],"resulting":[36],"collection":[37,63],"responses":[39,85],"and":[40,49,95,102,124],"the":[41,56,128],"corresponding":[42],"(model,":[43],"task)":[44],"score":[45],"matrix":[46],"sparse":[48,101],"unpaired.":[50],"In":[51],"this":[52],"paper,":[53],"we":[54,106,132],"introduce":[55],"Product":[57],"Kernel":[58],"Perspective":[59],"Space":[60],"(PKPS),":[61],"low-dimensional":[65],"representations":[66],"based":[69],"their":[71],"embedded":[72],"responses.":[73],"PKPS":[74,112],"generalizes":[75],"existing":[76],"methods":[77,117,136],"for":[78],"representing":[79],"black-box":[80],"by":[83],"comparing":[84],"to":[86,99,116],"similar":[87],"--":[88,93],"rather":[89],"than":[90],"just":[91],"identical":[92],"therefore":[97],"able":[98],"utilize":[100],"unpaired":[103],"information.":[104],"Theoretically,":[105],"show":[107,133],"that":[108,118,134],"prediction":[110,141],"using":[111],"query-efficient":[114],"relative":[115],"only":[119],"use":[120],"information":[121],"dense":[123],"paired":[125],"portions":[126],"evaluation":[129],"data.":[130],"Empirically,":[131],"PKPS-based":[135],"outperform":[137],"baselines":[138],"across":[142],"two":[143],"large":[144],"suites.":[146]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-11-04T00:00:00"}