{"id":"https://openalex.org/W7214735252","doi":"https://doi.org/10.48550/arxiv.2609.32109","title":"How Reusable Are Benchmarks with Richer Feedback?","display_name":"How Reusable Are Benchmarks with Richer Feedback?","publication_year":2026,"publication_date":"2026-09-26","ids":{"openalex":"https://openalex.org/W7214735252","doi":"https://doi.org/10.48550/arxiv.2609.32109"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.32109","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.32109","pdf_url":"https://arxiv.org/pdf/2609.32109","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/2609.32109","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084267332","display_name":"Youssef Allouah","orcid":"https://orcid.org/0000-0003-1048-7548","observed_orcids":["https://orcid.org/0000-0003-1048-7548"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Allouah, Youssef","raw_affiliation_strings":["Department of Computer Science Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061331093","display_name":"John C. Duchi","orcid":"https://orcid.org/0000-0003-0045-7185","observed_orcids":["https://orcid.org/0000-0003-0045-7185"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Duchi, John","raw_affiliation_strings":["Departments of Statistics and Electrical Engineering Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departments of Statistics and Electrical Engineering Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I97018004"],"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/T12535","display_name":"Machine Learning and Data Classification","score":0.2524000108242035,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.2524000108242035,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.1429000049829483,"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/T10028","display_name":"Topic Modeling","score":0.05979999899864197,"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/assessment-feedback","display_name":"assessment feedback","score":0.7680000066757202},{"id":"https://openalex.org/keywords/test-set-size","display_name":"test set size","score":0.5839999914169312},{"id":"https://openalex.org/keywords/model-building","display_name":"model development","score":0.30300000309944153}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7196000218391418},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7117999792098999},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6743000149726868},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6554999947547913},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.439300000667572},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.4056999981403351},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4000999927520752},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.39259999990463257},{"id":"https://openalex.org/C75235859","wikidata":"https://www.wikidata.org/wiki/Q582659","display_name":"Exponential growth","level":2,"score":0.31700000166893005},{"id":"https://openalex.org/C2982777018","wikidata":"https://www.wikidata.org/wiki/Q99268086","display_name":"Adaptive design","level":3,"score":0.28999999165534973},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28690001368522644},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.2847000062465668},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27140000462532043},{"id":"https://openalex.org/C2984074130","wikidata":"https://www.wikidata.org/wiki/Q73539779","display_name":"R package","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C111110010","wikidata":"https://www.wikidata.org/wiki/Q2627315","display_name":"Convex combination","level":4,"score":0.2563000023365021}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.32109","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.32109","pdf_url":"https://arxiv.org/pdf/2609.32109","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.2609.32109","doi":"https://doi.org/10.48550/arxiv.2609.32109","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.32109","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:2609.32109","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.32109","pdf_url":"https://arxiv.org/pdf/2609.32109","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/W7214735252.pdf","grobid_xml":"https://content.openalex.org/works/W7214735252.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W1982723861","https://openalex.org/W2077641783","https://openalex.org/W2225981128","https://openalex.org/W2624735416","https://openalex.org/W2786731311","https://openalex.org/W2963699739","https://openalex.org/W4205228770","https://openalex.org/W4411320023","https://openalex.org/W7165642588"],"related_works":["https://openalex.org/W7166854554","https://openalex.org/W4414890433","https://openalex.org/W4414528631","https://openalex.org/W7165785310","https://openalex.org/W4417115503","https://openalex.org/W7159155045","https://openalex.org/W4416385802","https://openalex.org/W7214034687","https://openalex.org/W7160908778","https://openalex.org/W4403941865"],"abstract_inverted_index":{"We":[0,17],"study":[1],"whether":[2],"benchmarks":[3,76],"reliably":[4],"guide":[5],"model":[6,75,127],"selection":[7],"as":[8],"developers":[9,109],"adapt":[10],"to":[11,25,79,84,112],"evaluation":[12],"feedback":[13,82],"across":[14],"multiple":[15],"criteria.":[16],"find":[18],"that":[19],"the":[20,27,40,45,50,116],"worst-case":[21],"test-set":[22],"size":[23],"needed":[24],"estimate":[26],"best":[28],"score":[29,91],"among":[30],"$k$":[31,55],"adaptively":[32],"chosen":[33],"models,":[34],"under":[35],"any":[36],"convex":[37],"combination":[38],"of":[39,47,53],"criteria,":[41,48,63,81],"grows":[42],"exponentially":[43],"with":[44,59,77],"number":[46],"reaching":[49],"$\u0398(\\sqrt{k})$":[51],"cost":[52],"answering":[54],"adaptive":[56],"statistical":[57],"queries":[58],"only":[60],"$O(\\log":[61],"k)$":[62],"at":[64],"fixed":[65],"accuracy":[66],"and":[67,93],"confidence.":[68],"In":[69],"attacks":[70],"on":[71],"multi-task":[72],"large":[73,89],"language":[74],"five":[78],"ten":[80],"restricted":[83],"nondominated":[85],"task":[86],"profiles":[87],"produces":[88],"reused-to-held-out":[90],"gaps":[92],"frequent":[94],"false":[95],"winners.":[96],"These":[97],"results":[98],"challenge":[99],"a":[100],"prominent":[101],"explanation":[102],"for":[103],"prior":[104],"observed":[105],"reliable":[106],"benchmark":[107],"reuse---that":[108],"mainly":[110],"respond":[111],"convincing":[113],"improvements":[114],"over":[115],"current":[117],"best---in":[118],"rich-feedback":[119],"settings,":[120],"while":[121],"leaving":[122],"open":[123],"how":[124],"often":[125],"ordinary":[126],"development":[128],"encounters":[129],"this":[130],"vulnerability.":[131]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-30T00:00:00"}