{"id":"https://openalex.org/W7225819921","doi":"https://doi.org/10.5281/zenodo.24140300","title":"Noise, Selection and Speed: What Local Runs and a Public Leaderboard Can Tell You About a Coding Agent","display_name":"Noise, Selection and Speed: What Local Runs and a Public Leaderboard Can Tell You About a Coding Agent","publication_year":2026,"publication_date":"2026-11-11","ids":{"openalex":"https://openalex.org/W7225819921","doi":"https://doi.org/10.5281/zenodo.24140300"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24140300","doi":"https://doi.org/10.5281/zenodo.24140300","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24140300","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.24140300","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5161495159","display_name":"Raul Malik","orcid":"https://orcid.org/0009-0005-3722-0132","observed_orcids":["https://orcid.org/0009-0005-3722-0132"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Malik, Raul","raw_affiliation_strings":["Independent"],"raw_orcid":"https://orcid.org/0009-0005-3722-0132","affiliations":[{"raw_affiliation_string":"Independent","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5161495159"],"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/T10260","display_name":"Software Engineering Research","score":0.7612000107765198,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.7612000107765198,"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"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.029500000178813934,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.02199999988079071,"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":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5893999934196472},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.5825999975204468},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5734000205993652},{"id":"https://openalex.org/C170806853","wikidata":"https://www.wikidata.org/wiki/Q2746099","display_name":"Gemma","level":2,"score":0.4521999955177307},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4269999861717224},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.38690000772476196},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.36230000853538513},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3538999855518341},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3292999863624573},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.326200008392334},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3197999894618988},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.30660000443458557},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2985000014305115},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C2781315470","wikidata":"https://www.wikidata.org/wiki/Q193623","display_name":"Binomial (polynomial)","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25699999928474426}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.5281/zenodo.24140300","doi":"https://doi.org/10.5281/zenodo.24140300","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24140300","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5281/zenodo.24140301","doi":"https://doi.org/10.5281/zenodo.24140301","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24140301","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5281/zenodo.24141849","doi":"https://doi.org/10.5281/zenodo.24141849","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24141849","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.5281/zenodo.24140300","doi":"https://doi.org/10.5281/zenodo.24140300","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24140300","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Agent":[0,44],"competitions":[1],"rank":[2],"teams":[3,113,115],"by":[4,131],"the":[5,25,40,72,78,87,96,105,136,140,145,151,156,163,179,187],"best":[6,97],"of":[7,69,98,104],"many":[8],"stochastic":[9],"runs":[10,48,126],"on":[11,49,71,144,150],"a":[12,22,33,66,89,123,132],"few":[13],"dozen":[14],"hidden":[15],"tasks.":[16],"I":[17,147,190],"measure":[18],"how":[19],"much":[20],"such":[21],"ranking,":[23],"and":[24,55,84,200],"local":[26,164],"experiments":[27,121],"behind":[28],"it,":[29],"can":[30,101],"resolve,":[31],"using":[32],"Gemma":[34,41],"4":[35,42],"31B":[36],"coding":[37],"agent":[38,137],"in":[39,81,108,170],"Developer":[43],"Competition.":[45],"Three":[46],"identical":[47],"129":[50],"tasks":[51,58,176],"solve":[52],"54,":[53],"51":[54],"53:":[56],"20":[57],"(16%)":[59],"change":[60],"outcome":[61],"between":[62],"runs,":[63],"which":[64],"implies":[65],"run-to-run":[67],"spread":[68],"0.030":[70],"58-task":[73],"public":[74],"score,":[75],"close":[76],"to":[77,114],"0.025":[79],"seen":[80],"byte-identical":[82],"resubmissions":[83],"well":[85],"below":[86],"0.047":[88],"binomial":[90],"model":[91],"assumes.":[92],"Under":[93],"this":[94,149],"noise,":[95],"k":[99],"submissions":[100,199],"explain":[102],"0.06":[103],"0.08":[106],"rise":[107],"median":[109],"score":[110],"from":[111],"one-submission":[112],"with":[116,177],"32":[117],"or":[118],"more.":[119],"Local":[120],"have":[122],"second":[124],"problem:":[125],"that":[127],"scale":[128],"time":[129,141],"limits":[130],"calibration":[133],"factor":[134],"give":[135,191],"2.5":[138],"times":[139],"it":[142],"has":[143],"scorer.":[146],"confirm":[148],"scorer's":[152],"own":[153],"hardware,":[154],"where":[155],"same":[157],"agent's":[158],"patches":[159],"still":[160],"pass":[161],"at":[162,186],"rate.":[165],"The":[166],"only":[167],"significant":[168],"gain":[169],"my":[171],"study,":[172],"64":[173],"against":[174],"54":[175],"twice":[178],"call":[180],"budget":[181],"(p":[182],"=":[183],"0.04),":[184],"disappears":[185],"measured":[188],"speed.":[189],"concrete":[192],"rules":[193],"for":[194],"comparing":[195],"agents,":[196],"choosing":[197],"final":[198],"reporting":[201],"leaderboard":[202],"results.":[203]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-12T00:00:00"}