{"id":"https://openalex.org/W7225459590","doi":"https://doi.org/10.5281/zenodo.24045212","title":"Three Pre-registered Comparisons of pi, Codex CLI and Claude Code on Personal-Assistant Tasks","display_name":"Three Pre-registered Comparisons of pi, Codex CLI and Claude Code on Personal-Assistant Tasks","publication_year":2026,"publication_date":"2026-11-07","ids":{"openalex":"https://openalex.org/W7225459590","doi":"https://doi.org/10.5281/zenodo.24045212"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24045212","doi":"https://doi.org/10.5281/zenodo.24045212","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24045212","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.24045212","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120861516","display_name":"Carl Vincent Ladres Kho","orcid":"https://orcid.org/0000-0003-3131-7214","observed_orcids":["https://orcid.org/0000-0003-3131-7214"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kho, Carl Vincent","raw_affiliation_strings":["Independent researcher"],"raw_orcid":"https://orcid.org/0000-0003-3131-7214","affiliations":[{"raw_affiliation_string":"Independent researcher","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5120861516"],"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":0.3334999978542328,"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":0.3334999978542328,"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/T13904","display_name":"Artificial Intelligence Applications","score":0.31540000438690186,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.05719999969005585,"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/ai-agents","display_name":"AI agents","score":0.5709999799728394},{"id":"https://openalex.org/keywords/personal-assistants","display_name":"personal assistants","score":0.5609999895095825},{"id":"https://openalex.org/keywords/claude-code","display_name":"Claude Code","score":0.9909999966621399},{"id":"https://openalex.org/keywords/tool-calls","display_name":"tool calls","score":0.7099999785423279},{"id":"https://openalex.org/keywords/agent-failure","display_name":"agent failure","score":0.3019999861717224},{"id":"https://openalex.org/keywords/task-success-rate","display_name":"task success rate","score":0.3659999966621399},{"id":"https://openalex.org/keywords/cost-comparison","display_name":"cost comparison","score":0.43299999833106995}],"concepts":[{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6790000200271606},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.6517000198364258},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5533999800682068},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4772000014781952},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3675999939441681},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.3644999861717224},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.24420000612735748},{"id":"https://openalex.org/C2778565505","wikidata":"https://www.wikidata.org/wiki/Q2207566","display_name":"Spec#","level":2,"score":0.24040000140666962},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2378000020980835}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24045212","doi":"https://doi.org/10.5281/zenodo.24045212","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24045212","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.24045213","doi":"https://doi.org/10.5281/zenodo.24045213","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24045213","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.24045212","doi":"https://doi.org/10.5281/zenodo.24045212","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24045212","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":["https://openalex.org/W7213372153","https://openalex.org/W7220707912","https://openalex.org/W7216310052","https://openalex.org/W7222809978","https://openalex.org/W7225424218","https://openalex.org/W7168292465","https://openalex.org/W7202211081","https://openalex.org/W7203839682","https://openalex.org/W7223655301","https://openalex.org/W7171537577"],"abstract_inverted_index":{"When":[0],"an":[1,167],"AI":[2],"agent":[3],"fails":[4],"at":[5,33],"a":[6,102,145,148,190],"task,":[7],"the":[8,12,16,20,25,41,46,53,179,203,278,284,294],"cause":[9],"can":[10],"be":[11],"language":[13],"model":[14,150,181],"or":[15],"program":[17],"that":[18,92,142,287],"runs":[19],"model,":[21,43],"which":[22],"is":[23],"called":[24],"harness.":[26],"Most":[27],"comparisons":[28],"of":[29,118,269],"agents":[30,97],"change":[31],"both":[32,112],"once.":[34],"We":[35],"compared":[36],"harnesses":[37,113],"while":[38,193],"giving":[39],"them":[40,277],"same":[42,204],"checked":[44],"against":[45,61,73,224],"provider's":[47],"own":[48],"report":[49],"on":[50,65,77,178,267,274],"every":[51],"run:":[52],"harness":[54],"pi,":[55],"configured":[56],"as":[57,100,104,126,174],"one":[58],"person's":[59],"assistant,":[60],"OpenAI's":[62],"Codex":[63,154],"CLI":[64],"OpenAI":[66],"models":[67],"(Studies":[68],"1":[69,111],"and":[70,72,121,183,211,243,272],"2)":[71],"Anthropic's":[74],"Claude":[75,78,209,233,261],"Code":[76,210,234,262],"Sonnet":[79],"4.5":[80],"(Study":[81],"3).":[82],"The":[83],"tasks":[84,271,280],"were":[85,291],"synthetic":[86],"errands":[87],"built":[88,281],"around":[89],"ten":[90],"mistakes":[91],"person":[93],"had":[94],"repeatedly":[95],"corrected":[96,292],"for,":[98],"such":[99],"reporting":[101],"job":[103],"done":[105],"without":[106],"checking":[107],"it.":[108],"In":[109,258],"Study":[110,130,198],"succeeded":[114],"equally":[115],"often":[116],"(98.3%":[117],"development":[119],"runs)":[120,139,207],"pi":[122,212,266],"used":[123],"about":[124],"twice":[125],"many":[127,175],"tool":[128,176,241],"calls.":[129],"2":[131],"(registered":[132,200],"in":[133,159,201],"advance;":[134,202],"30":[135,270],"harder":[136],"tasks,":[137,205],"540":[138],"asked":[140],"whether":[141],"tie":[143],"hid":[144],"ceiling.":[146],"On":[147],"weaker":[149],"pi's":[151,185,245],"lead":[152],"over":[153],"did":[155],"not":[156,236],"grow":[157],"(difference":[158],"differences":[160],"-7.8":[161],"points,":[162,228],"95%":[163,229],"CI":[164,230],"[-18.9,":[165],"2.2]),":[166],"inconclusive":[168],"result.":[169],"Pi":[170],"made":[171],"1.84":[172],"times":[173],"calls":[177],"stronger":[180],"only,":[182],"removing":[184,244],"extensions":[186,246],"kept":[187],"success":[188,252],"within":[189,216],"10-point":[191],"margin":[192],"cutting":[194],"cost":[195,263],"by":[196],"17%.":[197],"3":[199],"270":[206],"found":[208],"neither":[213,248],"shown":[214,220,237,249,254],"equivalent":[215],"10":[217],"points":[218],"nor":[219,253],"different":[221],"(success":[222],"43.3%":[223],"52.2%,":[225],"difference":[226],"-8.9":[227],"[-23.3,":[231],"5.6]).":[232],"was":[235,247],"to":[238,250,255,282],"make":[239],"fewer":[240],"calls,":[242],"keep":[251],"save":[256],"money.":[257],"exploratory":[259],"analyses":[260],"less":[264],"than":[265],"26":[268],"more":[273],"four,":[275],"among":[276],"three":[279],"overflow":[283],"context.":[285],"Graders":[286],"misjudged":[288],"some":[289],"answers":[290],"after":[293],"runs;":[295],"no":[296],"registered":[297],"decision":[298],"changed.":[299]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-11-08T00:00:00"}
