{"id":"https://openalex.org/W4417070798","doi":"https://doi.org/10.48550/arxiv.2509.08713","title":"The More You Automate, the Less You See: Hidden Pitfalls of AI Scientist Systems","display_name":"The More You Automate, the Less You See: Hidden Pitfalls of AI Scientist Systems","publication_year":2025,"publication_date":"2025-09-10","ids":{"openalex":"https://openalex.org/W4417070798","doi":"https://doi.org/10.48550/arxiv.2509.08713"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2509.08713","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.08713","pdf_url":"https://arxiv.org/pdf/2509.08713","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/2509.08713","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Luo, Ziming","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Ziming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047979305","display_name":"Atoosa Kasirzadeh","orcid":"https://orcid.org/0000-0002-5967-3782","observed_orcids":["https://orcid.org/0000-0002-5967-3782"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kasirzadeh, Atoosa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5034272491","display_name":"Nihar B. Shah","orcid":"https://orcid.org/0000-0001-5158-9677","observed_orcids":["https://orcid.org/0000-0001-5158-9677"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shah, Nihar B.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.4496999979019165,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.4496999979019165,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.21570000052452087,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13607","display_name":"Academic Publishing and Open Access","score":0.09700000286102295,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/failure-modes","display_name":"failure modes","score":0.9269999861717224},{"id":"https://openalex.org/keywords/benchmark-selection","display_name":"benchmark selection","score":0.9110000133514404},{"id":"https://openalex.org/keywords/data-leakage","display_name":"data leakage","score":0.996999979019165},{"id":"https://openalex.org/keywords/reproducibility","display_name":"reproducibility","score":0.7870000004768372},{"id":"https://openalex.org/keywords/research-integrity","display_name":"research integrity","score":0.6190000176429749},{"id":"https://openalex.org/keywords/transparency-and-accountability","display_name":"transparency and accountability","score":0.4410000145435333}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7447999715805054},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6280999779701233},{"id":"https://openalex.org/C2776050585","wikidata":"https://www.wikidata.org/wiki/Q7439360","display_name":"Scrutiny","level":2,"score":0.5712000131607056},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5573999881744385},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.4399000108242035},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.42719998955726624},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4262000024318695},{"id":"https://openalex.org/C2775884135","wikidata":"https://www.wikidata.org/wiki/Q845436","display_name":"Mandate","level":2,"score":0.42329999804496765},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4171999990940094},{"id":"https://openalex.org/C2777230681","wikidata":"https://www.wikidata.org/wiki/Q7923820","display_name":"Vetting","level":2,"score":0.38190001249313354},{"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/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.30709999799728394},{"id":"https://openalex.org/C147494362","wikidata":"https://www.wikidata.org/wiki/Q2078905","display_name":"Troubleshooting","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C2984917352","wikidata":"https://www.wikidata.org/wiki/Q12772819","display_name":"Scientific discovery","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C55587333","wikidata":"https://www.wikidata.org/wiki/Q1133029","display_name":"Engineering ethics","level":1,"score":0.2623000144958496},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.26170000433921814},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2509.08713","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.08713","pdf_url":"https://arxiv.org/pdf/2509.08713","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.2509.08713","doi":"https://doi.org/10.48550/arxiv.2509.08713","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.08713","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":"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":"pmh:oai:arXiv.org:2509.08713","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.08713","pdf_url":"https://arxiv.org/pdf/2509.08713","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7220387322","https://openalex.org/W4416026872","https://openalex.org/W7162324529","https://openalex.org/W7164926635","https://openalex.org/W7204947539","https://openalex.org/W7172473591","https://openalex.org/W7161721808","https://openalex.org/W7134202413","https://openalex.org/W4417114405","https://openalex.org/W7213510367"],"abstract_inverted_index":{"AI":[0,71,104,113],"scientist":[1,72,105,114],"systems,":[2],"capable":[3],"of":[4,30,40,45,56,109,119,125,154,175],"autonomously":[5],"executing":[6],"the":[7,27,51,117,145,159,179],"full":[8,146],"research":[9,58,171],"workflow":[10,29,148],"from":[11,144],"hypothesis":[12],"generation":[13],"and":[14,54,81,142,167,185],"experimentation":[15],"to":[16,102,139,172,181],"paper":[17,161,180],"writing,":[18],"hold":[19],"significant":[20],"potential":[21,66],"for":[22],"accelerating":[23],"scientific":[24],"discovery.":[25],"However,":[26],"internal":[28],"these":[31,87,176],"systems":[32,115],"have":[33],"not":[34],"been":[35],"closely":[36],"examined.":[37],"This":[38],"lack":[39],"scrutiny":[41],"poses":[42],"a":[43,123],"risk":[44],"introducing":[46],"flaws":[47],"that":[48,93,137],"could":[49],"undermine":[50],"integrity,":[52],"reliability,":[53],"trustworthiness":[55],"their":[57],"outputs.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63,89,135],"identify":[64],"four":[65],"failure":[67,96],"modes":[68],"in":[69,132],"contemporary":[70],"systems:":[73],"inappropriate":[74],"benchmark":[75],"selection,":[76],"data":[77],"leakage,":[78],"metric":[79],"misuse,":[80],"post-hoc":[82],"selection":[83],"bias.":[84],"To":[85],"examine":[86],"risks,":[88],"design":[90],"controlled":[91],"experiments":[92],"isolate":[94],"each":[95],"mode":[97],"while":[98],"addressing":[99],"challenges":[100],"unique":[101],"evaluating":[103,169],"systems.":[106],"Our":[107],"assessment":[108],"two":[110],"prominent":[111],"open-source":[112],"reveals":[116],"presence":[118],"several":[120],"failures,":[121],"across":[122],"spectrum":[124],"severity,":[126],"which":[127],"can":[128],"be":[129],"easily":[130],"overlooked":[131],"practice.":[133],"Finally,":[134],"demonstrate":[136],"access":[138],"trace":[140],"logs":[141],"code":[143],"automated":[147],"enables":[149],"far":[150],"more":[151],"effective":[152],"detection":[153],"such":[155],"failures":[156],"than":[157],"examining":[158],"final":[160],"alone.":[162],"We":[163],"thus":[164],"recommend":[165],"journals":[166],"conferences":[168],"AI-generated":[170],"mandate":[173],"submission":[174],"artifacts":[177],"alongside":[178],"ensure":[182],"transparency,":[183],"accountability,":[184],"reproducibility.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}