{"id":"https://openalex.org/W7214444580","doi":"https://doi.org/10.5281/zenodo.22980931","title":"Capability, Reliability, and Generality: A Blind Multi-Model Elicitation of Hypotheses About Frontier LLM Progress","display_name":"Capability, Reliability, and Generality: A Blind Multi-Model Elicitation of Hypotheses About Frontier LLM Progress","publication_year":2026,"publication_date":"2026-09-26","ids":{"openalex":"https://openalex.org/W7214444580","doi":"https://doi.org/10.5281/zenodo.22980931"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.22980931","doi":"https://doi.org/10.5281/zenodo.22980931","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22980931","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.22980931","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124164516","display_name":"Yanush Feshter","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Feshter, Yanush","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0002-1330-7530","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5124164516"],"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/T10028","display_name":"Topic Modeling","score":0.5717999935150146,"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":0.5717999935150146,"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/T13904","display_name":"Artificial Intelligence Applications","score":0.15610000491142273,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.10689999908208847,"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/large-language-models","display_name":"large language models","score":0.8209999799728394},{"id":"https://openalex.org/keywords/hypothesis-generation","display_name":"hypothesis generation","score":0.43700000643730164},{"id":"https://openalex.org/keywords/testable-predictions","display_name":"falsifiable predictions","score":0.8019999861717224},{"id":"https://openalex.org/keywords/evaluation-awareness","display_name":"evaluation awareness","score":0.43299999833106995},{"id":"https://openalex.org/keywords/in-context-learning","display_name":"in-context learning","score":0.609000027179718},{"id":"https://openalex.org/keywords/benchmark-performance","display_name":"benchmark performance","score":0.4099999964237213},{"id":"https://openalex.org/keywords/claude-opus","display_name":"Claude Opus","score":0.8360000252723694},{"id":"https://openalex.org/keywords/gpt-5-6","display_name":"GPT-5.6","score":0.9610000252723694}],"concepts":[{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6539999842643738},{"id":"https://openalex.org/C2778571376","wikidata":"https://www.wikidata.org/wiki/Q1355821","display_name":"Frontier","level":2,"score":0.636900007724762},{"id":"https://openalex.org/C2777152325","wikidata":"https://www.wikidata.org/wiki/Q108163","display_name":"Proposition","level":2,"score":0.6172999739646912},{"id":"https://openalex.org/C116222747","wikidata":"https://www.wikidata.org/wiki/Q220888","display_name":"Falsifiability","level":2,"score":0.5389000177383423},{"id":"https://openalex.org/C111640148","wikidata":"https://www.wikidata.org/wiki/Q847349","display_name":"Rubric","level":2,"score":0.4844000041484833},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4530999958515167},{"id":"https://openalex.org/C150672426","wikidata":"https://www.wikidata.org/wiki/Q191183","display_name":"Brainstorming","level":2,"score":0.44780001044273376},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.4357999861240387},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.41130000352859497},{"id":"https://openalex.org/C2778805511","wikidata":"https://www.wikidata.org/wiki/Q1713","display_name":"Citation","level":2,"score":0.3950999975204468},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.39250001311302185},{"id":"https://openalex.org/C197947376","wikidata":"https://www.wikidata.org/wiki/Q5155608","display_name":"Comparability","level":2,"score":0.3781999945640564},{"id":"https://openalex.org/C2777868144","wikidata":"https://www.wikidata.org/wiki/Q7239817","display_name":"Preference elicitation","level":3,"score":0.36309999227523804},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.3598000109195709},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.35929998755455017},{"id":"https://openalex.org/C7991579","wikidata":"https://www.wikidata.org/wiki/Q17955","display_name":"Criticism","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3206999897956848},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.313400000333786},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.3027999997138977},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29109999537467957},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.2808000147342682},{"id":"https://openalex.org/C118084267","wikidata":"https://www.wikidata.org/wiki/Q26110","display_name":"Positive economics","level":1,"score":0.27950000762939453},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.26899999380111694},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2669999897480011},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.26409998536109924},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.25459998846054077},{"id":"https://openalex.org/C190248442","wikidata":"https://www.wikidata.org/wiki/Q839486","display_name":"Qualitative research","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C2779462738","wikidata":"https://www.wikidata.org/wiki/Q17146409","display_name":"Realisation","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C75969862","wikidata":"https://www.wikidata.org/wiki/Q5141215","display_name":"Cognitive interview","level":3,"score":0.25130000710487366}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.5281/zenodo.22980931","doi":"https://doi.org/10.5281/zenodo.22980931","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22980931","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.22980932","doi":"https://doi.org/10.5281/zenodo.22980932","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22980932","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.22994669","doi":"https://doi.org/10.5281/zenodo.22994669","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22994669","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.23021639","doi":"https://doi.org/10.5281/zenodo.23021639","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23021639","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.22980931","doi":"https://doi.org/10.5281/zenodo.22980931","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22980931","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7155576675","https://openalex.org/W7084107716","https://openalex.org/W7166115268","https://openalex.org/W7162773986","https://openalex.org/W7162095784","https://openalex.org/W7117894208","https://openalex.org/W6922800472","https://openalex.org/W7222949183","https://openalex.org/W7223014764","https://openalex.org/W4399354747"],"abstract_inverted_index":{"A":[0,147],"qualitative":[1],"elicitation":[2],"study":[3],"in":[4,27,92,122],"which":[5],"three":[6,94],"frontier":[7,28,113],"large":[8],"language":[9,56],"models":[10,57,209],"(SuperGrok":[11],"4.6":[12],"Expert,":[13],"Claude":[14],"Opus":[15],"5.5":[16],"High,":[17],"GPT-5.6)":[18],"answered":[19],"the":[20,178,194,198,205,208],"same":[21],"seven":[22],"questions":[23],"about":[24],"whether":[25,126],"progress":[26],"LLMs":[29],"could":[30],"become":[31],"decoupled":[32],"across":[33],"capability,":[34],"benchmark":[35],"performance,":[36],"reliability,":[37],"real-world":[38],"usefulness":[39],"and":[40,76,79,102,142,155,207,214,218,248],"properties":[41],"relevant":[42],"to":[43,129],"robust":[44,123],"general":[45,124],"intelligence.":[46],"The":[47,63,107,135,191],"purpose":[48],"is":[49,58,111,133],"hypothesis":[50],"discovery,":[51],"not":[52,59,117,161],"confirmation:":[53],"agreement":[54],"among":[55],"evidence":[60],"of":[61,197,224],"truth.":[62],"paper":[64,136,192,229],"separates":[65],"model-generated":[66],"hypotheses,":[67],"cross-model":[68],"recurrence,":[69],"independently":[70],"verified":[71],"evidence,":[72],"mechanisms,":[73],"causal":[74],"claims":[75],"falsifiable":[77],"predictions,":[78],"checks":[80],"every":[81],"model-supplied":[82],"citation":[83],"or":[84],"figure":[85],"against":[86],"primary":[87],"sources.":[88],"Five":[89],"decompositions":[90],"recurred":[91],"all":[93],"models,":[95],"including":[96,200],"capability":[97,114],"ceiling":[98],"vs.":[99,104],"reliability":[100],"floor":[101],"model-level":[103],"system-level":[105],"capability.":[106],"strongest":[108],"defensible":[109],"proposition":[110],"that":[112,216],"gains":[115,121],"do":[116,130],"logically":[118],"entail":[119],"proportional":[120],"competence;":[125],"they":[127],"fail":[128],"so":[131],"empirically":[132],"open.":[134],"states":[137],"ten":[138],"hypotheses":[139],"with":[140,187,246],"counterarguments":[141],"proposes":[143],"nine":[144],"falsification":[145],"experiments.":[146],"second":[148],"round":[149],"adds":[150],"a":[151,156,169],"cross-review,":[152,239],"memory-off":[153,170],"reruns":[154],"control":[157],"question.":[158],"Anonymisation":[159],"did":[160],"hold:":[162],"reviewers":[163],"recognised":[164],"their":[165],"own":[166],"responses,":[167],"except":[168],"reviewer":[171],"(0/7).":[172],"Several":[173],"model-specific":[174],"themes":[175],"depended":[176],"on":[177,211],"researcher's":[179],"accumulated":[180],"context":[181],"(e.g.":[182],"evaluation":[183],"awareness:":[184],"26":[185],"mentions":[186],"memory,":[188],"0":[189],"without).":[190],"documents":[193],"full":[195],"provenance":[196],"hypothesis,":[199],"prior":[201],"joint":[202],"brainstorming":[203],"between":[204],"researcher":[206],"published":[210],"X":[212,253],"(@YaffFesh),":[213],"argues":[215],"in-context":[217],"clean":[219],"runs":[220],"are":[221],"complementary":[222],"arms":[223],"one":[225],"instrument.":[226],"Files:":[227],"main":[228],"(PDF);":[230],"Supplement":[231,235],"S1":[232],"(first-round":[233],"transcripts);":[234],"S2":[236],"(second":[237],"round:":[238],"reruns,":[240],"control,":[241],"X-post":[242],"context);":[243],"LaTeX":[244],"source":[245],"transcripts":[247],"analysis":[249],"data.":[250],"Author":[251],"profiles:":[252],"https://x.com/YaffFesh":[254],"\u00b7":[255],"Bluesky":[256],"https://bsky.app/profile/yafffesh.bsky.social":[257]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-09-27T00:00:00"}