{"id":"https://openalex.org/W7225035463","doi":"https://doi.org/10.5281/zenodo.23863738","title":"brAIAIn: A Language Model Trained Exclusively on What It Was Paid to Learn","display_name":"brAIAIn: A Language Model Trained Exclusively on What It Was Paid to Learn","publication_year":2026,"publication_date":"2026-11-01","ids":{"openalex":"https://openalex.org/W7225035463","doi":"https://doi.org/10.5281/zenodo.23863738"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23863738","doi":"https://doi.org/10.5281/zenodo.23863738","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23863738","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":"article-journal"},"volume":null,"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.23863738","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160307916","display_name":"BRAIAIN Laboratories","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"BRAIAIN Laboratories","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5160307916"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8286697,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.5102999806404114,"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":0.5102999806404114,"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":0.43650001287460327,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.004999999888241291,"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/training-data-provenance","display_name":"training data provenance","score":0.6650000214576721},{"id":"https://openalex.org/keywords/truthfulqa","display_name":"TruthfulQA","score":0.9210000038146973},{"id":"https://openalex.org/keywords/small-language-models","display_name":"small language models","score":0.5149999856948853}],"concepts":[{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.7681999802589417},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.715399980545044},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5812000036239624},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5590000152587891},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5526999831199646},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5321999788284302},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5042999982833862},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.48489999771118164},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.48030000925064087},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.44279998540878296},{"id":"https://openalex.org/C2778571376","wikidata":"https://www.wikidata.org/wiki/Q1355821","display_name":"Frontier","level":2,"score":0.4153999984264374},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.39100000262260437},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.30550000071525574},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.2896000146865845},{"id":"https://openalex.org/C94922259","wikidata":"https://www.wikidata.org/wiki/Q33215","display_name":"Constructed language","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C2780589192","wikidata":"https://www.wikidata.org/wiki/Q7285140","display_name":"Raising (metalworking)","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.27730000019073486},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.2590999901294708}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.23863738","doi":"https://doi.org/10.5281/zenodo.23863738","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23863738","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":"article-journal"},{"id":"doi:10.5281/zenodo.23863739","doi":"https://doi.org/10.5281/zenodo.23863739","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23863739","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":"article-journal"}],"best_oa_location":{"id":"doi:10.5281/zenodo.23863738","doi":"https://doi.org/10.5281/zenodo.23863738","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23863738","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":"article-journal"},"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/W4412887063","https://openalex.org/W4389519861","https://openalex.org/W7161581028","https://openalex.org/W7136204024","https://openalex.org/W7172420567","https://openalex.org/W3027602624","https://openalex.org/W7172501068","https://openalex.org/W4414478590","https://openalex.org/W4385571158","https://openalex.org/W4412886926"],"abstract_inverted_index":{"Frontier":[0],"language":[1,21],"models":[2],"are":[3],"trained":[4,43,84],"on":[5,16,44,85,129],"trillions":[6],"of":[7,34,61,95,111,149],"tokens":[8,113],"whose":[9,23],"origin":[10],"is":[11,26,82],"rarely":[12],"disclosed.":[13],"We":[14,159],"report":[15],"brAIAIn,":[17],"a":[18,31,45,59,91,150],"word":[19],"trigram":[20],"model":[22,117,126],"entire":[24],"trainingset":[25],"public,":[27],"numbered,":[28],"and,":[29],"with":[30],"small":[32],"number":[33],"labeled":[35,74],"exceptions,":[36],"paid":[37],"for.":[38],"The":[39],"first":[40],"version":[41,51,81],"was":[42],"twelve-line":[46],"founding":[47],"text.":[48],"Each":[49,80],"later":[50],"adds":[52],"exactly":[53],"one":[54],"sentence,":[55],"either":[56],"purchased":[57],"by":[58,70,88,115],"member":[60],"the":[62,71,101,109,116,125,155,164,169],"public":[63],"for":[64],"five":[65],"US":[66],"dollars":[67],"or":[68],"written":[69,87,114],"lab":[72],"and":[73,124,168],"as":[75],"an":[76],"unpaid":[77],"internal":[78],"release.":[79],"also":[83],"passages":[86],"its":[89,141],"predecessor,":[90],"deliberate":[92],"small-scale":[93],"instance":[94],"recursive":[96],"selftraining.":[97],"Across":[98],"7":[99],"versions":[100],"vocabulary":[102],"grew":[103],"from":[104,120],"96":[105],"to":[106,122],"130":[107],"words,":[108],"share":[110],"training":[112,166],"itself":[118],"rose":[119],"0%":[121],"41.9%,":[123],"scored":[127],"0.0%":[128],"all":[130],"1,319":[131],"GSM8K":[132],"test":[133],"problems":[134],"in":[135],"every":[136,161],"version.":[137],"On":[138],"TruthfulQA":[139],"MC1":[140],"best":[142],"perword":[143],"score,":[144],"36.7%,":[145],"falls":[146],"just":[147],"short":[148],"baseline":[151],"that":[152],"always":[153],"picks":[154],"longest":[156],"answer":[157],"(36.8%).":[158],"release":[160],"version's":[162],"weights,":[163],"complete":[165],"data":[167],"evaluation":[170],"code":[171],"under":[172],"CC0.":[173]},"counts_by_year":[],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2026-11-02T00:00:00"}