{"id":"https://openalex.org/W7148671215","doi":"https://doi.org/10.1007/s10994-026-07029-7","title":"GSM-Identity: Evaluating Mathematical Reasoning in LLMs via Equivalence Transformations","display_name":"GSM-Identity: Evaluating Mathematical Reasoning in LLMs via Equivalence Transformations","publication_year":2026,"publication_date":"2026-03-10","ids":{"openalex":"https://openalex.org/W7148671215","doi":"https://doi.org/10.1007/s10994-026-07029-7"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-026-07029-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-026-07029-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-026-07029-7.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-026-07029-7.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5132915906","display_name":"Kajal Negi","orcid":null},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]},{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Kajal Negi","raw_affiliation_strings":["Institute of Science and Technologies of Information \u201cA. Faedo\u201d, CNR, Pisa, Italy","University of Pisa, Pisa, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Science and Technologies of Information \u201cA. Faedo\u201d, CNR, Pisa, Italy","institution_ids":["https://openalex.org/I122991210"]},{"raw_affiliation_string":"University of Pisa, Pisa, Italy","institution_ids":["https://openalex.org/I108290504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045636436","display_name":"Giovanni Puccetti","orcid":"https://orcid.org/0000-0002-8906-0987"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giovanni Puccetti","raw_affiliation_strings":["Institute of Science and Technologies of Information \u201cA. Faedo\u201d, CNR, Pisa, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Science and Technologies of Information \u201cA. Faedo\u201d, CNR, Pisa, Italy","institution_ids":["https://openalex.org/I122991210"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082069715","display_name":"Andrea Esuli","orcid":"https://orcid.org/0000-0002-5725-4322"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea Esuli","raw_affiliation_strings":["Institute of Science and Technologies of Information \u201cA. Faedo\u201d, CNR, Pisa, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Science and Technologies of Information \u201cA. Faedo\u201d, CNR, Pisa, Italy","institution_ids":["https://openalex.org/I122991210"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5132915906"],"corresponding_institution_ids":["https://openalex.org/I108290504","https://openalex.org/I122991210"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42809577,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"115","issue":"4","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11345","display_name":"Cognitive and developmental aspects of mathematical skills","score":0.08810000121593475,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11345","display_name":"Cognitive and developmental aspects of mathematical skills","score":0.08810000121593475,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10130","display_name":"Mathematics Education and Teaching Techniques","score":0.059700001031160355,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.04699999839067459,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/equivalence","display_name":"Equivalence (formal languages)","score":0.8033000230789185},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6852999925613403},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.49639999866485596},{"id":"https://openalex.org/keywords/mathematical-model","display_name":"Mathematical model","score":0.4496999979019165},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.438400000333786}],"concepts":[{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.8033000230789185},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6852999925613403},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4982999861240387},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.49639999866485596},{"id":"https://openalex.org/C76969082","wikidata":"https://www.wikidata.org/wiki/Q486902","display_name":"Mathematical model","level":2,"score":0.4496999979019165},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.438400000333786},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.3882000148296356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3849000036716461},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33230000734329224},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2881999909877777},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.26899999380111694},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25519999861717224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10994-026-07029-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-026-07029-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-026-07029-7.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10994-026-07029-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-026-07029-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-026-07029-7.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.47925812005996704,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322651","display_name":"Consiglio Nazionale delle Ricerche","ror":"https://ror.org/04zaypm56"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7148671215.pdf","grobid_xml":"https://content.openalex.org/works/W7148671215.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2979826702","https://openalex.org/W3133702157","https://openalex.org/W3174126466","https://openalex.org/W4294214983","https://openalex.org/W4312497550","https://openalex.org/W4387321091","https://openalex.org/W4387782510","https://openalex.org/W4402671761","https://openalex.org/W4404782964","https://openalex.org/W7133228923"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"We":[1,52,73],"introduce":[2],"GSM-Identity,":[3,90],"a":[4,42,156],"pipeline":[5],"to":[6,16,44,59,115,119,149,171],"modify":[7],"existing":[8],"mathematical":[9,50,175],"reasoning":[10,161],"benchmarks":[11],"by":[12],"adding":[13],"extra":[14],"complexity":[15],"the":[17,30,108,120,141,167],"questions":[18,142],"while":[19,91,126],"preserving":[20],"their":[21,83],"fundamental":[22],"meaning.":[23],"By":[24],"systematically":[25],"transforming":[26],"numerical":[27],"values":[28],"in":[29,107,139],"GSM8K":[31,86],"dataset":[32],"into":[33,166],"mathematically":[34],"equivalent":[35],"but":[36],"less":[37],"obvious":[38],"expressions,":[39],"we":[40,124],"create":[41],"benchmark":[43],"measure":[45],"Large":[46],"Language":[47],"Models":[48],"(LLMs)":[49],"understanding.":[51],"evaluate":[53],"LLMs":[54,170],"ranging":[55],"from":[56,162],"7":[57,109],"billions":[58,61],"72":[60],"parameters":[62,111,133],"using":[63],"multiple":[64],"prompting":[65],"strategies,":[66],"including":[67],"standard,":[68],"notice-based,":[69],"and":[70,143],"chain-of-thought":[71],"approaches.":[72],"find":[74],"that":[75,105],"Math":[76],"oriented":[77],"models":[78,94,106,127],"can":[79],"retain":[80],"most":[81],"of":[82,122,169],"performance":[84,97],"on":[85,89],"when":[87,117],"evaluated":[88],"general":[92],"purpose":[93],"show":[95],"significant":[96],"degradation.":[98],"A":[99],"comparison":[100],"with":[101,128],"human":[102],"evaluations":[103],"reveals":[104],"billion":[110,132],"range":[112],"perform":[113],"similar":[114],"humans":[116,138],"exposed":[118],"kind":[121],"modifications":[123],"study,":[125],"more":[129,135,147],"than":[130,137],"70":[131],"are":[134,145],"accurate":[136],"answering":[140],"they":[144],"also":[146],"resilient":[148],"modifications.":[150],"Our":[151],"findings":[152],"highlight":[153],"GSM-Identity":[154],"as":[155],"valuable":[157],"tool":[158],"for":[159],"distinguishing":[160],"memorization,":[163],"offering":[164],"insights":[165],"abilities":[168],"understand":[172],"higher":[173],"level":[174],"concepts.":[176]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-04-04T00:00:00"}