{"id":"https://openalex.org/W4413304709","doi":"https://doi.org/10.1088/2632-2153/adfcb0","title":"Theoretical physics benchmark (TPBench)\u2014a dataset and study of AI reasoning capabilities in theoretical physics","display_name":"Theoretical physics benchmark (TPBench)\u2014a dataset and study of AI reasoning capabilities in theoretical physics","publication_year":2025,"publication_date":"2025-08-18","ids":{"openalex":"https://openalex.org/W4413304709","doi":"https://doi.org/10.1088/2632-2153/adfcb0"},"language":"en","primary_location":{"id":"doi:10.1088/2632-2153/adfcb0","is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/adfcb0","pdf_url":"https://iopscience.iop.org/article/10.1088/2632-2153/adfcb0/pdf","source":{"id":"https://openalex.org/S4210200687","display_name":"Machine Learning Science and Technology","issn_l":"2632-2153","issn":["2632-2153"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320083","host_organization_name":"IOP Publishing","host_organization_lineage":["https://openalex.org/P4310320083","https://openalex.org/P4310311669"],"host_organization_lineage_names":["IOP Publishing","Institute of Physics"],"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: Science and Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://iopscience.iop.org/article/10.1088/2632-2153/adfcb0/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083191806","display_name":"Daniel J. H. Chung","orcid":"https://orcid.org/0000-0003-4399-8504"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Daniel J H Chung","raw_affiliation_strings":["Department of Physics, University of Wisconsin-Madison, Madison, WI, United States of America"],"affiliations":[{"raw_affiliation_string":"Department of Physics, University of Wisconsin-Madison, Madison, WI, United States of America","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119341774","display_name":"Zhiqi Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiqi Gao","raw_affiliation_strings":["Department of Computer Science, University of Wisconsin-Madison, Madison, WI, United States of America"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Wisconsin-Madison, Madison, WI, United States of America","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091968189","display_name":"Yurii Kvasiuk","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yurii Kvasiuk","raw_affiliation_strings":["Department of Physics, University of Wisconsin-Madison, Madison, WI, United States of America"],"affiliations":[{"raw_affiliation_string":"Department of Physics, University of Wisconsin-Madison, Madison, WI, United States of America","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tianyi Li","orcid":"https://orcid.org/0000-0001-9545-8556"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianyi Li","raw_affiliation_strings":["Department of Physics, University of Wisconsin-Madison, Madison, WI, United States of America"],"affiliations":[{"raw_affiliation_string":"Department of Physics, University of Wisconsin-Madison, Madison, WI, United States of America","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003834498","display_name":"Moritz M\u00fcnchmeyer","orcid":"https://orcid.org/0000-0002-3777-7791"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]},{"id":"https://openalex.org/I4210107338","display_name":"Simons Foundation","ror":"https://ror.org/01cmst727","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210107338"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Moritz M\u00fcnchmeyer","raw_affiliation_strings":["Department of Physics, University of Wisconsin-Madison, Madison, WI, United States of America","NSF-Simons AI Institute for the Sky (SkAI), Chicago, IL, United States of America"],"affiliations":[{"raw_affiliation_string":"Department of Physics, University of Wisconsin-Madison, Madison, WI, United States of America","institution_ids":["https://openalex.org/I135310074"]},{"raw_affiliation_string":"NSF-Simons AI Institute for the Sky (SkAI), Chicago, IL, United States of America","institution_ids":["https://openalex.org/I4210107338"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077309439","display_name":"Maja Rudolph","orcid":"https://orcid.org/0009-0007-3739-2203"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maja Rudolph","raw_affiliation_strings":["Data Science Institute (DSI), University of Wisconsin-Madison, Madison, WI, United States of America"],"affiliations":[{"raw_affiliation_string":"Data Science Institute (DSI), University of Wisconsin-Madison, Madison, WI, United States of America","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103088414","display_name":"Fr\u00e9d\u00e9ric Sala","orcid":"https://orcid.org/0000-0003-0379-2827"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Frederic Sala","raw_affiliation_strings":["Department of Computer Science, University of Wisconsin-Madison, Madison, WI, United States of America"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Wisconsin-Madison, Madison, WI, United States of America","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019588882","display_name":"Sai Chaitanya Tadepalli","orcid":"https://orcid.org/0000-0001-9947-4748"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sai Chaitanya Tadepalli","raw_affiliation_strings":["Department of Physics, Indiana University, Bloomington, IN, United States of America"],"affiliations":[{"raw_affiliation_string":"Department of Physics, Indiana University, Bloomington, IN, United States of America","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5083191806"],"corresponding_institution_ids":["https://openalex.org/I135310074"],"apc_list":{"value":1600,"currency":"GBP","value_usd":1962},"apc_paid":{"value":1600,"currency":"GBP","value_usd":1962},"fwci":6.9508,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.96688094,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"6","issue":"3","first_page":"030505","last_page":"030505"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.5857999920845032,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.5857999920845032,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.557200014591217,"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/benchmark","display_name":"Benchmark (surveying)","score":0.6851552724838257},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.4557265341281891},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.06562566757202148},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.055070459842681885}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6851552724838257},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.4557265341281891},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.06562566757202148},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.055070459842681885}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1088/2632-2153/adfcb0","is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/adfcb0","pdf_url":"https://iopscience.iop.org/article/10.1088/2632-2153/adfcb0/pdf","source":{"id":"https://openalex.org/S4210200687","display_name":"Machine Learning Science and Technology","issn_l":"2632-2153","issn":["2632-2153"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320083","host_organization_name":"IOP Publishing","host_organization_lineage":["https://openalex.org/P4310320083","https://openalex.org/P4310311669"],"host_organization_lineage_names":["IOP Publishing","Institute of Physics"],"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: Science and Technology","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:d116f28ce7f34937a0980c3f29ccec51","is_oa":true,"landing_page_url":"https://doaj.org/article/d116f28ce7f34937a0980c3f29ccec51","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Learning: Science and Technology, Vol 6, Iss 3, p 030505 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1088/2632-2153/adfcb0","is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/adfcb0","pdf_url":"https://iopscience.iop.org/article/10.1088/2632-2153/adfcb0/pdf","source":{"id":"https://openalex.org/S4210200687","display_name":"Machine Learning Science and Technology","issn_l":"2632-2153","issn":["2632-2153"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320083","host_organization_name":"IOP Publishing","host_organization_lineage":["https://openalex.org/P4310320083","https://openalex.org/P4310311669"],"host_organization_lineage_names":["IOP Publishing","Institute of Physics"],"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: Science and Technology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1065316766","display_name":null,"funder_award_id":"Award","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G1600972551","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320306555","funder_display_name":"Wisconsin Alumni Research Foundation"},{"id":"https://openalex.org/G2023254112","display_name":null,"funder_award_id":"DE-SC0017647","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G2066175637","display_name":null,"funder_award_id":"DE-SC0017647","funder_id":"https://openalex.org/F4320337511","funder_display_name":"High Energy Physics"},{"id":"https://openalex.org/G2526076495","display_name":null,"funder_award_id":"DE-SC0017647","funder_id":"https://openalex.org/F4320337480","funder_display_name":"Basic Energy Sciences"},{"id":"https://openalex.org/G5153633400","display_name":null,"funder_award_id":"2307109","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8604054382","display_name":"SHF: Medium: Program Synthesis for Weak Supervision","funder_award_id":"2106707","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320306555","display_name":"Wisconsin Alumni Research Foundation","ror":"https://ror.org/00hwxbz16"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320337480","display_name":"Basic Energy Sciences","ror":"https://ror.org/05mg91w61"},{"id":"https://openalex.org/F4320337511","display_name":"High Energy Physics","ror":"https://ror.org/035m6g344"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413304709.pdf","grobid_xml":"https://content.openalex.org/works/W4413304709.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1972563066","https://openalex.org/W1991799006","https://openalex.org/W2050351112","https://openalex.org/W2053387157","https://openalex.org/W2064191127","https://openalex.org/W2081343451","https://openalex.org/W2096798206","https://openalex.org/W2262604762","https://openalex.org/W3004237104","https://openalex.org/W3009578594","https://openalex.org/W4230961355","https://openalex.org/W4313434078","https://openalex.org/W4385571050","https://openalex.org/W4385572162","https://openalex.org/W4388885788","https://openalex.org/W4389519108","https://openalex.org/W4389520747","https://openalex.org/W4401024016","https://openalex.org/W4402671952","https://openalex.org/W4404131920","https://openalex.org/W4408666882"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2935759653","https://openalex.org/W3105167352","https://openalex.org/W54078636","https://openalex.org/W2954470139","https://openalex.org/W1501425562","https://openalex.org/W2902782467","https://openalex.org/W3084825885","https://openalex.org/W2298861036","https://openalex.org/W2271181815"],"abstract_inverted_index":{"Abstract":[0],"We":[1,58,101,140],"introduce":[2],"a":[3],"benchmark":[4,29],"to":[5,11,39,151,165],"evaluate":[6,59],"the":[7,47,90,137,142,166,175,178],"capability":[8],"of":[9,27,31,34,77,104,120,177],"AI":[10,129],"solve":[12],"problems":[13,33,43,97,156],"in":[14,46,86,136],"theoretical":[15],"physics":[16],"(TP),":[17],"focusing":[18],"on":[19,63,174],"high-energy":[20],"theory":[21],"and":[22,66,75,79,106,108,148,157,163,169],"cosmology.":[23],"The":[24,154],"first":[25],"iteration":[26],"our":[28,60,94,125],"consists":[30],"57":[32],"varying":[35],"difficulty,":[36],"from":[37,54],"undergraduate":[38],"research":[40,132],"level.":[41],"These":[42],"are":[44,98,118,172],"novel":[45],"sense":[48],"that":[49,128],"they":[50],"do":[51],"not":[52],"come":[53],"public":[55,155],"problem":[56],"collections.":[57],"data":[61,167],"set":[62,168],"various":[64,161],"open":[65],"closed":[67],"language":[68],"models,":[69,93,162],"including":[70],"o3-mini,":[71],"o1,":[72],"DeepSeek-R1,":[73],"GPT-4o":[74],"versions":[76],"Llama":[78],"Qwen.":[80],"While":[81,113],"we":[82],"find":[83],"impressive":[84],"progress":[85],"model":[87],"performance":[88],"with":[89],"most":[91],"recent":[92],"research-level":[95],"difficulty":[96],"mostly":[99],"unsolved.":[100],"address":[102],"challenges":[103],"auto-verifiability":[105],"grading,":[107],"discuss":[109,141],"common":[110],"failure":[111],"modes.":[112],"currently":[114],"state-of-the":[115],"art":[116],"models":[117],"still":[119],"limited":[121],"use":[122],"for":[123,160],"researchers,":[124],"results":[126,159],"show":[127],"assisted":[130],"TP":[131],"may":[133],"become":[134],"possible":[135,149],"near":[138],"future.":[139],"main":[143],"obstacles":[144],"towards":[145],"this":[146],"goal":[147],"strategies":[150],"overcome":[152],"them.":[153],"solutions,":[158],"updates":[164],"score":[170],"distribution,":[171],"available":[173],"website":[176],"dataset":[179],"tpbench.org":[180],".":[181]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}