{"id":"https://openalex.org/W4402954703","doi":"https://doi.org/10.48550/arxiv.2409.01374","title":"H-ARC: A Robust Estimate of Human Performance on the Abstraction and Reasoning Corpus Benchmark","display_name":"H-ARC: A Robust Estimate of Human Performance on the Abstraction and Reasoning Corpus Benchmark","publication_year":2024,"publication_date":"2024-09-02","ids":{"openalex":"https://openalex.org/W4402954703","doi":"https://doi.org/10.48550/arxiv.2409.01374"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2409.01374","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.01374","pdf_url":"https://arxiv.org/pdf/2409.01374","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":"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/2409.01374","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107628756","display_name":"Solim LeGris","orcid":"https://orcid.org/0009-0003-2334-7234","observed_orcids":["https://orcid.org/0009-0003-2334-7234"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"LeGris, Solim","raw_affiliation_strings":["Department of Psychology ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Psychology ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008629284","display_name":"Wai Keen Vong","orcid":"https://orcid.org/0000-0002-1982-9156","observed_orcids":["https://orcid.org/0000-0002-1982-9156"]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vong, Wai Keen","raw_affiliation_strings":["Center for Data Science New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Data Science New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011713946","display_name":"Brenden M. Lake","orcid":"https://orcid.org/0000-0001-8959-3401","observed_orcids":["https://orcid.org/0000-0001-8959-3401"]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lake, Brenden M.","raw_affiliation_strings":["Center for Data Science New York University","Department of Psychology ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Data Science New York University","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"Department of Psychology ,","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083572203","display_name":"Todd Matthew Gureckis","orcid":"https://orcid.org/0000-0002-7139-4778","observed_orcids":["https://orcid.org/0000-0002-7139-4778"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gureckis, Todd M.","raw_affiliation_strings":["Department of Psychology ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Psychology ,","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.3330000042915344,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.3330000042915344,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.2838999927043915,"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/T10533","display_name":"Teaching and Learning Programming","score":0.13429999351501465,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/abstraction-and-reasoning-corpus","display_name":"Abstraction and Reasoning Corpus","score":0.9980000257492065},{"id":"https://openalex.org/keywords/out-of-distribution-generalization","display_name":"out-of-distribution generalization","score":0.9399999976158142},{"id":"https://openalex.org/keywords/benchmark-validity","display_name":"benchmark validity","score":0.7080000042915344},{"id":"https://openalex.org/keywords/human-machine-comparison","display_name":"human-machine comparison","score":0.5400000214576721}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8329676389694214},{"id":"https://openalex.org/C83415579","wikidata":"https://www.wikidata.org/wiki/Q161973","display_name":"Arc (geometry)","level":2,"score":0.6973615884780884},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.6949768662452698},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4940929710865021},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47635555267333984},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22762003540992737},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.14001402258872986},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.116814523935318},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.07235318422317505},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.06775990128517151},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.06517532467842102}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2409.01374","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.01374","pdf_url":"https://arxiv.org/pdf/2409.01374","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2409.01374","doi":"https://doi.org/10.48550/arxiv.2409.01374","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2409.01374","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:2409.01374","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.01374","pdf_url":"https://arxiv.org/pdf/2409.01374","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2223787628","display_name":"Collaborative Research: CompCog: Adversarial Collaborative Research on Intuitive Physical Reasoning","funder_award_id":"2121102","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"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402954703.pdf","grobid_xml":"https://content.openalex.org/works/W4402954703.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4413038790","https://openalex.org/W6949241801","https://openalex.org/W7130741265","https://openalex.org/W7131846630","https://openalex.org/W6893397666","https://openalex.org/W7138142412","https://openalex.org/W4416359063","https://openalex.org/W4417307492","https://openalex.org/W6922855675","https://openalex.org/W7214234379"],"abstract_inverted_index":{"The":[0],"Abstraction":[1],"and":[2,20,39,83,116,135,149,152,250],"Reasoning":[3],"Corpus":[4],"(ARC)":[5],"is":[6,42],"a":[7,70,87,98,139,156],"visual":[8],"program":[9],"synthesis":[10],"benchmark":[11],"designed":[12],"to":[13],"test":[14],"challenging":[15],"out-of-distribution":[16],"generalization":[17],"in":[18,185,200],"humans":[19,56,108],"machines.":[21],"Since":[22],"2019,":[23],"limited":[24],"progress":[25],"has":[26],"been":[27],"observed":[28],"on":[29,109,145,162,234],"the":[30,45,48,61,75,110,121,146,163,175,190,194,208,248],"challenge":[31],"using":[32,68],"existing":[33],"artificial":[34],"intelligence":[35],"methods.":[36],"Comparing":[37],"human":[38,91,103,130,220,254],"machine":[40],"performance":[41,104,131,221],"important":[43],"for":[44,228],"validity":[46],"of":[47,72,81,90,102,113,143,160,174,193,247],"benchmark.":[49],"While":[50],"previous":[51],"work":[52],"explored":[53],"how":[54],"well":[55],"can":[57],"solve":[58],"tasks":[59,73,119,177,198],"from":[60,74,79,120,253],"ARC":[62,123,197],"benchmark,":[63],"they":[64],"either":[65],"did":[66],"so":[67],"only":[69,85],"subset":[71],"original":[76,122],"dataset,":[77,240],"or":[78],"variants":[80],"ARC,":[82,235],"therefore":[84],"provided":[86],"tentative":[88],"estimate":[89,101,127],"performance.":[92],"In":[93],"this":[94],"work,":[95],"we":[96,168,236],"obtain":[97],"more":[99],"robust":[100],"by":[105,180,203],"evaluating":[106],"1729":[107],"full":[111],"set":[112],"400":[114,117],"training":[115,147],"evaluation":[118,165],"problem":[124],"set.":[125,166],"We":[126],"that":[128,171,189],"average":[129,142,159],"lies":[132],"between":[133,150],"73.3%":[134],"77.2%":[136],"correct":[137,154],"with":[138,155],"reported":[140,157],"empirical":[141,158],"76.2%":[144],"set,":[148],"55.9%":[151],"68.9%":[153],"64.2%":[161],"public":[164],"However,":[167],"also":[169],"find":[170],"790":[172],"out":[173],"800":[176],"were":[178],"solvable":[179,202],"at":[181],"least":[182],"one":[183],"person":[184],"three":[186],"attempts,":[187],"suggesting":[188],"vast":[191],"majority":[192],"publicly":[195,237],"available":[196],"are":[199,214],"principle":[201],"typical":[204],"crowd-workers":[205],"recruited":[206],"over":[207],"internet.":[209],"Notably,":[210],"while":[211],"these":[212],"numbers":[213],"slightly":[215],"lower":[216],"than":[217],"earlier":[218],"estimates,":[219],"still":[222],"greatly":[223],"exceeds":[224],"current":[225],"state-of-the-art":[226],"approaches":[227],"solving":[229],"ARC.":[230],"To":[231],"facilitate":[232],"research":[233],"release":[238],"our":[239],"called":[241],"H-ARC":[242],"(human-ARC),":[243],"which":[244],"includes":[245],"all":[246],"submissions":[249],"action":[251],"traces":[252],"participants.":[255]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2024-09-29T00:00:00"}