{"id":"https://openalex.org/W4415329545","doi":"https://doi.org/10.48550/arxiv.2505.16135","title":"Sudoku-Bench: Evaluating creative reasoning with Sudoku variants","display_name":"Sudoku-Bench: Evaluating creative reasoning with Sudoku variants","publication_year":2025,"publication_date":"2025-05-22","ids":{"openalex":"https://openalex.org/W4415329545","doi":"https://doi.org/10.48550/arxiv.2505.16135"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.16135","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.16135","pdf_url":"https://arxiv.org/pdf/2505.16135","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/2505.16135","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066963182","display_name":"Jeffrey Seely","orcid":"https://orcid.org/0000-0002-4242-8422","observed_orcids":["https://orcid.org/0000-0002-4242-8422"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seely, Jeffrey","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114424089","display_name":"Yuki Imajuku","orcid":"https://orcid.org/0009-0005-7470-8305","observed_orcids":["https://orcid.org/0009-0005-7470-8305"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Imajuku, Yuki","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076757483","display_name":"Tianyu Zhao","orcid":"https://orcid.org/0009-0006-2833-264X","observed_orcids":["https://orcid.org/0009-0006-2833-264X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Tianyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005809555","display_name":"Edoardo Cetin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cetin, Edoardo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5023448834","display_name":"Llion Jones","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jones, Llion","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.415800005197525,"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":0.415800005197525,"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/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.18140000104904175,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.12729999423027039,"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/sudoku","display_name":"Sudoku","score":0.6460000276565552},{"id":"https://openalex.org/keywords/reasoning-benchmarks","display_name":"reasoning benchmarks","score":0.6940000057220459},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8180000185966492},{"id":"https://openalex.org/keywords/creative-reasoning","display_name":"creative reasoning","score":0.9520000219345093},{"id":"https://openalex.org/keywords/memorization","display_name":"memorization","score":0.5950000286102295},{"id":"https://openalex.org/keywords/strategic-reasoning","display_name":"strategic reasoning","score":0.46799999475479126}],"concepts":[{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.7437000274658203},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.661899983882904},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6067000031471252},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5787000060081482},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5619999766349792},{"id":"https://openalex.org/C43971567","wikidata":"https://www.wikidata.org/wiki/Q3142865","display_name":"Logical reasoning","level":2,"score":0.3926999866962433},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.3824000060558319},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32350000739097595},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.30329999327659607},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2964000105857849},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C21847791","wikidata":"https://www.wikidata.org/wiki/Q191081","display_name":"Logical conjunction","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C2985612853","wikidata":"https://www.wikidata.org/wiki/Q185816","display_name":"Analogical reasoning","level":3,"score":0.28029999136924744},{"id":"https://openalex.org/C2776542307","wikidata":"https://www.wikidata.org/wiki/Q16912820","display_name":"Parenthesis","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C134752490","wikidata":"https://www.wikidata.org/wiki/Q374182","display_name":"Logical consequence","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.26249998807907104},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2583000063896179}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2505.16135","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.16135","pdf_url":"https://arxiv.org/pdf/2505.16135","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.2505.16135","doi":"https://doi.org/10.48550/arxiv.2505.16135","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.16135","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:2505.16135","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.16135","pdf_url":"https://arxiv.org/pdf/2505.16135","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":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415329545.pdf","grobid_xml":"https://content.openalex.org/works/W4415329545.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4414587542","https://openalex.org/W7140141301","https://openalex.org/W4414845990","https://openalex.org/W4401041990","https://openalex.org/W4416030423","https://openalex.org/W4415024510","https://openalex.org/W7108447852","https://openalex.org/W7133343188","https://openalex.org/W7165245162","https://openalex.org/W7160559924"],"abstract_inverted_index":{"Existing":[0],"reasoning":[1,52,143],"benchmarks":[2],"for":[3,51],"large":[4],"language":[5],"models":[6],"(LLMs)":[7],"frequently":[8],"fail":[9],"to":[10,38,68,116,139],"capture":[11],"authentic":[12],"creativity,":[13],"often":[14],"rewarding":[15],"memorization":[16,63],"of":[17,30,108,133],"previously":[18],"observed":[19],"patterns.":[20],"We":[21],"address":[22],"this":[23],"shortcoming":[24],"with":[25,106],"Sudoku-Bench,":[26],"a":[27,80,92,97,119],"curated":[28],"benchmark":[29],"challenging":[31],"and":[32,65,82,87,102],"unconventional":[33],"Sudoku":[34,44,77],"variants":[35,45,78],"specifically":[36],"selected":[37],"evaluate":[39],"creative,":[40],"multi-step":[41],"logical":[42,71],"reasoning.":[43],"form":[46],"an":[47],"unusually":[48],"effective":[49],"domain":[50],"research:":[53],"each":[54],"puzzle":[55,95,100],"introduces":[56],"unique":[57],"or":[58],"subtly":[59],"interacting":[60],"constraints,":[61],"making":[62,113],"infeasible":[64],"requiring":[66],"solvers":[67],"identify":[69],"novel":[70],"breakthroughs":[72],"(``break-ins'').":[73],"Despite":[74],"their":[75],"diversity,":[76],"maintain":[79],"common":[81],"compact":[83],"structure,":[84],"enabling":[85],"clear":[86],"consistent":[88],"evaluation.":[89],"Sudoku-Bench":[90],"includes":[91],"carefully":[93],"chosen":[94],"set,":[96],"standardized":[98],"text-based":[99],"representation,":[101],"flexible":[103],"tools":[104],"compatible":[105],"thousands":[107],"publicly":[109],"available":[110],"puzzles":[111,134],"--":[112],"it":[114],"easy":[115],"extend":[117],"into":[118],"general":[120],"research":[121],"environment.":[122],"Baseline":[123],"experiments":[124],"show":[125],"that":[126],"state-of-the-art":[127],"LLMs":[128],"solve":[129],"fewer":[130],"than":[131],"15\\%":[132],"unaided,":[135],"highlighting":[136],"significant":[137],"opportunities":[138],"advance":[140],"long-horizon,":[141],"strategic":[142],"capabilities.":[144]},"counts_by_year":[],"updated_date":"2026-09-29T14:09:16.559479","created_date":"2025-10-19T00:00:00"}