{"id":"https://openalex.org/W7166804902","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1669","title":"PuzzleClone: A DSL-Powered Framework for Synthesizing Verifiable Data","display_name":"PuzzleClone: A DSL-Powered Framework for Synthesizing Verifiable Data","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166804902","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1669"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1669","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1669","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1669","pdf_url":"https://aclanthology.org/2026.findings-acl.1669.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.findings-acl.1669.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139822121","display_name":"Kai Xiong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Xiong","raw_affiliation_strings":["HiThink Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HiThink Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130422970","display_name":"Yanwei Huang","orcid":"https://orcid.org/0009-0001-9453-7815","observed_orcids":["https://orcid.org/0009-0001-9453-7815"]},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yanwei Huang","raw_affiliation_strings":["HKUST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKUST","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034543604","display_name":"Rongjunchen Zhang","orcid":"https://orcid.org/0000-0003-1823-2726","observed_orcids":["https://orcid.org/0000-0003-1823-2726"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rongjunchen Zhang","raw_affiliation_strings":["HiThink Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HiThink Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139744078","display_name":"Kun Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kun Chen","raw_affiliation_strings":["HiThink Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HiThink Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071627107","display_name":"Haipang Wu","orcid":"https://orcid.org/0009-0000-0386-8479","observed_orcids":["https://orcid.org/0009-0000-0386-8479"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haipang WU","raw_affiliation_strings":["HiThink Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HiThink Research","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073986937","display_name":"Yingcai Wu","orcid":"https://orcid.org/0000-0002-1119-3237","observed_orcids":["https://orcid.org/0000-0002-1119-3237"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingcai Wu","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.43891859,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"33378","last_page":"33404"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5810999870300293,"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":0.5810999870300293,"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":0.1356000006198883,"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":0.05209999904036522,"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/domain-specific-languages","display_name":"domain-specific languages","score":0.7009999752044678},{"id":"https://openalex.org/keywords/puzzle-generation","display_name":"puzzle generation","score":0.6100000143051147},{"id":"https://openalex.org/keywords/logical-specifications","display_name":"logical specifications","score":0.40299999713897705},{"id":"https://openalex.org/keywords/llm-training-data","display_name":"LLM training data","score":0.48100000619888306},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.5960000157356262},{"id":"https://openalex.org/keywords/logic-puzzles","display_name":"logic puzzles","score":0.5809999704360962},{"id":"https://openalex.org/keywords/data-augmentation","display_name":"data augmentation","score":0.5249999761581421},{"id":"https://openalex.org/keywords/post-training-fine-tuning","display_name":"post-training fine-tuning","score":0.7289999723434448}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6532999873161316},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.4553999900817871},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.25119999051094055},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.24959999322891235},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.24570000171661377},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.24490000307559967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1669","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1669","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1669","pdf_url":"https://aclanthology.org/2026.findings-acl.1669.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1669","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1669","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1669","pdf_url":"https://aclanthology.org/2026.findings-acl.1669.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166804902.pdf","grobid_xml":"https://content.openalex.org/works/W7166804902.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4414587542","https://openalex.org/W4416017259","https://openalex.org/W7140132769","https://openalex.org/W4404990680","https://openalex.org/W4414845990","https://openalex.org/W4392222438","https://openalex.org/W7223100088","https://openalex.org/W4412944614","https://openalex.org/W4414698783","https://openalex.org/W4412945228"],"abstract_inverted_index":{"High-quality":[0],"mathematical":[1,148,168],"and":[2,40,82,85,103,115,130,147,160,167,182],"logical":[3,73],"datasets":[4,33],"with":[5],"verifiable":[6,53],"answers":[7],"are":[8,184],"essential":[9],"for":[10,51],"strengthening":[11],"the":[12,26,140],"reasoning":[13],"capabilities":[14],"of":[15,28,113],"large":[16],"language":[17],"models":[18],"(LLMs).While":[19],"recent":[20],"data":[21,54,183],"augmentation":[22],"techniques":[23],"have":[24],"facilitated":[25],"creation":[27],"large-scale":[29],"benchmarks,":[30],"existing":[31],"LLM-generated":[32],"often":[34],"suffer":[35],"from":[36,156,177],"limited":[37],"reliability,":[38],"diversity,":[39],"scalability.To":[41],"address":[42],"these":[43],"challenges,":[44],"we":[45,94],"introduce":[46],"Puz-zleClone,":[47],"a":[48,58,90,97,110],"formal":[49],"framework":[50],"synthesizing":[52],"at":[55,186],"scale":[56],"using":[57],"novel":[59],"DSLdriven":[60],"approach.Our":[61],"approach":[62],"features":[63],"three":[64],"key":[65],"innovations:":[66],"(1)":[67],"encoding":[68],"seed":[69],"puzzles":[70,108],"into":[71],"structured":[72],"specifications,":[74],"(2)":[75],"generating":[76],"scalable":[77],"variants":[78],"through":[79],"systematic":[80],"variable":[81],"constraint":[83],"randomization,":[84],"(3)":[86],"ensuring":[87],"validity":[88],"via":[89],"reproduction":[91],"mechanism.Applying":[92],"PuzzleClone,":[93],"construct":[95],"PC-83K,":[96],"benchmark":[98],"comprising":[99],"over":[100],"83K":[101],"diverse":[102],"programmatically":[104],"validated":[105],"puzzles.The":[106],"generated":[107],"span":[109],"wide":[111],"spectrum":[112],"difficulty":[114],"formats,":[116],"posing":[117],"significant":[118],"challenges":[119],"to":[120,158,171,179],"current":[121],"state-of-the-art":[122],"models.Experimental":[123],"results":[124],"show":[125],"that":[126],"post":[127],"training":[128,150],"(SFT":[129],"RL)":[131],"on":[132,139,144,154],"PC-83K":[133,155],"yields":[134],"substantial":[135],"improvements":[136,163],"not":[137],"only":[138],"testset":[141],"but":[142],"also":[143],"various":[145],"logic":[146,166],"benchmarks.Post":[149],"raises":[151],"average":[152],"performance":[153],"14.5":[157],"66.0":[159],"delivers":[161],"consistent":[162],"across":[164],"7":[165],"benchmarks":[169],"up":[170],"18.4":[172],"absolute":[173],"percentage":[174],"points":[175],"(SATBench":[176],"51.6":[178],"70.0).Our":[180],"code":[181],"available":[185],"https://github.com/":[187],"HiThink-Research/PuzzleClone.":[188]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-07-02T00:00:00"}