{"id":"https://openalex.org/W7125980535","doi":"https://doi.org/10.1145/3793655.3793709","title":"Tricky\u00b2: Towards a Benchmark for Evaluating Human and LLM Error Interactions","display_name":"Tricky\u00b2: Towards a Benchmark for Evaluating Human and LLM Error Interactions","publication_year":2026,"publication_date":"2026-04-12","ids":{"openalex":"https://openalex.org/W7125980535","doi":"https://doi.org/10.1145/3793655.3793709"},"language":null,"primary_location":{"id":"doi:10.1145/3793655.3793709","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3793655.3793709","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 IEEE/ACM Third International Conference on AI Foundation Models and Software Engineering","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3793655.3793709","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023662155","display_name":"Cole G. Granger","orcid":null},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]},{"id":"https://openalex.org/I267592682","display_name":"Williams (United States)","ror":"https://ror.org/007zhvp17","country_code":"US","type":"company","lineage":["https://openalex.org/I267592682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cole Granger","raw_affiliation_strings":["William & Mary, Williamsburg, USA"],"raw_orcid":"https://orcid.org/0009-0002-6787-8101","affiliations":[{"raw_affiliation_string":"William & Mary, Williamsburg, USA","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124094640","display_name":"Dipin Khati","orcid":null},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]},{"id":"https://openalex.org/I267592682","display_name":"Williams (United States)","ror":"https://ror.org/007zhvp17","country_code":"US","type":"company","lineage":["https://openalex.org/I267592682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dipin Khati","raw_affiliation_strings":["William & Mary, Williamsburg, USA"],"raw_orcid":"https://orcid.org/0009-0008-4489-7733","affiliations":[{"raw_affiliation_string":"William & Mary, Williamsburg, USA","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124110816","display_name":"Daniel Rodriguez-Cardenas","orcid":null},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]},{"id":"https://openalex.org/I267592682","display_name":"Williams (United States)","ror":"https://ror.org/007zhvp17","country_code":"US","type":"company","lineage":["https://openalex.org/I267592682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Rodriguez-Cardenas","raw_affiliation_strings":["William & Mary, Williamsburg, USA"],"raw_orcid":"https://orcid.org/0000-0002-3238-1229","affiliations":[{"raw_affiliation_string":"William & Mary, Williamsburg, USA","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124104332","display_name":"Denys Poshyvanyk","orcid":null},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]},{"id":"https://openalex.org/I267592682","display_name":"Williams (United States)","ror":"https://ror.org/007zhvp17","country_code":"US","type":"company","lineage":["https://openalex.org/I267592682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Denys Poshyvanyk","raw_affiliation_strings":["William & Mary, Williamsburg, USA"],"raw_orcid":"https://orcid.org/0000-0002-5626-7586","affiliations":[{"raw_affiliation_string":"William & Mary, Williamsburg, USA","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"249","last_page":"253"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.6055999994277954,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10260","display_name":"Software Engineering Research","score":0.6055999994277954,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11986","display_name":"Scientific Computing and Data Management","score":0.05620000138878822,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.052299998700618744,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/pipeline","display_name":"Pipeline (software)","score":0.6546000242233276},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6126999855041504},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5673999786376953},{"id":"https://openalex.org/keywords/human-error","display_name":"Human error","score":0.5156000256538391},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4767000079154968},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.4422999918460846},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.4366999864578247},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.42829999327659607}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7595000267028809},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6546000242233276},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6126999855041504},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5673999786376953},{"id":"https://openalex.org/C169806903","wikidata":"https://www.wikidata.org/wiki/Q5937752","display_name":"Human error","level":2,"score":0.5156000256538391},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4767000079154968},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.4422999918460846},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.4366999864578247},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.42829999327659607},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4099000096321106},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.399399995803833},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3910999894142151},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38999998569488525},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.38909998536109924},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.38109999895095825},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.3504999876022339},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3310000002384186},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3179999887943268},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.30219998955726624},{"id":"https://openalex.org/C191147762","wikidata":"https://www.wikidata.org/wiki/Q186289","display_name":"Human reliability","level":3,"score":0.2856999933719635},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.2711000144481659},{"id":"https://openalex.org/C82214349","wikidata":"https://www.wikidata.org/wiki/Q657339","display_name":"Software metric","level":5,"score":0.26350000500679016}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3793655.3793709","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3793655.3793709","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 IEEE/ACM Third International Conference on AI Foundation Models and Software Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2601.18949","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.18949","pdf_url":"https://arxiv.org/pdf/2601.18949","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3793655.3793709","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3793655.3793709","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 IEEE/ACM Third International Conference on AI Foundation Models and Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4772491753101349,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"are":[4],"increasingly":[5],"integrated":[6],"into":[7],"software":[8],"development":[9],"workflows,":[10],"yet":[11],"they":[12],"often":[13],"introduce":[14],"subtle":[15],"logic":[16],"or":[17],"data-misuse":[18],"errors":[19,50],"that":[20,39],"differ":[21],"from":[22],"human":[23,77],"bugs.":[24],"To":[25],"study":[26],"how":[27],"these":[28],"two":[29],"error":[30,95],"types":[31],"interact,":[32],"we":[33],"construct":[34],"Tricky2,":[35],"a":[36,66],"hybrid":[37,103],"dataset":[38,110],"augments":[40],"the":[41,109],"existing":[42],"TrickyBugs":[43],"[14]":[44],"corpus":[45,84],"of":[46,93,121],"human-written":[47],"defects":[48,78],"with":[49],"injected":[51],"by":[52],"both":[53],"GPT-5":[54],"and":[55,60,79,88,100,113,124],"OpenAI-oss-20b":[56],"across":[57],"C++,":[58],"Python,":[59],"Java":[61],"programs.":[62],"Our":[63],"approach":[64],"uses":[65],"taxonomy-guided":[67],"prompting":[68],"framework":[69],"to":[70],"generate":[71],"machine-originated":[72],"bugs":[73],"while":[74],"preserving":[75],"original":[76],"program":[80],"structure.":[81],"The":[82],"resulting":[83],"spans":[85],"human-only,":[86],"LLM-only,":[87],"human+LLM":[89],"splits,":[90],"enabling":[91],"analysis":[92],"mixed-origin":[94],"behavior,":[96],"multi-bug":[97],"repair":[98,125],"robustness,":[99],"reliability":[101],"in":[102],"human\u2013machine":[104],"code.":[105],"This":[106],"paper":[107],"outlines":[108],"construction":[111],"pipeline":[112],"illustrates":[114],"its":[115],"use":[116],"through":[117],"small-scale":[118],"baseline":[119],"evaluations":[120],"classification,":[122],"localization,":[123],"tasks.":[126]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-01-29T00:00:00"}