{"id":"https://openalex.org/W7104554792","doi":"https://doi.org/10.21227/k8q7-kt20","title":"\"BouncerBench\"","display_name":"\"BouncerBench\"","publication_year":2025,"publication_date":"2025-11-09","ids":{"openalex":"https://openalex.org/W7104554792","doi":"https://doi.org/10.21227/k8q7-kt20"},"language":null,"primary_location":{"id":"doi:10.21227/k8q7-kt20","is_oa":true,"landing_page_url":"https://doi.org/10.21227/k8q7-kt20","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.21227/k8q7-kt20","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Noble Saji Mathews","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Noble Saji Mathews","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Meiyappan Nagappan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meiyappan Nagappan","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":false,"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":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.524399995803833},{"id":"https://openalex.org/keywords/ticket","display_name":"Ticket","score":0.5087000131607056},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4309999942779541},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.367900013923645},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.33570000529289246}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5927000045776367},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.524399995803833},{"id":"https://openalex.org/C2776540713","wikidata":"https://www.wikidata.org/wiki/Q7800647","display_name":"Ticket","level":2,"score":0.5087000131607056},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4309999942779541},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4020000100135803},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.367900013923645},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.33570000529289246},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3343999981880188},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3190999925136566},{"id":"https://openalex.org/C153180980","wikidata":"https://www.wikidata.org/wiki/Q19776675","display_name":"Commit","level":2,"score":0.296099990606308}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21227/k8q7-kt20","is_oa":true,"landing_page_url":"https://doi.org/10.21227/k8q7-kt20","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.21227/k8q7-kt20","is_oa":true,"landing_page_url":"https://doi.org/10.21227/k8q7-kt20","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Dataset"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"\"BouncerBench":[0],"is":[1],"a":[2,22,47],"benchmark":[3],"for":[4],"evaluating":[5],"the":[6,35],"ability":[7],"of":[8,37,49],"Large":[9],"Language":[10],"Models":[11],"(LLMs)":[12],"to":[13,34,55],"abstain":[14],"when":[15,21],"presented":[16],"with":[17],"ambiguous":[18],"tasks":[19],"or":[20],"sufficiently":[23],"accurate":[24],"response":[25],"cannot":[26],"be":[27,53],"provided.":[28],"Trust":[29],"and":[30,44],"reliability":[31],"are":[32],"critical":[33],"success":[36],"AI":[38],"agents":[39],"in":[40],"software":[41],"engineering":[42],"tasks,":[43],"BouncerBench":[45],"introduces":[46],"notion":[48],"\\\"bouncers\\\"":[50],"that":[51],"could":[52],"applied":[54],"any":[56],"autonomous":[57],"ticket":[58],"resolution":[59],"system.\"":[60]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-11-10T00:00:00"}
