{"id":"https://openalex.org/W7171949950","doi":"https://doi.org/10.1145/3793302.3793383","title":"Running Large Language Models at Scale for Mining Software Repositories: Lessons Learned from HPC-Based Batch Inference","display_name":"Running Large Language Models at Scale for Mining Software Repositories: Lessons Learned from HPC-Based Batch Inference","publication_year":2026,"publication_date":"2026-04-13","ids":{"openalex":"https://openalex.org/W7171949950","doi":"https://doi.org/10.1145/3793302.3793383"},"language":null,"primary_location":{"id":"doi:10.1145/3793302.3793383","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3793302.3793383","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 23rd International Conference on Mining Software Repositories","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3793302.3793383","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5095378106","display_name":"Ruoyu Su","orcid":"https://orcid.org/0009-0008-6206-8787"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Ruoyu Su","raw_affiliation_strings":["University of Oulu, Oulu, Finland"],"raw_orcid":"https://orcid.org/0009-0008-6206-8787","affiliations":[{"raw_affiliation_string":"University of Oulu, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065369537","display_name":"Matteo Esposito","orcid":"https://orcid.org/0000-0002-8451-3668"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Matteo Esposito","raw_affiliation_strings":["University of Oulu, Oulu, Finland"],"raw_orcid":"https://orcid.org/0000-0002-8451-3668","affiliations":[{"raw_affiliation_string":"University of Oulu, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086929289","display_name":"Davide Taibi","orcid":"https://orcid.org/0000-0002-3210-3990"},"institutions":[{"id":"https://openalex.org/I177969490","display_name":"University of Southern Denmark","ror":"https://ror.org/03yrrjy16","country_code":"DK","type":"education","lineage":["https://openalex.org/I177969490"]},{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["DK","FI"],"is_corresponding":false,"raw_author_name":"Davide Taibi","raw_affiliation_strings":["University of Southern Denmark, Vejle, Denmark and University of Oulu, Oulu, Finland"],"raw_orcid":"https://orcid.org/0000-0002-3210-3990","affiliations":[{"raw_affiliation_string":"University of Southern Denmark, Vejle, Denmark and University of Oulu, Oulu, Finland","institution_ids":["https://openalex.org/I177969490","https://openalex.org/I98381234"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015576503","display_name":"Valentina Lenarduzzi","orcid":"https://orcid.org/0000-0003-0511-5133"},"institutions":[{"id":"https://openalex.org/I177969490","display_name":"University of Southern Denmark","ror":"https://ror.org/03yrrjy16","country_code":"DK","type":"education","lineage":["https://openalex.org/I177969490"]},{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["DK","FI"],"is_corresponding":false,"raw_author_name":"Valentina Lenarduzzi","raw_affiliation_strings":["University of Southern Denmark, Vejle, Denmark and University of Oulu, Oulu, Finland"],"raw_orcid":"https://orcid.org/0000-0003-0511-5133","affiliations":[{"raw_affiliation_string":"University of Southern Denmark, Vejle, Denmark and University of Oulu, Oulu, Finland","institution_ids":["https://openalex.org/I177969490","https://openalex.org/I98381234"]}]}],"institutions":[],"countries_distinct_count":2,"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":"1036","last_page":"1037"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/commit","display_name":"Commit","score":0.7926999926567078},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5595999956130981},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5103999972343445},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.48649999499320984},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.4178999960422516},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3472000062465668},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.33899998664855957},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.33799999952316284}],"concepts":[{"id":"https://openalex.org/C153180980","wikidata":"https://www.wikidata.org/wiki/Q19776675","display_name":"Commit","level":2,"score":0.7926999926567078},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7754999995231628},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5595999956130981},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5103999972343445},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.48649999499320984},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4422999918460846},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.4178999960422516},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.41110000014305115},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37779998779296875},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3472000062465668},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.33899998664855957},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.33799999952316284},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.321399986743927},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C171981572","wikidata":"https://www.wikidata.org/wiki/Q7554239","display_name":"Software analytics","level":5,"score":0.30140000581741333},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.29019999504089355},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2802000045776367},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2766999900341034},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.26440000534057617},{"id":"https://openalex.org/C135945739","wikidata":"https://www.wikidata.org/wiki/Q1211457","display_name":"Software release life cycle","level":5,"score":0.2587999999523163},{"id":"https://openalex.org/C2984968299","wikidata":"https://www.wikidata.org/wiki/Q1077784","display_name":"Software tool","level":3,"score":0.257099986076355}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3793302.3793383","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3793302.3793383","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 23rd International Conference on Mining Software Repositories","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3793302.3793383","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3793302.3793383","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 23rd International Conference on Mining Software Repositories","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G36806144","display_name":null,"funder_award_id":"6GSoft","funder_id":"https://openalex.org/F4320328501","funder_display_name":"Business Finland"}],"funders":[{"id":"https://openalex.org/F4320328501","display_name":"Business Finland","ror":"https://ror.org/05bgf9v38"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W4386750094","https://openalex.org/W4405846350","https://openalex.org/W4413360246","https://openalex.org/W7082369169","https://openalex.org/W7132835993"],"related_works":[],"abstract_inverted_index":{"The":[0],"rapid":[1],"diffusion":[2],"of":[3,47,59,86,88],"Large":[4],"Language":[5],"Models":[6],"(LLMs)":[7],"is":[8,17],"fundamentally":[9],"changing":[10],"how":[11],"Mining":[12],"Software":[13],"Repositories":[14],"(MSR)":[15],"research":[16],"conducted,":[18],"particularly":[19],"for":[20,77],"studies":[21],"that":[22],"rely":[23,62],"on":[24,63],"unstructured":[25],"textual":[26],"artifacts":[27,89],"such":[28],"as":[29],"commit":[30],"messages,":[31],"issue":[32],"discussions,":[33],"pull":[34],"request":[35],"reviews,":[36],"and":[37,53,97],"practitioner-generated":[38],"content.":[39],"While":[40],"recent":[41],"work":[42],"has":[43],"demonstrated":[44],"the":[45,57],"potential":[46],"LLMs":[48],"to":[49],"support":[50],"classification,":[51],"summarization,":[52],"qualitative":[54],"analysis":[55],"tasks,":[56],"majority":[58],"existing":[60],"approaches":[61],"interactive":[64],"or":[65,84],"API-based":[66],"executions":[67],"[2,":[68],"3,":[69],"6].":[70],"Such":[71],"execution":[72],"models":[73],"are":[74],"poorly":[75],"suited":[76],"large-scale":[78],"empirical":[79],"MSR":[80],"studies,":[81],"where":[82],"thousands":[83,87],"hundreds":[85],"must":[90],"be":[91],"processed":[92],"in":[93],"a":[94],"controlled,":[95],"reproducible,":[96],"cost-aware":[98],"manner.":[99]},"counts_by_year":[],"updated_date":"2026-08-02T14:50:37.381335","created_date":"2026-08-01T00:00:00"}
