{"id":"https://openalex.org/W3047598928","doi":"https://doi.org/10.1145/3397537.3397551","title":"Three trillion lines: infrastructure for mining GitHub in the classroom","display_name":"Three trillion lines: infrastructure for mining GitHub in the classroom","publication_year":2020,"publication_date":"2020-03-23","ids":{"openalex":"https://openalex.org/W3047598928","doi":"https://doi.org/10.1145/3397537.3397551","mag":"3047598928"},"language":"en","primary_location":{"id":"doi:10.1145/3397537.3397551","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3397537.3397551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Conference Companion of the 4th International Conference on Art, Science, and Engineering of Programming","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026483529","display_name":"Toni Mattis","orcid":"https://orcid.org/0000-0001-7024-9838"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Toni Mattis","raw_affiliation_strings":["HPI, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HPI, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011714104","display_name":"Patrick Rein","orcid":"https://orcid.org/0000-0001-9454-8381"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patrick Rein","raw_affiliation_strings":["HPI, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HPI, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079160871","display_name":"Robert Hirschfeld","orcid":"https://orcid.org/0000-0002-4249-6003"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Robert Hirschfeld","raw_affiliation_strings":["HPI, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HPI, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2004,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.36835821,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.993399977684021,"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"}},"topics":[{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.993399977684021,"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"}},{"id":"https://openalex.org/T10533","display_name":"Teaching and Learning Programming","score":0.9699000120162964,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11283","display_name":"Experimental Learning in Engineering","score":0.9606999754905701,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6514804363250732},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3267550468444824}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6514804363250732},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3267550468444824}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3397537.3397551","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3397537.3397551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Conference Companion of the 4th International Conference on Art, Science, and Engineering of Programming","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"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":8,"referenced_works":["https://openalex.org/W2125910575","https://openalex.org/W2172147300","https://openalex.org/W2703757306","https://openalex.org/W2778782177","https://openalex.org/W2811027495","https://openalex.org/W3005988334","https://openalex.org/W3089854626","https://openalex.org/W3098636286"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"The":[0,24],"increasing":[1],"interest":[2],"in":[3],"collaborative":[4],"software":[5],"development":[6,22],"on":[7,69],"platforms":[8],"like":[9],"GitHub":[10],"has":[11,27],"led":[12],"to":[13,59,103],"the":[14,39,78],"availability":[15],"of":[16,19,32,44],"large":[17],"amounts":[18],"data":[20,56],"about":[21,46],"activities.":[23],"GHTorrent":[25],"project":[26],"recorded":[28],"a":[29,82],"significant":[30],"proportion":[31],"GitHub\u2019s":[33],"public":[34,42],"event":[35],"stream":[36],"and":[37,61,72,96,99,110],"hosts":[38],"currently":[40],"largest":[41],"dataset":[43],"meta-data":[45,98],"open-source":[47],"development.":[48],"We":[49,80],"describe":[50],"our":[51],"infrastructure":[52],"that":[53,89],"makes":[54],"this":[55,70],"locally":[57],"available":[58],"researchers":[60],"students,":[62],"examples":[63],"for":[64,84,108],"research":[65,109],"activities":[66],"carried":[67],"out":[68],"infrastructure,":[71],"what":[73],"we":[74],"learned":[75],"from":[76],"building":[77],"system.":[79],"identify":[81],"need":[83],"domain-specific":[85],"tools,":[86],"especially":[87],"databases,":[88],"can":[90],"deal":[91],"with":[92],"large-scale":[93],"code":[94],"repositories":[95],"associated":[97],"outline":[100],"open":[101],"challenges":[102],"use":[104],"them":[105],"more":[106],"effectively":[107],"machine":[111],"learning":[112],"settings.":[113]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}