{"id":"https://openalex.org/W1982280055","doi":"https://doi.org/10.1145/1328438.1328488","title":"From dirt to shovels","display_name":"From dirt to shovels","publication_year":2008,"publication_date":"2008-01-07","ids":{"openalex":"https://openalex.org/W1982280055","doi":"https://doi.org/10.1145/1328438.1328488","mag":"1982280055"},"language":"en","primary_location":{"id":"doi:10.1145/1328438.1328488","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1328438.1328488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 35th annual ACM SIGPLAN-SIGACT symposium on Principles of programming languages","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/A5056099984","display_name":"Kathleen Fisher","orcid":"https://orcid.org/0000-0001-5249-2615"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kathleen Fisher","raw_affiliation_strings":["AT&T Labs Research, San Jose, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT&T Labs Research, San Jose, CA","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049454219","display_name":"David Walker","orcid":"https://orcid.org/0000-0003-3681-149X"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Walker","raw_affiliation_strings":["Princeton University, Princeton, NJ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University, Princeton, NJ","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101906756","display_name":"Kenny Q. Zhu","orcid":"https://orcid.org/0000-0003-3782-3230"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kenny Q. Zhu","raw_affiliation_strings":["Princeton University, Princeton, NJ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University, Princeton, NJ","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101817826","display_name":"Peter S. White","orcid":"https://orcid.org/0000-0003-0313-033X"},"institutions":[{"id":"https://openalex.org/I4210140281","display_name":"Galois (United States)","ror":"https://ror.org/03g8y8161","country_code":"US","type":"company","lineage":["https://openalex.org/I4210140281"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter White","raw_affiliation_strings":["Galois: Inc., Beaverton, OR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Galois: Inc., Beaverton, OR","institution_ids":["https://openalex.org/I4210140281"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.8754,"has_fulltext":false,"cited_by_count":85,"citation_normalized_percentile":{"value":0.98497667,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"421","last_page":"434"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9980999827384949,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9980999827384949,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9976000189781189,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9940999746322632,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/dirt","display_name":"Dirt","score":0.7900975942611694},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4416337311267853},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.18611326813697815},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.0726778507232666}],"concepts":[{"id":"https://openalex.org/C2778582501","wikidata":"https://www.wikidata.org/wiki/Q555882","display_name":"Dirt","level":2,"score":0.7900975942611694},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4416337311267853},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.18611326813697815},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0726778507232666}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1328438.1328488","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1328438.1328488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 35th annual ACM SIGPLAN-SIGACT symposium on Principles of programming languages","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W5832829","https://openalex.org/W11658723","https://openalex.org/W140384553","https://openalex.org/W1503682011","https://openalex.org/W1510758414","https://openalex.org/W1511974523","https://openalex.org/W1553019137","https://openalex.org/W1575798196","https://openalex.org/W1586689013","https://openalex.org/W1602991328","https://openalex.org/W1969005071","https://openalex.org/W1990751139","https://openalex.org/W2029873015","https://openalex.org/W2034797903","https://openalex.org/W2042541403","https://openalex.org/W2092386826","https://openalex.org/W2095745830","https://openalex.org/W2096496923","https://openalex.org/W2096679454","https://openalex.org/W2101460669","https://openalex.org/W2101672116","https://openalex.org/W2104086170","https://openalex.org/W2106895292","https://openalex.org/W2109486375","https://openalex.org/W2111251067","https://openalex.org/W2116493296","https://openalex.org/W2123229843","https://openalex.org/W2132843347","https://openalex.org/W2134164043","https://openalex.org/W2146950091","https://openalex.org/W2150721933","https://openalex.org/W2162340487","https://openalex.org/W2166549982","https://openalex.org/W2169131377","https://openalex.org/W2172549414","https://openalex.org/W4246839229","https://openalex.org/W4248513939","https://openalex.org/W6633154970"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2057213227","https://openalex.org/W2483334712","https://openalex.org/W2352212546","https://openalex.org/W195039303","https://openalex.org/W2157479968","https://openalex.org/W2036897369","https://openalex.org/W2382531111","https://openalex.org/W2381195684"],"abstract_inverted_index":{"An":[0],"ad":[1,81,107],"hoc":[2,82,108],"data":[3,8,13,23,60,75,83,109,119,127,189],"source":[4,9,110],"is":[5,52,96],"any":[6,86],"semistructured":[7],"for":[10,140,164],"which":[11],"useful":[12,59],"analysis":[14,128,165],"and":[15,28,37,74,111,137,166],"transformation":[16],"tools":[17,129],"are":[18],"not":[19],"readily":[20],"available.":[21],"Such":[22],"must":[24],"be":[25],"queried,":[26],"transformed":[27],"displayed":[29],"by":[30,207],"systems":[31],"administrators,":[32],"computational":[33],"biologists,":[34],"financial":[35],"analysts":[36],"hosts":[38],"of":[39,58,93,105,176,186,214,227],"others":[40],"on":[41],"a":[42,56,64,71,97,113,205],"regular":[43],"basis.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48],"demonstrate":[49],"that":[50,100,218],"it":[51,181,201],"possible":[53],"to":[54,124,134,196,203],"generate":[55,135],"suite":[57],"processing":[61],"tools,":[62],"including":[63],"semi-structured":[65],"query":[66],"engine,":[67],"several":[68],"format":[69,114],"converters,":[70],"statistical":[72],"analyzer":[73],"visualization":[76],"routines":[77],"directly":[78],"from":[79],"the":[80,94,103,117,141,152,174,184,187,197,212,215],"itself,":[84],"without":[85],"human":[87],"intervention.":[88],"The":[89],"key":[90],"technical":[91],"contribution":[92],"work":[95],"multi-phase":[98],"algorithm":[99],"automatically":[101],"infers":[102],"structure":[104],"an":[106],"produces":[112],"specification":[115],"in":[116,192],"PADS":[118,153],"description":[120,206],"language.":[121],"Programmers":[122],"wishing":[123],"implement":[125],"custom":[126],"can":[130],"use":[131],"such":[132],"descriptions":[133,150,221],"printing":[136],"parsing":[138],"libraries":[139],"data.":[142,229],"Alternatively,":[143],"our":[144,177],"software":[145],"infrastructure":[146],"will":[147],"push":[148],"these":[149],"through":[151],"compiler,":[154],"creating":[155],"format-dependent":[156],"modules":[157],"that,":[158],"when":[159],"linked":[160],"with":[161],"format-independent":[162],"algorithms":[163],"transformation,":[167],"result":[168],"infully":[169],"functional":[170],"tools.":[171],"We":[172,209],"evaluate":[173,211],"performance":[175],"inference":[178],"algorithm,":[179,216],"showing":[180],"scales":[182],"linearlyin":[183],"size":[185],"training":[188],"-":[190],"completing":[191],"seconds,":[193],"as":[194],"opposed":[195],"hours":[198],"or":[199],"days":[200],"takes":[202],"write":[204],"hand.":[208],"also":[210],"correctness":[213],"demonstrating":[217],"generating":[219],"accurate":[220],"often":[222],"requires":[223],"less":[224],"than":[225],"5%":[226],"theavailable":[228]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}