{"id":"https://openalex.org/W2161056691","doi":"https://doi.org/10.1109/icdm.2003.1250920","title":"Parsing without a grammar: making sense of unknown file formats","display_name":"Parsing without a grammar: making sense of unknown file formats","publication_year":2004,"publication_date":"2004-03-30","ids":{"openalex":"https://openalex.org/W2161056691","doi":"https://doi.org/10.1109/icdm.2003.1250920","mag":"2161056691"},"language":"en","primary_location":{"id":"doi:10.1109/icdm.2003.1250920","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2003.1250920","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Third IEEE International Conference on Data Mining","raw_type":"proceedings-article"},"type":"article","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/A5080449111","display_name":"Levon Lloyd","orcid":null},"institutions":[{"id":"https://openalex.org/I1327163397","display_name":"State University of New York","ror":"https://ror.org/01q1z8k08","country_code":"US","type":"education","lineage":["https://openalex.org/I1327163397"]},{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"L. Lloyd","raw_affiliation_strings":["Department of Computer Science, State University of New York, Stony Brook, Stony Brook, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, State University of New York, Stony Brook, Stony Brook, NY, USA","institution_ids":["https://openalex.org/I59553526","https://openalex.org/I1327163397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060741187","display_name":"Steven Skiena","orcid":"https://orcid.org/0000-0003-0397-7514"},"institutions":[{"id":"https://openalex.org/I1327163397","display_name":"State University of New York","ror":"https://ror.org/01q1z8k08","country_code":"US","type":"education","lineage":["https://openalex.org/I1327163397"]},{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Skiena","raw_affiliation_strings":["Department of Computer Science, State University of New York, Stony Brook, Stony Brook, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, State University of New York, Stony Brook, Stony Brook, NY, USA","institution_ids":["https://openalex.org/I59553526","https://openalex.org/I1327163397"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1550232,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"195","last_page":"202"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.996999979019165,"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":0.996999979019165,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9930999875068665,"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":0.9872999787330627,"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/computer-science","display_name":"Computer science","score":0.891902506351471},{"id":"https://openalex.org/keywords/bracketing","display_name":"Bracketing (phenomenology)","score":0.7378836870193481},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.7292253375053406},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.452301561832428},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.44848501682281494},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.4386396110057831},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41276153922080994},{"id":"https://openalex.org/keywords/file-format","display_name":"File format","score":0.41036349534988403},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3932405114173889},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33356133103370667},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.0919426679611206},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07199066877365112}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.891902506351471},{"id":"https://openalex.org/C102944935","wikidata":"https://www.wikidata.org/wiki/Q4953701","display_name":"Bracketing (phenomenology)","level":2,"score":0.7378836870193481},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7292253375053406},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.452301561832428},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.44848501682281494},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.4386396110057831},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41276153922080994},{"id":"https://openalex.org/C97250363","wikidata":"https://www.wikidata.org/wiki/Q235557","display_name":"File format","level":2,"score":0.41036349534988403},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3932405114173889},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33356133103370667},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0919426679611206},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07199066877365112},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdm.2003.1250920","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2003.1250920","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Third IEEE International Conference on Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W938539187","https://openalex.org/W1970516708","https://openalex.org/W1971784203","https://openalex.org/W1986861328","https://openalex.org/W1990061958","https://openalex.org/W2029948740","https://openalex.org/W2038670074","https://openalex.org/W2319660501","https://openalex.org/W6660343642"],"related_works":["https://openalex.org/W2121662537","https://openalex.org/W2223582818","https://openalex.org/W4252197189","https://openalex.org/W2777188078","https://openalex.org/W4287391398","https://openalex.org/W3120365279","https://openalex.org/W3134518482","https://openalex.org/W3037567003","https://openalex.org/W2261617724","https://openalex.org/W2006157161"],"abstract_inverted_index":{"The":[0],"thousands":[1],"of":[2,25,40,66],"specialized":[3],"structured":[4],"file":[5,43],"formats":[6],"in":[7],"use":[8],"today":[9],"present":[10],"a":[11,41],"substantial":[12],"barrier":[13],"to":[14],"freely":[15],"exchanging":[16],"information":[17],"between":[18],"applications":[19],"programs.":[20],"We":[21,51],"consider":[22],"the":[23,31,63],"problem":[24],"deducing":[26],"such":[27],"basic":[28,64],"features":[29,65],"as":[30],"whitespace":[32],"characters,":[33],"bracketing":[34],"delimiter":[35],"symbols,":[36],"and":[37],"self-delimiter":[38],"characters":[39],"given":[42],"format":[44],"from":[45],"one":[46],"or":[47],"more":[48],"example":[49,57],"files.":[50],"demonstrate":[52],"that":[53],"for":[54],"sufficiently":[55],"large":[56],"files,":[58],"we":[59],"can":[60],"typically":[61],"identify":[62],"interest.":[67]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}