{"id":"https://openalex.org/W7166504597","doi":"https://doi.org/10.63317/4fpwcgmuqk8x","title":"EarlySciRev: A Dataset of Early-Stage Scientific Revisions Extracted from LaTeX Writing Traces","display_name":"EarlySciRev: A Dataset of Early-Stage Scientific Revisions Extracted from LaTeX Writing Traces","publication_year":2026,"publication_date":"2026-05-01","ids":{"openalex":"https://openalex.org/W7166504597","doi":"https://doi.org/10.63317/4fpwcgmuqk8x"},"language":null,"primary_location":{"id":"doi:10.63317/4fpwcgmuqk8x","is_oa":true,"landing_page_url":"https://doi.org/10.63317/4fpwcgmuqk8x","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2026/workshops/nslp/pdf/2026.nslp-1.12.pdf","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://www.lrec-conf.org/proceedings/lrec2026/workshops/nslp/pdf/2026.nslp-1.12.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038574034","display_name":"L\u00e9ane Jourdan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"L\u00e9ane Jourdan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099442738","display_name":"Julien Aubert-B\u00e9duchaud","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Julien Aubert-B\u00e9duchaud","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132663304","display_name":"Yannis Chupin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yannis Chupin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132721326","display_name":"Marah Baccari","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marah Baccari","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5025206208","display_name":"Florian Boudin","orcid":"https://orcid.org/0000-0001-5849-2261"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Florian Boudin","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.84485331,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"119","last_page":"126"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.22679999470710754,"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"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.22679999470710754,"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"}},{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.19900000095367432,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11948","display_name":"Machine Learning in Materials Science","score":0.12470000237226486,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7121000289916992},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6168000102043152},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5347999930381775},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4846999943256378},{"id":"https://openalex.org/keywords/technical-writing","display_name":"Technical writing","score":0.3472000062465668},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.3411000072956085},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.32499998807907104}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7121000289916992},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6425999999046326},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6168000102043152},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5347999930381775},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4846999943256378},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.476500004529953},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3677999973297119},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36320000886917114},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3513999879360199},{"id":"https://openalex.org/C98545295","wikidata":"https://www.wikidata.org/wiki/Q1193158","display_name":"Technical writing","level":3,"score":0.3472000062465668},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.3411000072956085},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.32499998807907104},{"id":"https://openalex.org/C2984917352","wikidata":"https://www.wikidata.org/wiki/Q12772819","display_name":"Scientific discovery","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C2781083858","wikidata":"https://www.wikidata.org/wiki/Q17327049","display_name":"Scientific literature","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C2983685735","wikidata":"https://www.wikidata.org/wiki/Q5227355","display_name":"Data source","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C2993821838","wikidata":"https://www.wikidata.org/wiki/Q17327049","display_name":"Scientific article","level":3,"score":0.28380000591278076},{"id":"https://openalex.org/C2778949450","wikidata":"https://www.wikidata.org/wiki/Q1965486","display_name":"Scientific writing","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2513999938964844},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.63317/4fpwcgmuqk8x","is_oa":true,"landing_page_url":"https://doi.org/10.63317/4fpwcgmuqk8x","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2026/workshops/nslp/pdf/2026.nslp-1.12.pdf","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.63317/4fpwcgmuqk8x","is_oa":true,"landing_page_url":"https://doi.org/10.63317/4fpwcgmuqk8x","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2026/workshops/nslp/pdf/2026.nslp-1.12.pdf","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8889471888542175,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166504597.pdf","grobid_xml":"https://content.openalex.org/works/W7166504597.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Scientific":[0],"writing":[1,136],"is":[2,58],"an":[3],"iterative":[4],"process":[5],"that":[6,59],"generates":[7],"rich":[8],"revision":[9,28,86,105,119,138],"traces,":[10],"yet":[11],"publicly":[12],"available":[13],"resources":[14,123],"typically":[15],"expose":[16],"only":[17],"final":[18,80],"or":[19,67,128],"near-final":[20],"versions":[21],"of":[22,27,32,44],"papers.This":[23],"limits":[24],"empirical":[25],"study":[26],"behaviour":[29],"and":[30,88,131,140],"evaluation":[31],"large":[33],"language":[34],"models":[35],"(LLMs)":[36],"for":[37,118],"scientific":[38,46,135],"writing.We":[39],"introduce":[40],"EarlySciRev,":[41],"a":[42,115],"dataset":[43],"early-stage":[45],"text":[47,61],"revisions":[48,127],"automatically":[49],"extracted":[50],"from":[51,96],"arXiv":[52],"LaTeX":[53,63],"source":[54],"files.Our":[55],"key":[56],"observation":[57],"commented-out":[60],"in":[62,108],"often":[64],"preserves":[65],"discarded":[66],"alternative":[68],"formulations":[69],"written":[70],"by":[71],"the":[72],"authors":[73],"themselves.By":[74],"aligning":[75],"commented":[76],"segments":[77],"with":[78],"nearby":[79],"text,":[81],"we":[82],"extract":[83],"paragraph-level":[84],"candidate":[85,98],"pairs":[87],"apply":[89],"LLM-based":[90],"filtering":[91],"to":[92],"retain":[93],"genuine":[94],"revisions.Starting":[95],"1.28M":[97],"pairs,":[99,106],"our":[100],"pipeline":[101],"yields":[102],"578k":[103],"validated":[104],"grounded":[107],"authentic":[109],"early":[110],"drafting":[111],"traces.We":[112],"additionally":[113],"provide":[114],"human-annotated":[116],"benchmark":[117],"detection.EarlySciRev":[120],"complements":[121],"existing":[122],"focused":[124],"on":[125,134],"late-stage":[126],"synthetic":[129],"rewrites":[130],"supports":[132],"research":[133],"dynamics,":[137],"modelling,":[139],"LLM-assisted":[141],"editing.":[142]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-06-30T00:00:00"}
