{"id":"https://openalex.org/W7202201192","doi":"https://doi.org/10.48550/arxiv.2608.07617","title":"TeXFix-Bench: An Empirically Grounded Multi-Format Benchmark for LLM-Based Document Source Repair","display_name":"TeXFix-Bench: An Empirically Grounded Multi-Format Benchmark for LLM-Based Document Source Repair","publication_year":2026,"publication_date":"2026-08-07","ids":{"openalex":"https://openalex.org/W7202201192","doi":"https://doi.org/10.48550/arxiv.2608.07617"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.07617","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.07617","pdf_url":"https://arxiv.org/pdf/2608.07617","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.07617","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5144220577","display_name":"Prajwal S. Venkateshmurthy","orcid":"https://orcid.org/0009-0004-8830-0725","observed_orcids":["https://orcid.org/0009-0004-8830-0725"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Venkateshmurthy, Prajwal S.","raw_affiliation_strings":["Independent Researcher San Jose , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher San Jose , CA , USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5144220577"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.8726000189781189,"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":0.8726000189781189,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.1193000003695488,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.002099999925121665,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/latex","display_name":"LaTeX","score":0.6119999885559082},{"id":"https://openalex.org/keywords/typst","display_name":"Typst","score":0.9399999976158142},{"id":"https://openalex.org/keywords/markdown","display_name":"Markdown","score":0.9980000257492065},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.6460000276565552},{"id":"https://openalex.org/keywords/fault-classification","display_name":"fault classification","score":0.9599999785423279},{"id":"https://openalex.org/keywords/zero-shot-evaluation","display_name":"zero-shot evaluation","score":0.5709999799728394},{"id":"https://openalex.org/keywords/scientific-writing","display_name":"scientific writing","score":0.3799999952316284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6244999766349792},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5989000201225281},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.567799985408783},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.5597000122070312},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5422000288963318},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.4514000117778778},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.40950000286102295},{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.40790000557899475},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.40639999508857727},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.3880999982357025},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3709999918937683},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.3630000054836273},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3440000116825104},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3312999904155731},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32170000672340393},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C200833197","wikidata":"https://www.wikidata.org/wiki/Q333707","display_name":"Compile time","level":3,"score":0.30959999561309814},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.07617","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.07617","pdf_url":"https://arxiv.org/pdf/2608.07617","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.07617","doi":"https://doi.org/10.48550/arxiv.2608.07617","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.07617","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.07617","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.07617","pdf_url":"https://arxiv.org/pdf/2608.07617","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7202201192.pdf","grobid_xml":"https://content.openalex.org/works/W7202201192.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W841012168","https://openalex.org/W2061575154","https://openalex.org/W2135841285","https://openalex.org/W2156723666","https://openalex.org/W4392934763","https://openalex.org/W4402457502","https://openalex.org/W7172220604"],"related_works":["https://openalex.org/W4412944125","https://openalex.org/W7138063852","https://openalex.org/W7204207709","https://openalex.org/W4416037500","https://openalex.org/W7131411048","https://openalex.org/W7147223813","https://openalex.org/W7160958579","https://openalex.org/W2408844256","https://openalex.org/W2509728321","https://openalex.org/W7221367548"],"abstract_inverted_index":{"Scientific":[0],"and":[1,13,72,115,142,191,210,241],"technical":[2],"writing":[3],"depends":[4],"on":[5,17,111],"markup":[6],"sources":[7],"that":[8,35,201],"must":[9],"compile:":[10],"LaTeX,":[11],"Typst,":[12],"Markdown":[14],"pipelines":[15],"fail":[16],"missing":[18],"delimiters,":[19],"mismatched":[20],"environments,":[21],"broken":[22],"imports,":[23],"or":[24],"package":[25,73],"conflicts.":[26],"Existing":[27],"document-repair":[28],"evaluations":[29],"inject":[30],"faults":[31,65,101],"with":[32,151,219],"ad-hoc":[33],"edits":[34],"lack":[36],"an":[37,84],"empirical":[38],"fault":[39,56],"model.":[40],"We":[41,133,236],"present":[42],"TeXFix-Bench,":[43],"a":[44,54,116,147,179],"multi-format":[45],"benchmark":[46],"for":[47],"LLM-based":[48],"full-source":[49],"document":[50,208],"repair":[51,107,125,234],"grounded":[52],"in":[53],"mined":[55,121],"taxonomy.":[57],"A":[58,96,164,174,193],"Grounded-Theory":[59],"study":[60,119],"of":[61,203],"localized":[62],"hard-crash":[63],"LaTeX":[64,190],"from":[66,131,137,214],"TeX":[67],"Stack":[68],"Exchange,":[69],"GitHub":[70],"commits,":[71],"documentation":[74],"(168":[75],"verified":[76],"faults,":[77],"dual":[78],"open":[79],"coding":[80],"at":[81,157],"$\u03ba$=0.34)":[82],"yields":[83,178],"18-category":[85],"taxonomy":[86],"instantiated":[87],"as":[88],"DocMut:":[89],"48":[90],"AST-aware":[91],"operators":[92],"across":[93],"three":[94],"formats.":[95],"three-model":[97],"cross-benchmark":[98],"shows":[99,200],"DocMut":[100],"are":[102],"5.6-9.2":[103],"pp":[104],"harder":[105,188],"to":[106],"than":[108,189],"pattern-based":[109],"mutations":[110],"the":[112,217,220,238],"same":[113],"seeds,":[114],"real-error":[117],"case":[118],"(88":[120],"human":[122],"crashes,":[123],"67.0%":[124],"success)":[126],"brackets":[127],"both":[128],"synthetic":[129],"sets":[130],"below.":[132],"construct":[134],"10,437":[135],"instances":[136],"743":[138],"openly":[139],"licensed":[140],"seeds":[141],"evaluate":[143],"seven":[144],"LLMs":[145],"under":[146],"fixed":[148],"zero-shot":[149],"protocol":[150],"provider-pinned":[152],"routing,":[153],"collecting":[154],"48,651":[155],"attempts":[156],"about":[158],"USD":[159],"200":[160],"total":[161],"inference":[162],"cost.":[163],"complete":[165],"6,613-instance":[166],"x":[167],"7-model":[168],"balanced":[169],"matrix":[170],"confirms":[171],"all":[172,242],"rankings.":[173],"pinned":[175],"engine":[176],"gate":[177],"27.5-point":[180],"intention-to-treat":[181],"compile":[182,215,222],"spread":[183],"(56.7-84.2%).":[184],"Typst":[185],"is":[186],"markedly":[187],"Markdown.":[192],"restoration":[194,211],"oracle":[195],"over":[196],"28,129":[197],"compiling":[198,204],"repairs":[199,205],"13.6-18.5%":[202],"materially":[206],"alter":[207],"text,":[209],"rank":[212],"diverges":[213],"rank:":[216],"model":[218],"lowest":[221],"rate":[223],"restores":[224],"content":[225],"best":[226],"among":[227],"its":[228],"successes.":[229],"Compile":[230],"success":[231],"alone":[232],"overstates":[233],"quality.":[235],"release":[237],"taxonomy,":[239],"DocMut,":[240],"campaign":[243],"artifacts.":[244]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-12T00:00:00"}
