{"id":"https://openalex.org/W7223968025","doi":"https://doi.org/10.5281/zenodo.23701130","title":"Honest Automated Subtitle Repair: A Reproducible Defect-Injection Benchmark of the VideoText.io Subtitle Quality Engine","display_name":"Honest Automated Subtitle Repair: A Reproducible Defect-Injection Benchmark of the VideoText.io Subtitle Quality Engine","publication_year":2026,"publication_date":"2026-10-27","ids":{"openalex":"https://openalex.org/W7223968025","doi":"https://doi.org/10.5281/zenodo.23701130"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23701130","doi":"https://doi.org/10.5281/zenodo.23701130","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23701130","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"volume":null,"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.23701130","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5094102800","display_name":"Guntupalli Santhosh","orcid":"https://orcid.org/0009-0003-8648-2994","observed_orcids":["https://orcid.org/0009-0003-8648-2994"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"GUNTUPALLI, SANTHOSH","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0003-8648-2994","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5094102800"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.9195394,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.5634999871253967,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.5634999871253967,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.28200000524520874,"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/T10260","display_name":"Software Engineering Research","score":0.09009999781847,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/srt","display_name":"SRT","score":0.5529999732971191},{"id":"https://openalex.org/keywords/videotext","display_name":"videotext","score":0.4449999928474426},{"id":"https://openalex.org/keywords/reproducibility","display_name":"reproducibility","score":0.6420000195503235}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8422999978065491},{"id":"https://openalex.org/C2780364048","wikidata":"https://www.wikidata.org/wiki/Q204028","display_name":"Subtitle","level":2,"score":0.8108999729156494},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7296000123023987},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4812000095844269},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4180000126361847},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.413100004196167},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.40119999647140503},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3653999865055084},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.35670000314712524},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31540000438690186},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31369999051094055},{"id":"https://openalex.org/C106436119","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assurance","level":3,"score":0.31060001254081726},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2980000078678131},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.259799987077713},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.25850000977516174},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.2549999952316284}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.23701130","doi":"https://doi.org/10.5281/zenodo.23701130","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23701130","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},{"id":"doi:10.5281/zenodo.23701131","doi":"https://doi.org/10.5281/zenodo.23701131","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23701131","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.5281/zenodo.23701130","doi":"https://doi.org/10.5281/zenodo.23701130","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23701130","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W1494198834"],"related_works":["https://openalex.org/W7102431443","https://openalex.org/W7221758073","https://openalex.org/W2530796318","https://openalex.org/W4285105502","https://openalex.org/W6979889412","https://openalex.org/W7204552900","https://openalex.org/W4401109362","https://openalex.org/W3118108424","https://openalex.org/W2770824972","https://openalex.org/W4293084213"],"abstract_inverted_index":{"This":[0],"technical":[1],"report":[2,173],"presents":[3],"a":[4,196],"reproducible":[5],"defect-injection":[6],"benchmark":[7,37,125,223,248],"evaluating":[8],"the":[9,82,118,131,176,199,207,212,247],"VideoText":[10,84,137,155],"subtitle":[11,16,26,85,161,227],"quality":[12],"engine":[13],"for":[14,98],"automated":[15],"validation":[17],"and":[18,31,52,70,163,217,229,256,263],"repair.":[19],"The":[20,36,134,172,222,244],"study":[21,135],"evaluates":[22,61,175],"2,000":[23,124],"synthetic":[24,225],"SRT":[25],"files":[27,102,228],"containing":[28,103],"118,803":[29],"cues":[30],"11,597":[32,78,191,204],"deliberately":[33],"injected":[34,79,192],"defects.":[35],"covers":[38],"overlapping":[39],"subtitles,":[40],"excessive":[41,47],"line":[42],"lengths,":[43],"multi-line":[44],"formatting":[45],"violations,":[46],"reading":[48],"speeds,":[49],"invalid":[50],"timestamps,":[51],"challenging":[53],"repair":[54,64,86,143],"conditions.":[55],"An":[56],"independently":[57,140],"implemented":[58,141],"rule":[59],"oracle":[60],"detection":[62],"accuracy,":[63,69,235],"compliance,":[65],"text":[66,162],"preservation,":[67],"reporting":[68,164],"reproducibility.":[71],"Key":[72],"findings":[73,90],"include:":[74],"Detection":[75],"of":[76,100,109,117,190],"all":[77,110,123,203],"defects":[80,105,165,193,205],"by":[81,182,267],"evaluated":[83,132],"engine.":[87],"Zero":[88],"false-positive":[89],"across":[91,122,130],"107,206":[92],"unmodified":[93],"cues.":[94],"Fully":[95],"compliant":[96],"output":[97,129],"1,190":[99],"1,200":[101],"repairable":[104,152],"(99.2%).":[106],"Independent":[107],"confirmation":[108],"10,322":[111],"fixes":[112],"reported":[113],"as":[114],"completed.":[115],"Preservation":[116],"original":[119,186],"word":[120],"sequence":[121],"files.":[126],"Deterministic,":[127],"repeatable":[128],"corpus.":[133],"compares":[136],"against":[138],"two":[139],"baseline":[142,147,254],"algorithms.":[144],"A":[145],"stronger":[146],"achieved":[148],"100%":[149],"compliance":[150],"on":[151],"files,":[153],"while":[154],"demonstrated":[156],"advantages":[157],"in":[158,206],"handling":[159],"overflowing":[160],"that":[166],"could":[167],"not":[168,231],"safely":[169],"be":[170],"repaired.":[171],"also":[174],"separate":[177,220],"public":[178],"check_subtitles":[179],"implementation":[180,187,201],"used":[181],"AI":[183],"assistants.":[184],"Its":[185],"detected":[188,202],"9,997":[189],"(86.2%).":[194],"Following":[195],"code":[197],"correction,":[198],"updated":[200],"benchmark.":[208],"These":[209],"results":[210,258],"describe":[211],"tested":[213],"code;":[214],"production":[215],"deployment":[216],"verification":[218],"are":[219],"requirements.":[221],"uses":[224],"English-language":[226],"does":[230],"evaluate":[232],"speech":[233],"recognition":[234],"translation":[236],"quality,":[237],"audio":[238],"alignment,":[239],"or":[240],"real-world":[241],"viewer":[242],"comprehension.":[243],"publication":[245],"includes":[246],"corpus,":[249],"evaluation":[250],"scripts,":[251],"independent":[252,261],"oracle,":[253],"implementations,":[255],"per-file":[257],"to":[259],"support":[260],"reproduction":[262],"further":[264],"research.":[265],"Developed":[266],"Santhosh":[268],"Guntupalli":[269],"at":[270],"VideoText.":[271,291],"Project:":[272],"https://videotext.io":[273],"Keywords:":[274],"Subtitle":[275,277,281,285],"Repair,":[276],"Quality":[278],"Assurance,":[279],"Automated":[280],"Correction,":[282],"SRT,":[283],"WebVTT,":[284],"Validation,":[286,290],"Reproducible":[287],"Benchmark,":[288],"Deterministic":[289]},"counts_by_year":[],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2026-10-28T00:00:00"}
