{"id":"https://openalex.org/W7135201085","doi":"https://doi.org/10.3390/a19030214","title":"Efficient and Verified Research Data Extraction with LLM","display_name":"Efficient and Verified Research Data Extraction with LLM","publication_year":2026,"publication_date":"2026-03-13","ids":{"openalex":"https://openalex.org/W7135201085","doi":"https://doi.org/10.3390/a19030214"},"language":"en","primary_location":{"id":"doi:10.3390/a19030214","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a19030214","pdf_url":"https://www.mdpi.com/1999-4893/19/3/214/pdf","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-4893/19/3/214/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129093930","display_name":"Aleksandr Serdiukov","orcid":null},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Aleksandr Serdiukov","raw_affiliation_strings":["Faculty of Information Technology and Programming, ITMO University, 197101 St. Petersburg, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology and Programming, ITMO University, 197101 St. Petersburg, Russia","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128973599","display_name":"Vitaliy Dravgelis","orcid":null},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Vitaliy Dravgelis","raw_affiliation_strings":["Faculty of Information Technology and Programming, ITMO University, 197101 St. Petersburg, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology and Programming, ITMO University, 197101 St. Petersburg, Russia","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057377929","display_name":"Daniil Smutin","orcid":"https://orcid.org/0009-0009-1460-4108"},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]},{"id":"https://openalex.org/I4210152028","display_name":"Institute of Biomedical Chemistry","ror":"https://ror.org/040wrkp27","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210110862","https://openalex.org/I4210152028"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Daniil Smutin","raw_affiliation_strings":["Faculty of Information Technology and Programming, ITMO University, 197101 St. Petersburg, Russia","Institute of Biomedical Chemistry, 119121 Moscow, Russia"],"raw_orcid":"https://orcid.org/0009-0009-1460-4108","affiliations":[{"raw_affiliation_string":"Faculty of Information Technology and Programming, ITMO University, 197101 St. Petersburg, Russia","institution_ids":["https://openalex.org/I173089394"]},{"raw_affiliation_string":"Institute of Biomedical Chemistry, 119121 Moscow, Russia","institution_ids":["https://openalex.org/I4210152028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020887835","display_name":"Amir Taldaev","orcid":"https://orcid.org/0000-0003-2593-1963"},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]},{"id":"https://openalex.org/I4210105571","display_name":"Institute of Bioorganic Chemistry","ror":"https://ror.org/01dg04253","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210105571","https://openalex.org/I4210129690"]},{"id":"https://openalex.org/I4210152028","display_name":"Institute of Biomedical Chemistry","ror":"https://ror.org/040wrkp27","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210110862","https://openalex.org/I4210152028"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Amir Taldaev","raw_affiliation_strings":["Faculty of Information Technology and Programming, ITMO University, 197101 St. Petersburg, Russia","Institute of Biomedical Chemistry, 119121 Moscow, Russia","Research Center for Molecular Mechanisms of Aging and Age-Related Diseases, Moscow Center for Advanced Studies, 123592 Moscow, Russia","Shemyakin-Ovchinnikov Institute of Bioorganic Chemistry RAS, 117997 Moscow, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology and Programming, ITMO University, 197101 St. Petersburg, Russia","institution_ids":["https://openalex.org/I173089394"]},{"raw_affiliation_string":"Institute of Biomedical Chemistry, 119121 Moscow, Russia","institution_ids":["https://openalex.org/I4210152028"]},{"raw_affiliation_string":"Research Center for Molecular Mechanisms of Aging and Age-Related Diseases, Moscow Center for Advanced Studies, 123592 Moscow, Russia","institution_ids":[]},{"raw_affiliation_string":"Shemyakin-Ovchinnikov Institute of Bioorganic Chemistry RAS, 117997 Moscow, Russia","institution_ids":["https://openalex.org/I4210105571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027665555","display_name":"A. B. Ivanov","orcid":"https://orcid.org/0000-0002-7997-0637"},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Artem Ivanov","raw_affiliation_strings":["Faculty of Information Technology and Programming, ITMO University, 197101 St. Petersburg, Russia"],"raw_orcid":"https://orcid.org/0000-0002-7997-0637","affiliations":[{"raw_affiliation_string":"Faculty of Information Technology and Programming, ITMO University, 197101 St. Petersburg, Russia","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082734053","display_name":"Leonid Adonin","orcid":"https://orcid.org/0000-0003-1563-4615"},"institutions":[{"id":"https://openalex.org/I37355250","display_name":"Saint-Petersburg State University of Telecommunications","ror":"https://ror.org/00pcyc255","country_code":"RU","type":"education","lineage":["https://openalex.org/I37355250"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Leonid Adonin","raw_affiliation_strings":["Faculty of Radioelectronic Systems and Robotics, The Bonch-Bruevich Saint-Petersburg State University of Telecommunications, 193232 St. Petersburg, Russia"],"raw_orcid":"https://orcid.org/0000-0003-1563-4615","affiliations":[{"raw_affiliation_string":"Faculty of Radioelectronic Systems and Robotics, The Bonch-Bruevich Saint-Petersburg State University of Telecommunications, 193232 St. Petersburg, Russia","institution_ids":["https://openalex.org/I37355250"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048360368","display_name":"Sergey Muravyov","orcid":"https://orcid.org/0000-0002-4251-1744"},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Sergey Muravyov","raw_affiliation_strings":["Faculty of Information Technology and Programming, ITMO University, 197101 St. Petersburg, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology and Programming, ITMO University, 197101 St. Petersburg, Russia","institution_ids":["https://openalex.org/I173089394"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34681114,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"19","issue":"3","first_page":"214","last_page":"214"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9355999827384949,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9355999827384949,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.012000000104308128,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.006800000090152025,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.598800003528595},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.531499981880188},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4381999969482422},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4124999940395355},{"id":"https://openalex.org/keywords/json","display_name":"JSON","score":0.40939998626708984},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.40790000557899475},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.40299999713897705},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.3986000120639801},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.34369999170303345}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7177000045776367},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.598800003528595},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.531499981880188},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46230000257492065},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4381999969482422},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43320000171661377},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4124999940395355},{"id":"https://openalex.org/C2780416260","wikidata":"https://www.wikidata.org/wiki/Q2063","display_name":"JSON","level":2,"score":0.40939998626708984},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.40790000557899475},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.40299999713897705},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.3986000120639801},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3831000030040741},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3702000081539154},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.34369999170303345},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.3140000104904175},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.31349998712539673},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.31040000915527344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3066999912261963},{"id":"https://openalex.org/C2778805511","wikidata":"https://www.wikidata.org/wiki/Q1713","display_name":"Citation","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29899999499320984},{"id":"https://openalex.org/C88006597","wikidata":"https://www.wikidata.org/wiki/Q690117","display_name":"Disk formatting","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C92446256","wikidata":"https://www.wikidata.org/wiki/Q3306762","display_name":"Data validation","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C154690210","wikidata":"https://www.wikidata.org/wiki/Q1668499","display_name":"Rewriting","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C78063203","wikidata":"https://www.wikidata.org/wiki/Q3062596","display_name":"DNA extraction","level":4,"score":0.2786000072956085},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C29275276","wikidata":"https://www.wikidata.org/wiki/Q2268965","display_name":"Conceptual schema","level":3,"score":0.27219998836517334},{"id":"https://openalex.org/C40077939","wikidata":"https://www.wikidata.org/wiki/Q2336004","display_name":"Semi-structured data","level":3,"score":0.2718999981880188},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.26179999113082886},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.25279998779296875}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/a19030214","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a19030214","pdf_url":"https://www.mdpi.com/1999-4893/19/3/214/pdf","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:c0fc0755fc7e4518b04f4e28f06155d9","is_oa":true,"landing_page_url":"https://doaj.org/article/c0fc0755fc7e4518b04f4e28f06155d9","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms, Vol 19, Iss 3, p 214 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/a19030214","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a19030214","pdf_url":"https://www.mdpi.com/1999-4893/19/3/214/pdf","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3107435225","display_name":null,"funder_award_id":"075-15-2025-461","funder_id":"https://openalex.org/F4320327494","funder_display_name":"Ministry of Science and Higher Education of the Russian Federation"}],"funders":[{"id":"https://openalex.org/F4320327494","display_name":"Ministry of Science and Higher Education of the Russian Federation","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7135201085.pdf","grobid_xml":"https://content.openalex.org/works/W7135201085.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1951724000","https://openalex.org/W2774486220","https://openalex.org/W2793422535","https://openalex.org/W2990427812","https://openalex.org/W4242289937","https://openalex.org/W4309674289","https://openalex.org/W4387321091","https://openalex.org/W4392343921","https://openalex.org/W4394713233","https://openalex.org/W4396977542","https://openalex.org/W4399812563","https://openalex.org/W4400663124","https://openalex.org/W4404048128","https://openalex.org/W4405555367","https://openalex.org/W4406259849","https://openalex.org/W4406663495","https://openalex.org/W4406866255","https://openalex.org/W4408832102","https://openalex.org/W4409190866","https://openalex.org/W4411622822","https://openalex.org/W4415916253"],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"hold":[4],"promise":[5],"for":[6,155,169],"automated":[7],"extraction":[8,35,96,130],"of":[9,48,123,153,173],"structured":[10,156],"biological":[11],"information":[12],"from":[13,41,133],"scientific":[14,42,157],"literature,":[15],"yet":[16],"their":[17],"reliability":[18],"in":[19],"some":[20],"domain-specific":[21],"tasks,":[22],"such":[23],"as":[24],"DNA":[25],"probe":[26],"parsing":[27],"remains":[28],"underexplored.":[29],"We":[30],"developed":[31],"a":[32,45,68,163],"verification-focused,":[33],"schema-guided":[34],"pipeline":[36],"that":[37,72,128],"transforms":[38],"unstructured":[39],"texts":[40],"articles":[43],"into":[44],"normalized":[46],"database":[47],"oligonucleotide":[49],"probes,":[50],"primers,":[51],"and":[52,67,112,120,135,149,166],"associated":[53],"metadata.":[54],"The":[55,160],"system":[56],"combined":[57],"multi-turn":[58],"JSON":[59],"generation,":[60],"strict":[61],"schema":[62],"validation,":[63],"sequence-specific":[64],"rule":[65],"checks,":[66],"post-processing":[69],"recovery":[70,125],"module":[71,126],"rescues":[73],"systematically":[74],"corrupted":[75],"nucleotide":[76],"outputs.":[77],"Benchmarking":[78],"across":[79],"nine":[80],"contemporary":[81],"LLMs":[82,154],"revealed":[83],"distinct":[84],"accuracy\u2013hallucination":[85],"trade-offs,":[86],"with":[87],"the":[88,93,121,124,147,150],"context-optimized":[89],"Qwen3":[90],"model":[91],"achieving":[92],"highest":[94],"overall":[95],"efficiency":[97],"while":[98],"maintaining":[99],"low":[100],"hallucination":[101],"rates.":[102],"Iterative":[103],"prompting":[104],"substantially":[105],"improved":[106],"fidelity":[107],"but":[108],"introduced":[109],"notable":[110],"latency":[111],"variance.":[113],"Across":[114],"all":[115],"models,":[116],"stable":[117],"error":[118],"profiles":[119],"success":[122],"indicated":[127],"most":[129],"failures":[131],"stem":[132],"systematic":[134],"correctable":[136],"formatting":[137],"issues":[138],"rather":[139],"than":[140],"semantic":[141],"misunderstandings.":[142],"These":[143],"findings":[144],"highlight":[145],"both":[146],"potential":[148],"current":[151],"limitations":[152],"data":[158],"extraction.":[159],"research":[161],"provides":[162],"reproducible":[164],"benchmark":[165],"extensible":[167],"framework":[168],"future":[170],"large-scale":[171],"curation":[172],"molecular":[174],"biology":[175],"datasets.":[176]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-14T00:00:00"}