{"id":"https://openalex.org/W4411528198","doi":"https://doi.org/10.1145/3735654.3735942","title":"End-To-End ML with LLMs and Semantic Data Management: Experiences from Chemistry 4.0","display_name":"End-To-End ML with LLMs and Semantic Data Management: Experiences from Chemistry 4.0","publication_year":2025,"publication_date":"2025-06-22","ids":{"openalex":"https://openalex.org/W4411528198","doi":"https://doi.org/10.1145/3735654.3735942"},"language":"en","primary_location":{"id":"doi:10.1145/3735654.3735942","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3735654.3735942","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3735654.3735942","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Workshop on Data Management for End-to-End Machine Learning","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3735654.3735942","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022294418","display_name":"Sayed Hoseini","orcid":"https://orcid.org/0000-0002-4489-9025"},"institutions":[{"id":"https://openalex.org/I4210113269","display_name":"Hochschule Niederrhein","ror":"https://ror.org/027b9qx26","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210113269"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sayed Hoseini","raw_affiliation_strings":["Hochschule Niederrhein, University of Applied Sciences, Krefeld, Germany"],"raw_orcid":"https://orcid.org/0000-0002-4489-9025","affiliations":[{"raw_affiliation_string":"Hochschule Niederrhein, University of Applied Sciences, Krefeld, Germany","institution_ids":["https://openalex.org/I4210113269"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016895239","display_name":"Vincent Herrmann","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113269","display_name":"Hochschule Niederrhein","ror":"https://ror.org/027b9qx26","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210113269"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Vincent Herrmann","raw_affiliation_strings":["Hochschule Niederrhein, University of Applied Sciences, Krefeld, Germany"],"raw_orcid":"https://orcid.org/0009-0005-6006-1731","affiliations":[{"raw_affiliation_string":"Hochschule Niederrhein, University of Applied Sciences, Krefeld, Germany","institution_ids":["https://openalex.org/I4210113269"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043782050","display_name":"Christoph Quix","orcid":"https://orcid.org/0000-0002-1698-4345"},"institutions":[{"id":"https://openalex.org/I4210110507","display_name":"Fraunhofer Institute for Applied Information Technology","ror":"https://ror.org/01ak24c12","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210110507","https://openalex.org/I4923324"]},{"id":"https://openalex.org/I4210113269","display_name":"Hochschule Niederrhein","ror":"https://ror.org/027b9qx26","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210113269"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christoph Quix","raw_affiliation_strings":["Hochschule Niederrhein & Fraunhofer FIT, Krefeld/St. Augustin, Germany"],"raw_orcid":"https://orcid.org/0000-0002-1698-4345","affiliations":[{"raw_affiliation_string":"Hochschule Niederrhein & Fraunhofer FIT, Krefeld/St. Augustin, Germany","institution_ids":["https://openalex.org/I4210113269","https://openalex.org/I4210110507"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.14138311,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9930999875068665,"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":0.9930999875068665,"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/T11937","display_name":"Research Data Management Practices","score":0.9865999817848206,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9406999945640564,"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/computer-science","display_name":"Computer science","score":0.501197338104248},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4237973093986511},{"id":"https://openalex.org/keywords/data-management","display_name":"Data management","score":0.41880926489830017},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.3670384883880615},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1378517746925354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.501197338104248},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4237973093986511},{"id":"https://openalex.org/C1668388","wikidata":"https://www.wikidata.org/wiki/Q1149776","display_name":"Data management","level":2,"score":0.41880926489830017},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.3670384883880615},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1378517746925354}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3735654.3735942","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3735654.3735942","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3735654.3735942","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Workshop on Data Management for End-to-End Machine Learning","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3735654.3735942","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3735654.3735942","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3735654.3735942","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Workshop on Data Management for End-to-End Machine Learning","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2028916887","display_name":null,"funder_award_id":"13FH557KX0","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"}],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411528198.pdf","grobid_xml":"https://content.openalex.org/works/W4411528198.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W2083253722","https://openalex.org/W2164947858","https://openalex.org/W2953631544","https://openalex.org/W3042021489","https://openalex.org/W3135071100","https://openalex.org/W3181257149","https://openalex.org/W3206724556","https://openalex.org/W3206811428","https://openalex.org/W4200044786","https://openalex.org/W4225000412","https://openalex.org/W4283322925","https://openalex.org/W4284977004","https://openalex.org/W4310529830","https://openalex.org/W4312754859","https://openalex.org/W4367319005","https://openalex.org/W4385520852","https://openalex.org/W4387847223","https://openalex.org/W4389320207","https://openalex.org/W4390731917","https://openalex.org/W4391136507","https://openalex.org/W4391876619","https://openalex.org/W4392357044","https://openalex.org/W4395689785","https://openalex.org/W4397048921","https://openalex.org/W4399117322","https://openalex.org/W4401879861","https://openalex.org/W4403536355","https://openalex.org/W4403536613","https://openalex.org/W4405901049"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W2948807893","https://openalex.org/W2899084033","https://openalex.org/W2778153218","https://openalex.org/W2748952813","https://openalex.org/W1531601525","https://openalex.org/W4391375266","https://openalex.org/W2078814861","https://openalex.org/W2527526854","https://openalex.org/W2496730672"],"abstract_inverted_index":{"Machine":[0],"Learning":[1],"(ML)":[2],"in":[3,36,53],"industrial":[4],"chemistry":[5],"is":[6,45],"often":[7],"hindered":[8],"by":[9,99,139],"the":[10,22,112,129,134,145,153,157],"complexity":[11],"of":[12,24,32,136,156],"preprocessing":[13,88],"heterogeneous":[14],"datasets.":[15],"In":[16],"this":[17],"proof-of-concept":[18],"study,":[19],"we":[20],"explore":[21],"use":[23],"semantic":[25,43,101,130],"data":[26,66],"management":[27],"to":[28,47,63,80,132],"support":[29],"LLM-driven":[30],"automation":[31],"end-to-end":[33],"ML":[34,69],"pipelines":[35],"a":[37,54],"real-world":[38],"Chemistry":[39],"4.0":[40],"setting.":[41],"A":[42],"model":[44,131],"used":[46],"capture":[48],"domain":[49],"knowledge":[50],"and":[51,68,89],"metadata":[52],"machine-readable":[55],"form,":[56],"guiding":[57],"LLMs":[58,76,104],"through":[59],"natural":[60],"language":[61],"prompts":[62],"generate":[64,107],"complete":[65],"wrangling":[67],"modeling":[70],"code.":[71],"We":[72],"evaluate":[73],"several":[74],"state-of-the-art":[75],"on":[77,152],"their":[78],"ability":[79],"autonomously":[81],"produce":[82],"functionally":[83],"correct":[84],"Python":[85],"code":[86,137],"for":[87,114,124],"Gaussian":[90],"Process":[91],"modeling.":[92],"Our":[93],"results":[94],"show":[95],"that,":[96],"when":[97],"guided":[98],"structured":[100],"context,":[102],"larger":[103],"can":[105],"reliably":[106],"accurate":[108],"pipelines,":[109],"significantly":[110],"reducing":[111],"need":[113],"manual":[115],"intervention.":[116],"These":[117],"findings":[118],"provide":[119],"an":[120],"encouraging":[121],"starting":[122],"point":[123],"further":[125],"exploration":[126],"toward":[127],"leveraging":[128],"improve":[133],"robustness":[135],"generation":[138,146],"systematically":[140],"integrating":[141],"relevant":[142],"information":[143],"into":[144],"process,":[147],"rather":[148],"than":[149],"relying":[150],"solely":[151],"raw":[154],"intelligence":[155],"LLM.":[158]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}