{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T00:07:25Z","timestamp":1755216445820,"version":"3.43.0"},"reference-count":57,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T00:00:00Z","timestamp":1754265600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T00:00:00Z","timestamp":1754265600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2025,9,30]]},"abstract":"Abstract<\/jats:title>\n The structure and electronic properties of nitrides have garnered significant research interest. To improve prediction efficiency and generalization ability, this study proposes an large language model (LLM) fine-tuning method trained by data with description of nitride crystal structure, obtaining textual data directly through automated workflow, bypassing the need for complex feature engineering. The outcomes demonstrate a notable enhancement in the prediction of material properties. With the GPT-3.5-turbo model fine-tuned, the \n \n \n \n \n \n R<\/mml:mi>\n <\/mml:mrow>\n \n 2<\/mml:mn>\n <\/mml:mrow>\n <\/mml:msup>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula> value went up from 0.6890 to 0.9868 and from 0.5119 to 0.9824. The fine-tuned GPT-3.5-turbo model outperforms GPT-3.5 and GPT-4.0 in terms of average prediction accuracy, with a 73.43\n \n \n \n \n %<\/mml:mi>\n <\/mml:mrow>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula> and 67.13\n \n \n \n \n %<\/mml:mi>\n <\/mml:mrow>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula> increase, respectively. Additionally, the generalizability of the model is checked by applying it to unknown nitrides. The average accuracy of the fine-tuned GPT-3.5-turbo model are 90.50\n \n \n \n \n %<\/mml:mi>\n <\/mml:mrow>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula> and 80.40\n \n \n \n \n %<\/mml:mi>\n <\/mml:mrow>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>, compared with the results of the first principles calculation. These outcomes are on par with what shallow ML models achieve. The results of this work demonstrate that fine-tuned LLMs can serve as effective and generalizable tools for predicting the band gap (\n \n \n \n \n \n \n E<\/mml:mi>\n <\/mml:mrow>\n g<\/mml:mi>\n <\/mml:msub>\n <\/mml:mrow>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>) and formation energy (\n \n \n \n \u0394<\/mml:mi>\n \n \n H<\/mml:mtext>\n \n f<\/mml:mi>\n <\/mml:mrow>\n <\/mml:msub>\n <\/mml:mrow>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>) of III-VIIIB and III-IVA nitrides, thereby simplifying the prediction process and saving time.<\/jats:p>","DOI":"10.1088\/2632-2153\/adf374","type":"journal-article","created":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T22:51:46Z","timestamp":1753311106000},"page":"035019","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Domain-specific large language model for predicting band gap and formation energy of III-VIIIB and III-IVA nitrides based on fine-tuned GPT-3.5-turbo"],"prefix":"10.1088","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-1111-7306","authenticated-orcid":false,"given":"Lin","family":"Hu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1650-4276","authenticated-orcid":true,"given":"Guozhu","family":"Jia","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2025,8,4]]},"reference":[{"key":"mlstadf374bib1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpcs.2021.110011","article-title":"Stability and electronic and optical properties of ternary nitride phases of MgSnN2: a first-principles study","volume":"153","author":"Dumre","year":"2021","journal-title":"J. Phys. Chem. Solids"},{"key":"mlstadf374bib2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1904926116","article-title":"Ternary nitride semiconductors in the rocksalt crystal structure","volume":"116","author":"Bauers","year":"2019","journal-title":"Proc. Natl Acad. Sci."},{"key":"mlstadf374bib3","doi-asserted-by":"publisher","DOI":"10.1002\/adfm.202209880","article-title":"Recent advances in mechanically transferable III-nitride based on 2D buffer strategy","volume":"33","author":"Song","year":"2023","journal-title":"Adv. Funct. Mater."},{"key":"mlstadf374bib4","doi-asserted-by":"publisher","first-page":"64244","DOI":"10.1021\/acsami.4c13648","article-title":"Nitrogen complex-driven vacancy cluster in group-III nitrides","volume":"16","author":"Shin","year":"2024","journal-title":"ACS Appl. Mater. Interfaces"},{"key":"mlstadf374bib5","doi-asserted-by":"publisher","first-page":"134","DOI":"10.19491\/j.issn.1001-9278.2024.10.023","article-title":"Progress in applications of carbon nitride nano organic materials","volume":"38","author":"Xuejing","year":"2024","journal-title":"China Plast."},{"key":"mlstadf374bib6","doi-asserted-by":"publisher","DOI":"10.1016\/j.mser.2020.100578","article-title":"Recent progress in group III-nitride nanostructures: from materials to applications","volume":"142","author":"Chen","year":"2020","journal-title":"Mater. Sci. Eng."},{"key":"mlstadf374bib7","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6633\/aa7bb2","article-title":"Optoelectronic device physics and technology of nitride semiconductors from the uv to the terahertz","volume":"80","author":"Moustakas","year":"2017","journal-title":"Rep. Prog. Phys."},{"key":"mlstadf374bib8","doi-asserted-by":"publisher","DOI":"10.1016\/j.cocom.2022.e00711","article-title":"Theoretical investigation of some fundamental physical properties of the ternary nitrides Ca4SiN4 and Ca4GeN4 under pressure and temperature effect","volume":"32","author":"Boucenna","year":"2022","journal-title":"Comput. Condens. Matter"},{"key":"mlstadf374bib9","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1016\/j.commatsci.2014.06.045","article-title":"Structural, mechanical, electronic and optical properties of layered ternary nitrides SrZrN2 and SrHfN2: first-principles calculations","volume":"93","author":"Tian","year":"2014","journal-title":"Comput. Mater. Sci."},{"key":"mlstadf374bib10","doi-asserted-by":"publisher","first-page":"6742","DOI":"10.1039\/C5TA09446A","article-title":"Design of nitride semiconductors for solar energy conversion","volume":"4","author":"Zakutayev","year":"2016","journal-title":"J. Mater. Chem. A"},{"key":"mlstadf374bib11","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1038\/s41597-020-00723-8","article-title":"A band-gap database for semiconducting inorganic materials calculated with hybrid functional","volume":"7","author":"Kim","year":"2020","journal-title":"Sci. Data"},{"key":"mlstadf374bib12","doi-asserted-by":"publisher","first-page":"5156","DOI":"10.1039\/D2CP06082E","article-title":"Density functional theory study of bulk properties of transition metal nitrides","volume":"25","author":"Lynn","year":"2023","journal-title":"Phys. Chem. Chem. Phys."},{"key":"mlstadf374bib13","article-title":"Enhancing prediction accuracy of physical band gaps in semiconductor materials","volume":"4","author":"Masood","year":"2023","journal-title":"Cell Rep. Phys. Sci."},{"key":"mlstadf374bib14","doi-asserted-by":"publisher","DOI":"10.1016\/j.cartre.2024.100413","article-title":"The influence of carbon content to the band gap of abc stacked trilayer hybridized graphene and hexagonal boron nitride","volume":"17","author":"Sun","year":"2024","journal-title":"Carbon Trends"},{"key":"mlstadf374bib15","doi-asserted-by":"publisher","DOI":"10.1016\/j.commatsci.2024.113560","article-title":"The effects of biaxial strain and sulfur\/boron doping on the photocatalytic performance of the g-C3N5 system: a first-principles study","volume":"247","author":"Yao","year":"2025","journal-title":"Comput. Mater. Sci."},{"key":"mlstadf374bib16","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevMaterials.8.044602","article-title":"Chemical trend of radiative recombination in III-nitrides","volume":"8","author":"Liu","year":"2024","journal-title":"Phys. Rev. Mater."},{"key":"mlstadf374bib17","doi-asserted-by":"publisher","first-page":"9196","DOI":"10.3390\/app14209196","article-title":"Machine learning accelerated design of high-temperature ternary and quaternary nitride superconductors","volume":"14","author":"Islam","year":"2024","journal-title":"Appl. Sci."},{"key":"mlstadf374bib18","doi-asserted-by":"publisher","first-page":"1908","DOI":"10.1016\/j.cjph.2024.04.032","article-title":"Study of the novel boron nitride polymorphs: first-principles calculations and machine learning","volume":"89","author":"Fan","year":"2024","journal-title":"Chin. J. Phys."},{"key":"mlstadf374bib19","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1016\/j.ijhydene.2024.07.245","article-title":"Optimization of g-C3N4 synthesis parameters based on machine learning to predict the efficiency of photocatalytic hydrogen production","volume":"81","author":"Yurova","year":"2024","journal-title":"Int. J. Hydrog. Energy"},{"year":"2015","author":"Koch","key":"mlstadf374bib20"},{"key":"mlstadf374bib21","doi-asserted-by":"publisher","first-page":"A1133","DOI":"10.1103\/PhysRev.140.A1133","article-title":"Self-consistent equations including exchange and correlation effects","volume":"140","author":"Kohn","year":"1965","journal-title":"Phys. Rev."},{"key":"mlstadf374bib22","doi-asserted-by":"publisher","DOI":"10.1088\/2515-7639\/ab084b","article-title":"From DFT to machine learning: recent approaches to materials science\u2013a review","volume":"2","author":"Schleder","year":"2019","journal-title":"J. Phys. Mater."},{"key":"mlstadf374bib23","doi-asserted-by":"publisher","DOI":"10.1016\/j.mtcomm.2021.102932","article-title":"Accurate bandgap predictions of solids assisted by machine learning","volume":"29","author":"Wang","year":"2021","journal-title":"Mater. Today Commun."},{"key":"mlstadf374bib24","doi-asserted-by":"publisher","first-page":"4031","DOI":"10.1021\/acs.chemmater.8b00686","article-title":"Machine-learning-assisted accurate band gap predictions of functionalized mxene","volume":"30","author":"Rajan","year":"2018","journal-title":"Chem. Mater."},{"key":"mlstadf374bib25","doi-asserted-by":"publisher","first-page":"1668","DOI":"10.1021\/acs.jpclett.8b00124","article-title":"Predicting the band gaps of inorganic solids by machine learning","volume":"9","author":"Zhuo","year":"2018","journal-title":"J. Phys. Chem. Lett."},{"key":"mlstadf374bib26","doi-asserted-by":"publisher","first-page":"39481","DOI":"10.1021\/acsomega.3c05224","article-title":"Graph comparison of molecular crystals in band gap prediction using neural networks","volume":"8","author":"Taniguchi","year":"2023","journal-title":"ACS Omega"},{"key":"mlstadf374bib27","doi-asserted-by":"publisher","first-page":"21561","DOI":"10.1016\/j.ceramint.2023.03.292","article-title":"Data-driven optimization of hardness and toughness of high-entropy nitride coatings","volume":"49","author":"Wu","year":"2023","journal-title":"Ceram. Int."},{"key":"mlstadf374bib28","doi-asserted-by":"publisher","first-page":"803","DOI":"10.1016\/j.actamat.2020.09.068","article-title":"Dramatically enhanced combination of ultimate tensile strength and electric conductivity of alloys via machine learning screening","volume":"200","author":"Zhang","year":"2020","journal-title":"Acta Mater."},{"key":"mlstadf374bib29","doi-asserted-by":"publisher","DOI":"10.1016\/j.actamat.2022.118341","article-title":"Machine learning assisted predictions of multi-component phase diagrams and fine boundary information","volume":"240","author":"He","year":"2022","journal-title":"Acta Mater."},{"key":"mlstadf374bib30","doi-asserted-by":"publisher","first-page":"1307","DOI":"10.1007\/s40145-022-0612-4","article-title":"Hou X and Wang E Maximizing the mechanical performance of Ti3AlC2-based max phases with aid of machine learning","volume":"11","author":"Duan","year":"2022","journal-title":"J. Adv. Ceram."},{"key":"mlstadf374bib31","doi-asserted-by":"publisher","DOI":"10.1016\/j.actamat.2022.118378","article-title":"Wang E and Hou X A new strategy for long-term complex oxidation of max phases: database generation and oxidation kinetic model establishment with aid of machine learning","volume":"241","author":"Guo","year":"2022","journal-title":"Acta Mater."},{"key":"mlstadf374bib32","doi-asserted-by":"publisher","DOI":"10.1002\/srin.202200694","article-title":"Investigation of multistage oxidation behavior of Al4SiC4 powders with aid of back propagation artificial neural network","volume":"94","author":"Guo","year":"2023","journal-title":"Steel Res. Int."},{"key":"mlstadf374bib33","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevMaterials.6.123803","article-title":"Accurate property prediction with interpretable machine learning model for small datasets via transformed atom vector","volume":"6","author":"Chen","year":"2022","journal-title":"Phys. Rev. Mater."},{"key":"mlstadf374bib34","doi-asserted-by":"publisher","first-page":"18069","DOI":"10.1007\/s00521-019-04051-w","article-title":"The importance of interpretability and visualization in machine learning for applications in medicine and health care","volume":"32","author":"Vellido","year":"2020","journal-title":"Neural Comput. Appl."},{"key":"mlstadf374bib35","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1038\/s41524-019-0241-9","article-title":"Identification of advanced spin-driven thermoelectric materials via interpretable machine learning","volume":"5","author":"Iwasaki","year":"2019","journal-title":"npj Comput. Mater."},{"key":"mlstadf374bib36","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1038\/s41524-022-00808-5","article-title":"Data-driven analysis of process, structure and properties of additively manufactured inconel 718 thin walls","volume":"8","author":"Fang","year":"2022","journal-title":"npj Comput. Mater."},{"key":"mlstadf374bib37","doi-asserted-by":"publisher","first-page":"16032","DOI":"10.1021\/acscatal.3c04956","article-title":"Catalyst energy prediction with catberta: unveiling feature exploration strategies through large language models","volume":"13","author":"Ock","year":"2023","journal-title":"ACS Catal."},{"key":"mlstadf374bib38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s42256-024-00930-7","article-title":"Multimodal language and graph learning of adsorption configuration in catalysis","volume":"6","author":"Ock","year":"2024","journal-title":"Nat. Mach. Intell."},{"key":"mlstadf374bib39","doi-asserted-by":"publisher","DOI":"10.1016\/j.commatsci.2024.113256","article-title":"Alloybert: Alloy property prediction with large language models","volume":"244","author":"Chaudhari","year":"2024","journal-title":"Comput. Mater. Sci."},{"article-title":"Regression with large language models for materials and molecular property prediction","year":"2024","author":"Jacobs","key":"mlstadf374bib40"},{"key":"mlstadf374bib41","doi-asserted-by":"publisher","DOI":"10.1016\/j.addlet.2024.100232","article-title":"Amgpt: a large language model for contextual querying in additive manufacturing","volume":"11","author":"Chandrasekhar","year":"2024","journal-title":"Addit. Manuf. Lett."},{"key":"mlstadf374bib42","doi-asserted-by":"publisher","DOI":"10.1063\/1.4812323","article-title":"The materials project: a materials genome approach to accelerating materials innovation","volume":"1","author":"Jain","year":"2013","journal-title":"APL Mater."},{"key":"mlstadf374bib43","doi-asserted-by":"publisher","first-page":"874","DOI":"10.1557\/mrc.2019.94","article-title":"Robocrystallographer: automated crystal structure text descriptions and analysis","volume":"9","author":"Ganose","year":"2019","journal-title":"MRS Commun."},{"key":"mlstadf374bib44","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1038\/s42256-023-00626-4","article-title":"Parameter-efficient fine-tuning of large-scale pre-trained language models","volume":"5","author":"Ding","year":"2023","journal-title":"Nat. Mach. Intell."},{"key":"mlstadf374bib45","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2024.124378","article-title":"Domain-specific large language models for fault diagnosis of heating, ventilation and air conditioning systems by labeled-data-supervised fine-tuning","volume":"377","author":"Zhang","year":"2025","journal-title":"Appl. Energy"},{"article-title":"Lora: Low-rank adaptation of large language models","year":"2021","author":"Hu","key":"mlstadf374bib46"},{"key":"mlstadf374bib47","doi-asserted-by":"publisher","first-page":"6385","DOI":"10.1039\/D4RA00402G","article-title":"Predicting band gaps of ABN3 perovskites: an account from machine learning and first-principle dft studies","volume":"14","author":"Ghosh","year":"2024","journal-title":"RSC Adv."},{"key":"mlstadf374bib48","doi-asserted-by":"publisher","first-page":"3238","DOI":"10.1039\/C8TC05554H","article-title":"Band gap and band alignment prediction of nitride-based semiconductors using machine learning","volume":"7","author":"Huang","year":"2019","journal-title":"J. Mater. Chem."},{"key":"mlstadf374bib49","doi-asserted-by":"publisher","DOI":"10.1016\/j.mssp.2024.108354","article-title":"First-principles study of structural, electronic, mechanical, optical, thermodynamic and thermoelectric properties of ternary ZnSnN2 and ZnMoN2 nitrides","volume":"176","author":"Murtaza","year":"2024","journal-title":"Mater. Sci. Semicond. Process."},{"key":"mlstadf374bib50","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/j.jssc.2013.03.046","article-title":"Synthesis and single-crystal structure determination of the zinc nitride halides Zn2nx (X = Cl, Br, I)","volume":"203","author":"Liu","year":"2013","journal-title":"J. Solid State Chem."},{"key":"mlstadf374bib51","doi-asserted-by":"publisher","first-page":"800","DOI":"10.1021\/ic3019265","article-title":"Carbon-induced ferromagnetism in the antiferromagnetic metallic host material Mn3znn","volume":"52","author":"Sun","year":"2013","journal-title":"Inorg. Chem."},{"key":"mlstadf374bib52","doi-asserted-by":"publisher","DOI":"10.1063\/1.2202236","article-title":"Tetragonal I41\/ amd crystal structure of Li3BN2 from dehydrogenated LI\u2013B\u2013N\u2013H 2006","volume":"99","author":"Pinkerton","year":"2006","journal-title":"J. Appl. Phys."},{"key":"mlstadf374bib53","doi-asserted-by":"publisher","DOI":"10.1063\/1.4971248","article-title":"Strong piezoelectric response in stable TiZnN2, ZrZnN2 and HfZnN2 found by ab initio high-throughput approach","volume":"120","author":"Tholander","year":"2016","journal-title":"J. Appl. Phys."},{"key":"mlstadf374bib54","doi-asserted-by":"publisher","DOI":"10.1016\/j.physe.2024.115973","article-title":"Thermoelectric properties of monolayer and bilayer di boron nitride (di BN)","volume":"162","author":"Marfoua","year":"2024","journal-title":"Physica E"},{"key":"mlstadf374bib55","doi-asserted-by":"crossref","DOI":"10.21203\/rs.3.rs-6373794\/v1","article-title":"Matterchat: a multi-modal llm for material science","author":"Tang","year":"2025"},{"key":"mlstadf374bib56","doi-asserted-by":"publisher","DOI":"10.1016\/j.mtcomm.2022.103962","article-title":"Structural stability, electronic and optical properties of zr-al-n ternary nitrides using the first-principles explorations","volume":"32","author":"Yang","year":"2022","journal-title":"Mater. Today Commun."},{"key":"mlstadf374bib57","doi-asserted-by":"publisher","DOI":"10.1063\/1.4960109","article-title":"Stabilization of orthorhombic phase in single-crystal ZnSnN2 films","volume":"6","author":"Senabulya","year":"2016","journal-title":"AIP Adv."}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adf374","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adf374\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adf374","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adf374\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adf374\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adf374\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adf374\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adf374\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T10:09:21Z","timestamp":1754302161000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adf374"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,4]]},"references-count":57,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,8,4]]},"published-print":{"date-parts":[[2025,9,30]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/adf374","relation":{},"ISSN":["2632-2153"],"issn-type":[{"type":"electronic","value":"2632-2153"}],"subject":[],"published":{"date-parts":[[2025,8,4]]},"assertion":[{"value":"Domain-specific large language model for predicting band gap and formation energy of III-VIIIB and III-IVA nitrides based on fine-tuned GPT-3.5-turbo","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2025 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2025-03-19","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-07-23","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-08-04","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}