{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T19:03:44Z","timestamp":1776279824397,"version":"3.50.1"},"reference-count":74,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T00:00:00Z","timestamp":1755734400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T00:00:00Z","timestamp":1755734400000},"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":"<jats:title>Abstract<\/jats:title>\n               <jats:p>We present CrysMTM, a large-scale, multimodal dataset designed to benchmark temperature- and phase-sensitive machine learning models for crystalline materials. The dataset comprises approximately 30\u2009000 atomistic samples covering the three primary polymorphs of titanium dioxide\u2013anatase, brookite, and rutile\u2013each evaluated across a temperature spectrum ranging from cryogenic to ambient and elevated conditions. Each data entry integrates three complementary modalities: (1) three-dimensional atomic coordinates, (2) RGBA molecular visualizations, and (3) structured textual metadata encompassing geometric descriptors, local bonding environments, and phase transformation parameters. This multimodal structure enables both supervised and self-supervised learning across graph-based, image-based, and language-based architectures. CrysMTM supports rigorous evaluation of model robustness under thermal perturbations and crystallographic phase transitions. Baseline benchmarking across 18 models\u2013including graph neural networks (GNNs), convolutional neural networks, and foundation models\u2013reveals significant property-specific challenges. For example, bandgap predictions exhibit errors exceeding 25%, while volumetric expansion and atomic displacement estimations frequently deviate by more than 100%. Even state-of-the-art GNNs, which achieve an average in-distribution (ID) mean absolute percentage error of approximately 20%, show a threefold increase under out-of-distribution (OOD) thermal conditions. In contrast, a few-shot multimodal large language model reduces global prediction error from 96% to 23% and narrows the performance gap between ID and OOD cases to just four percentage points. These results highlight both the selective difficulty posed by temperature-sensitive geometric targets and the considerable room for innovation in model design. All dataset files, model implementations, and pretrained checkpoints are available at <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/KurbanIntelligenceLab\/CrysMTM\">https:\/\/github.com\/KurbanIntelligenceLab\/CrysMTM<\/jats:ext-link>.<\/jats:p>","DOI":"10.1088\/2632-2153\/adf9bc","type":"journal-article","created":{"date-parts":[[2025,8,8]],"date-time":"2025-08-08T22:53:47Z","timestamp":1754693627000},"page":"030603","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["CrysMTM: a multiphase, temperature-resolved, multimodal dataset for crystalline materials"],"prefix":"10.1088","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1458-302X","authenticated-orcid":true,"given":"Can","family":"Polat","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Erchin","family":"Serpedin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7263-0234","authenticated-orcid":true,"given":"Mustafa","family":"Kurban","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3142-2866","authenticated-orcid":false,"given":"Hasan","family":"Kurban","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2025,8,21]]},"reference":[{"key":"mlstadf9bcbib1","author":"Rohrer","year":"2001"},{"key":"mlstadf9bcbib2","author":"Yeomans","year":"1992"},{"key":"mlstadf9bcbib3","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1016\/j.cemconres.2011.10.007","article-title":"Chemical and mechanical stability of sodium sulfate activated slag after exposure to elevated temperature","volume":"42","author":"Rashad","year":"2012","journal-title":"Cement Concr. Res."},{"key":"mlstadf9bcbib4","doi-asserted-by":"publisher","first-page":"8226","DOI":"10.1039\/C4CS00210E","article-title":"Understanding catalysis","volume":"43","author":"Roduner","year":"2014","journal-title":"Chem. Soc. Rev."},{"key":"mlstadf9bcbib5","doi-asserted-by":"publisher","first-page":"3400","DOI":"10.1038\/s41467-018-05774-5","article-title":"High entropy oxides for reversible energy storage","volume":"9","author":"Sarkar","year":"2018","journal-title":"Nat. Commun."},{"key":"mlstadf9bcbib6","doi-asserted-by":"publisher","DOI":"10.1063\/5.0012330","article-title":"Temperature dependence on bandgap of semiconductor photocatalysts","volume":"152","author":"Cho","year":"2020","journal-title":"J. Chem. Phys."},{"key":"mlstadf9bcbib7","doi-asserted-by":"publisher","first-page":"5089","DOI":"10.1039\/B821991E","article-title":"Photoelectrocatalytic materials for environmental applications","volume":"19","author":"Zhang","year":"2009","journal-title":"J. Mater. Chem."},{"key":"mlstadf9bcbib8","doi-asserted-by":"publisher","first-page":"855","DOI":"10.1007\/s10853-010-5113-0","article-title":"Review of the anatase to rutile phase transformation","volume":"46","author":"Hanaor","year":"2011","journal-title":"J. Mater. Sci."},{"key":"mlstadf9bcbib9","doi-asserted-by":"publisher","DOI":"10.1016\/j.commatsci.2020.109843","article-title":"Tailoring the structural properties and electronic structure of anatase, brookite and rutile phase TiO2 nanoparticles: (DFTB) calculations","volume":"183","author":"Kurban","year":"2020","journal-title":"Comput. Mater. Sci."},{"key":"mlstadf9bcbib10","doi-asserted-by":"publisher","first-page":"21114","DOI":"10.1016\/j.ijhydene.2018.09.051","article-title":"Resistive-type hydrogen gas sensor based on TiO2: a review","volume":"43","author":"Li","year":"2018","journal-title":"Int. J. Hydrog. Energy"},{"key":"mlstadf9bcbib11","doi-asserted-by":"publisher","DOI":"10.1002\/aenm.202003303","article-title":"Visible-light responsive TiO2-based materials for efficient solar energy utilization","volume":"11","author":"Zhang","year":"2021","journal-title":"Adv. Energy Mater."},{"key":"mlstadf9bcbib12","doi-asserted-by":"publisher","first-page":"12697","DOI":"10.1039\/D0CP02513E","article-title":"Predicting the phase diagram of titanium dioxide with random search and pattern recognition","volume":"22","author":"Reinhardt","year":"2020","journal-title":"Phys. Chem. Chem. Phys."},{"key":"mlstadf9bcbib13","doi-asserted-by":"publisher","DOI":"10.1016\/j.commatsci.2024.113248","article-title":"Enhancing the electronic properties of TiO2 nanoparticles through carbon doping: an integrated DFTB and computer vision approach","volume":"244","author":"Kurban","year":"2024","journal-title":"Comput. Mater. Sci."},{"key":"mlstadf9bcbib14","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1038\/s41524-023-01110-8","article-title":"Exploring anharmonic lattice dynamics and dielectric relations in niobate perovskites from first-principles self-consistent phonon calculations","volume":"9","author":"Kim","year":"2023","journal-title":"npj Comput. Mater."},{"key":"mlstadf9bcbib15","doi-asserted-by":"publisher","DOI":"10.1007\/s11433-021-1748-7","article-title":"Phonon anharmonicity: a pertinent review of recent progress and perspective","volume":"64","author":"Wei","year":"2021","journal-title":"Sci. China Phys. Mech. Astron."},{"key":"mlstadf9bcbib16","doi-asserted-by":"publisher","first-page":"674","DOI":"10.1002\/jrs.6530","article-title":"Investigation of temperature-dependent phonon dynamics of BixRe1\u2212xSe2 (x = 0.0, 0.1, 0.5) via Raman spectroscopy","volume":"54","author":"Patel","year":"2023","journal-title":"J. Raman Spectrosc."},{"key":"mlstadf9bcbib17","doi-asserted-by":"publisher","first-page":"2864","DOI":"10.1021\/ci300415d","article-title":"Enumeration of 166 billion organic small molecules in the chemical Universe database GDB-17","volume":"52","author":"Ruddigkeit","year":"2012","journal-title":"J. Chem. Inf. Model."},{"key":"mlstadf9bcbib18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2014.22","article-title":"Quantum chemistry structures and properties of 134 kilo molecules","volume":"1","author":"Ramakrishnan","year":"2014","journal-title":"Sci. Data"},{"key":"mlstadf9bcbib19","doi-asserted-by":"publisher","first-page":"138","DOI":"10.1038\/s41524-020-00406-3","article-title":"Benchmarking materials property prediction methods: the matbench test set and automatminer reference algorithm","volume":"6","author":"Dunn","year":"2020","journal-title":"npj Comput. Mater."},{"key":"mlstadf9bcbib20","doi-asserted-by":"publisher","first-page":"6059","DOI":"10.1021\/acscatal.0c04525","article-title":"Open catalyst 2020 (OC20) dataset and community challenges","volume":"11","author":"Chanussot","year":"2021","journal-title":"ACS Catal."},{"key":"mlstadf9bcbib21","doi-asserted-by":"publisher","first-page":"3066","DOI":"10.1021\/acscatal.2c05426","article-title":"The open catalyst 2022 (OC20) dataset and challenges for oxide electrocatalysts","volume":"13","author":"Tran","year":"2023","journal-title":"ACS Catal."},{"key":"mlstadf9bcbib22","doi-asserted-by":"publisher","first-page":"7260","DOI":"10.1103\/PhysRevB.58.7260","article-title":"Self-consistent-charge density-functional tight-binding method for simulations of complex materials properties","volume":"58","author":"Elstner","year":"1998","journal-title":"Phys. Rev. B"},{"key":"mlstadf9bcbib23","doi-asserted-by":"publisher","DOI":"10.1063\/1.5143190","article-title":"Dftb+, a software package for efficient approximate density functional theory based atomistic simulations","volume":"152","author":"Hourahine","year":"2020","journal-title":"J. Chem. Phys."},{"key":"mlstadf9bcbib24","doi-asserted-by":"publisher","first-page":"B864","DOI":"10.1103\/PhysRev.136.B864","article-title":"Inhomogeneous electron gas","volume":"136","author":"Hohenberg","year":"1964","journal-title":"Phys. Rev."},{"key":"mlstadf9bcbib25","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":"mlstadf9bcbib26","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1021\/ct300849w","article-title":"DFTB3: extension of the self-consistent-charge density-functional tight-binding method (SCC-DFTB)","volume":"9","author":"Gaus","year":"2013","journal-title":"J. Chem. Theory Comput."},{"key":"mlstadf9bcbib27","doi-asserted-by":"publisher","first-page":"931","DOI":"10.1021\/ct100684s","article-title":"Parametrization and benchmark of DFTB3 for organic molecules","volume":"7","author":"Gaus","year":"2011","journal-title":"J. Chem. Theory Comput."},{"key":"mlstadf9bcbib28","doi-asserted-by":"publisher","first-page":"5239","DOI":"10.1021\/acs.jctc.1c00399","article-title":"Using DFTB to model photocatalytic anatase\u2013rutile TiO2 nanocrystalline interfaces and their band alignment","volume":"17","author":"Gupta","year":"2021","journal-title":"J. Chem. Theory Comput."},{"key":"mlstadf9bcbib29","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.78.214106","article-title":"Atomic structure of nanometer-sized amorphous TiO2","volume":"78","author":"Zhang","year":"2008","journal-title":"Phys. Rev. B"},{"key":"mlstadf9bcbib30","doi-asserted-by":"publisher","DOI":"10.1088\/0957-4484\/19\/14\/145605","article-title":"Phase-pure TiO2 nanoparticles: anatase, brookite and rutile","volume":"19","author":"Reyes-Coronado","year":"2008","journal-title":"Nanotechnology"},{"key":"mlstadf9bcbib31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-018-27135-4","article-title":"Enhanced photocatalytic activity of se-doped TiO2 under visible light irradiation","volume":"8","author":"Xie","year":"2018","journal-title":"Sci. Rep."},{"key":"mlstadf9bcbib32","doi-asserted-by":"publisher","first-page":"6533","DOI":"10.1021\/nl503131s","article-title":"Tio2 anatase with a bandgap in the visible region","volume":"14","author":"Dette","year":"2014","journal-title":"Nano Lett."},{"key":"mlstadf9bcbib33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/srep04043","article-title":"Microbial fuel cell assisted band gap narrowed TiO2 for visible light-induced photocatalytic activities and power generation","volume":"8","author":"Khan","year":"2018","journal-title":"Sci. Rep."},{"key":"mlstadf9bcbib34","doi-asserted-by":"publisher","DOI":"10.7567\/APEX.6.121101","article-title":"Temperature-dependent optical properties of titanium oxide thin films studied by spectroscopic ellipsometry","volume":"6","author":"Zhang","year":"2013","journal-title":"Appl. Phys. Express"},{"key":"mlstadf9bcbib35","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1016\/j.matlet.2017.12.120","article-title":"Temperature-dependent phase transformation of TiO2 nanoparticles synthesized by sol-gel method","volume":"215","author":"Dubey","year":"2018","journal-title":"Mater. Lett."},{"key":"mlstadf9bcbib36","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1016\/j.materresbull.2018.04.021","article-title":"The role of hydrothermal conditions in determining 1d TiO2 nanomaterials bandgap energies and crystal phases","volume":"105","author":"Peng","year":"2018","journal-title":"Mater. Res. Bull."},{"key":"mlstadf9bcbib37","doi-asserted-by":"publisher","first-page":"8706","DOI":"10.1021\/ja00072a025","article-title":"Synthesis and characterization of nearly monodisperse CDE (e = sulfur, selenium, tellurium) semiconductor nanocrystallites","volume":"115","author":"Murray","year":"1993","journal-title":"J. Am. Chem. Soc."},{"key":"mlstadf9bcbib38","doi-asserted-by":"publisher","DOI":"10.1063\/1.4812323","article-title":"Commentary: the materials project: a materials genome approach to accelerating materials innovation","volume":"1","author":"Jain","year":"2013","journal-title":"APL Mater."},{"key":"mlstadf9bcbib39","doi-asserted-by":"publisher","first-page":"4043","DOI":"10.1038\/srep04043","article-title":"Why is anatase a better photocatalyst than rutile?-model studies on epitaxial TiO2 films","volume":"4","author":"Luttrell","year":"2014","journal-title":"Sci. Rep."},{"key":"mlstadf9bcbib40","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1016\/j.cclet.2010.11.017","article-title":"Nano-tube TiO2 as a new catalyst for eco-friendly synthesis of imines in sunlight","volume":"22","author":"Hosseini-Sarvari","year":"2011","journal-title":"Chin. Chem. Lett."},{"key":"mlstadf9bcbib41","doi-asserted-by":"publisher","first-page":"2891","DOI":"10.1021\/cr0500535","article-title":"Titanium dioxide nanomaterials: synthesis, properties, modifications and applications","volume":"107","author":"Chen","year":"2007","journal-title":"Chem. Rev."},{"key":"mlstadf9bcbib42","doi-asserted-by":"publisher","first-page":"758","DOI":"10.3139\/146.110337","article-title":"Adsorption of nucleotides on the rutile (110) surface","volume":"101","author":"Gemming","year":"2010","journal-title":"Int. J Mater. Res."},{"key":"mlstadf9bcbib43","doi-asserted-by":"publisher","first-page":"7424","DOI":"10.1021\/acscatal.5b01562","article-title":"On oxygen activation at rutile-and anatase- TiO2","volume":"5","author":"Buchalska","year":"2015","journal-title":"ACS Catal."},{"key":"mlstadf9bcbib44","doi-asserted-by":"publisher","first-page":"192","DOI":"10.1016\/j.jallcom.2015.01.085","article-title":"Phase transitions and mechanical stability of TiO2 polymorphs under high pressure","volume":"631","author":"Liu","year":"2015","journal-title":"J. Alloys Compd."},{"key":"mlstadf9bcbib45","doi-asserted-by":"publisher","first-page":"8732","DOI":"10.1021\/ja902302h","article-title":"970 million druglike small molecules for virtual screening in the chemical Universe database GDB-13","volume":"131","author":"Blum","year":"2009","journal-title":"J. Am. Chem. Soc."},{"key":"mlstadf9bcbib46","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.108.058301","article-title":"Fast and accurate modeling of molecular atomization energies with machine learning","volume":"108","author":"Rupp","year":"2012","journal-title":"Phys. Rev. Lett."},{"key":"mlstadf9bcbib47","doi-asserted-by":"publisher","first-page":"eadf0873","DOI":"10.1126\/sciadv.adf0873","article-title":"Accurate global machine learning force fields for molecules with hundreds of atoms","volume":"9","author":"Chmiela","year":"2023","journal-title":"Sci. Adv."},{"key":"mlstadf9bcbib48","doi-asserted-by":"publisher","first-page":"D1516","DOI":"10.1093\/nar\/gkae1059","article-title":"Pubchem 2025 update","volume":"53","author":"Kim","year":"2025","journal-title":"Nucl. Acids Res."},{"key":"mlstadf9bcbib49","doi-asserted-by":"publisher","first-page":"25853","DOI":"10.1039\/D2CP03966D","article-title":"nablaDFT: large-scale conformational energy and Hamiltonian prediction benchmark and dataset","volume":"24","author":"Khrabrov","year":"2022","journal-title":"Phys. Chem. Chem. Phys."},{"key":"mlstadf9bcbib50","article-title":"QH9: a quantum Hamiltonian prediction benchmark for QM9 molecules","volume":"vol 36","author":"Yu","year":"2024"},{"key":"mlstadf9bcbib51","first-page":"pp 2507","article-title":"Learn to explain: multimodal reasoning via thought chains for science question answering","volume":"vol 35","author":"Lu","year":"2022"},{"key":"mlstadf9bcbib52","article-title":"Scibench: evaluating college-level scientific problem-solving abilities of large language models","author":"Wang","year":"2023"},{"key":"mlstadf9bcbib53","first-page":"pp 9556","article-title":"MMMU: a massive multi-discipline multimodal understanding and reasoning benchmark for expert AGI","author":"Yue","year":"2024"},{"key":"mlstadf9bcbib54","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2024.acl-long.211","article-title":"Olympiadbench: a challenging benchmark for promoting AGI with Olympiad-level bilingual multimodal scientific problems","author":"He","year":"2024"},{"key":"mlstadf9bcbib55","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1039\/C7SC02664A","article-title":"Moleculenet: a benchmark for molecular machine learning","volume":"9","author":"Wu","year":"2018","journal-title":"Chem. Sci."},{"key":"mlstadf9bcbib56","article-title":"ChemLit-QA: a human evaluated dataset for chemistry rag tasks","author":"Wellawatte","year":"2024"},{"key":"mlstadf9bcbib57","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2024.findings-emnlp.192","article-title":"Honeycomb: a flexible llm-based agent system for materials science","author":"Zhang","year":"2024"},{"key":"mlstadf9bcbib58","doi-asserted-by":"publisher","first-page":"5730","DOI":"10.1021\/jp8110343","article-title":"Adsorption of phosphonic acid at the TiO2 anatase (101) and rutile (110) surface","volume":"113","author":"Luschtinetz","year":"2009","journal-title":"J. Phys. Chem. C"},{"key":"mlstadf9bcbib59","first-page":"1102","article-title":"Adsorption of nucleotides on the rutile (110) surface","volume":"98","author":"Enyashin","year":"2007","journal-title":"Int. J. Mater Res."},{"key":"mlstadf9bcbib60","doi-asserted-by":"publisher","first-page":"1584","DOI":"10.1007\/s11051-013-1584-7","article-title":"Influence of size and temperature on the phase stability and thermophysical properties of anatase TiO2 nanoparticles: molecular dynamics simulation","volume":"15","author":"Okeke","year":"2013","journal-title":"J. Nanopart. Res."},{"key":"mlstadf9bcbib61","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1016\/j.ces.2016.02.035","article-title":"Effects of heat treatment on the atomic structure and surface energy of rutile and anatase TiO2 nanoparticles under vacuum and water environments","volume":"146","author":"Okeke","year":"2016","journal-title":"Chem. Eng. Sci."},{"key":"mlstadf9bcbib62","doi-asserted-by":"publisher","first-page":"729","DOI":"10.1134\/S1560354715060088","article-title":"On geodesics of the rotation group so (3)","volume":"20","author":"Novelia","year":"2015","journal-title":"Regular Chaotic Dyn."},{"key":"mlstadf9bcbib63","article-title":"Schnet: a continuous-filter convolutional neural network for modeling quantum interactions","volume":"vol 30","author":"Sch\u00fctt","year":"2017"},{"key":"mlstadf9bcbib64","first-page":"pp 9323","article-title":"E (n) equivariant graph neural networks","author":"Garcia Satorras","year":"2021"},{"key":"mlstadf9bcbib65","first-page":"pp 9013","article-title":"FAENet: frame averaging equivariant GNN for materials modeling","author":"Duval","year":"2023"},{"key":"mlstadf9bcbib66","article-title":"Gotennet: rethinking efficient 3D equivariant graph neural networks","author":"Aykent","year":"2025"},{"key":"mlstadf9bcbib67","first-page":"pp 770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"mlstadf9bcbib68","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"mlstadf9bcbib69","first-page":"pp 8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"mlstadf9bcbib70","article-title":"Visnet: an equivariant geometry-enhanced graph neural network with vector-scalar interactive message passing for molecules","author":"Wang","year":"2022"},{"key":"mlstadf9bcbib71","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ad9708","article-title":"Multimodal neural network-based predictive modeling of nanoparticle properties from pure compounds","volume":"5","author":"Polat","year":"2024","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstadf9bcbib72","article-title":"Fast graph representation learning with pytorch geometric","author":"Fey","year":"2019"},{"key":"mlstadf9bcbib73","article-title":"Pytorch: an imperative style, high-performance deep learning library","author":"Paszke","year":"2019"},{"key":"mlstadf9bcbib74","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2014"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adf9bc","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adf9bc\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adf9bc","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adf9bc\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adf9bc\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adf9bc\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adf9bc\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adf9bc\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T12:42:33Z","timestamp":1755780153000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adf9bc"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,21]]},"references-count":74,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,8,21]]},"published-print":{"date-parts":[[2025,9,30]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/adf9bc","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,21]]},"assertion":[{"value":"CrysMTM: a multiphase, temperature-resolved, multimodal dataset for crystalline materials","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":"2025-04-18","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-08-08","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-08-21","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}