FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4378966181> ?p ?o ?g. }

• W4378966181 endingPage "129680" @default.
• W4378966181 startingPage "129680" @default.
• W4378966181 abstract "The knowledge of scientific articles within Generative Pre-trained Transformers (GPT) is not exhaustive due to factors such as data coverage, freshness, complexity, paywalls, and context. While it can provide general information on scientific topics, it may struggle with specialized terminology, recent research, and nuanced understanding. As a result, relying on GPT as a scientific assistant tool may not be ideal. Instead, it is important to consult specialized resources and databases for a comprehensive understanding of specific scientific domains and access to the latest research. A custom data driven GPT can enhance its performance as a scientific assistant tool by improving domain knowledge, providing up-to-date information, reducing ambiguity and errors, performing customized tasks, and offering enhanced search capabilities. This work demonstrates and evaluates the use of such GPT models using a small selection of peer reviewed published thermal spray articles as the reference domain knowledge. The specific domain knowledge model works exceptionally well outperforming the general state-of-the-art large language models." @default.
• W4378966181 created "2023-06-02" @default.
• W4378966181 creator A5017546542 @default.
• W4378966181 date "2023-08-01" @default.
• W4378966181 modified "2023-09-25" @default.
• W4378966181 title "Generative pre-trained transformers (GPT) for surface engineering" @default.
• W4378966181 cites W1464907442 @default.
• W4378966181 cites W1982959744 @default.
• W4378966181 cites W1984553047 @default.
• W4378966181 cites W1987075977 @default.
• W4378966181 cites W1992268138 @default.
• W4378966181 cites W1999560808 @default.
• W4378966181 cites W2042846171 @default.
• W4378966181 cites W2049019780 @default.
• W4378966181 cites W2064675550 @default.
• W4378966181 cites W2064882916 @default.
• W4378966181 cites W2081069198 @default.
• W4378966181 cites W2085463815 @default.
• W4378966181 cites W2087987029 @default.
• W4378966181 cites W2089040375 @default.
• W4378966181 cites W2111016241 @default.
• W4378966181 cites W2128665411 @default.
• W4378966181 cites W2130104383 @default.
• W4378966181 cites W2144729626 @default.
• W4378966181 cites W2161863134 @default.
• W4378966181 cites W2162879392 @default.
• W4378966181 cites W2164715575 @default.
• W4378966181 cites W2265439010 @default.
• W4378966181 cites W2463989947 @default.
• W4378966181 cites W2569726794 @default.
• W4378966181 cites W2756347308 @default.
• W4378966181 cites W2802500265 @default.
• W4378966181 cites W2883435820 @default.
• W4378966181 cites W2914649143 @default.
• W4378966181 cites W2945274002 @default.
• W4378966181 cites W2995359970 @default.
• W4378966181 cites W3005828927 @default.
• W4378966181 cites W3039324719 @default.
• W4378966181 cites W3095319910 @default.
• W4378966181 cites W3127427413 @default.
• W4378966181 cites W3208291105 @default.
• W4378966181 cites W3213412325 @default.
• W4378966181 cites W4210766236 @default.
• W4378966181 cites W4226317096 @default.
• W4378966181 cites W4280526255 @default.
• W4378966181 cites W4282915864 @default.
• W4378966181 cites W4283583653 @default.
• W4378966181 cites W4309477536 @default.
• W4378966181 cites W4310138326 @default.
• W4378966181 cites W4318499068 @default.
• W4378966181 cites W4320495408 @default.
• W4378966181 doi "https://doi.org/10.1016/j.surfcoat.2023.129680" @default.
• W4378966181 hasPublicationYear "2023" @default.
• W4378966181 type Work @default.
• W4378966181 citedByCount "1" @default.
• W4378966181 countsByYear W43789661812023 @default.
• W4378966181 crossrefType "journal-article" @default.
• W4378966181 hasAuthorship W4378966181A5017546542 @default.
• W4378966181 hasConcept C119599485 @default.
• W4378966181 hasConcept C127413603 @default.
• W4378966181 hasConcept C134306372 @default.
• W4378966181 hasConcept C138885662 @default.
• W4378966181 hasConcept C151730666 @default.
• W4378966181 hasConcept C154945302 @default.
• W4378966181 hasConcept C165801399 @default.
• W4378966181 hasConcept C199360897 @default.
• W4378966181 hasConcept C207685749 @default.
• W4378966181 hasConcept C2522767166 @default.
• W4378966181 hasConcept C2780522230 @default.
• W4378966181 hasConcept C2781083858 @default.
• W4378966181 hasConcept C33923547 @default.
• W4378966181 hasConcept C36503486 @default.
• W4378966181 hasConcept C39890363 @default.
• W4378966181 hasConcept C41008148 @default.
• W4378966181 hasConcept C41895202 @default.
• W4378966181 hasConcept C547195049 @default.
• W4378966181 hasConcept C66322947 @default.
• W4378966181 hasConcept C86803240 @default.
• W4378966181 hasConceptScore W4378966181C119599485 @default.
• W4378966181 hasConceptScore W4378966181C127413603 @default.
• W4378966181 hasConceptScore W4378966181C134306372 @default.
• W4378966181 hasConceptScore W4378966181C138885662 @default.
• W4378966181 hasConceptScore W4378966181C151730666 @default.
• W4378966181 hasConceptScore W4378966181C154945302 @default.
• W4378966181 hasConceptScore W4378966181C165801399 @default.
• W4378966181 hasConceptScore W4378966181C199360897 @default.
• W4378966181 hasConceptScore W4378966181C207685749 @default.
• W4378966181 hasConceptScore W4378966181C2522767166 @default.
• W4378966181 hasConceptScore W4378966181C2780522230 @default.
• W4378966181 hasConceptScore W4378966181C2781083858 @default.
• W4378966181 hasConceptScore W4378966181C33923547 @default.
• W4378966181 hasConceptScore W4378966181C36503486 @default.
• W4378966181 hasConceptScore W4378966181C39890363 @default.
• W4378966181 hasConceptScore W4378966181C41008148 @default.
• W4378966181 hasConceptScore W4378966181C41895202 @default.
• W4378966181 hasConceptScore W4378966181C547195049 @default.
• W4378966181 hasConceptScore W4378966181C66322947 @default.
• W4378966181 hasConceptScore W4378966181C86803240 @default.

• next