{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T20:28:21Z","timestamp":1766435301052,"version":"3.48.0"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032091161"},{"type":"electronic","value":"9783032091178"}],"license":[{"start":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T00:00:00Z","timestamp":1761264000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T00:00:00Z","timestamp":1761264000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-09117-8_3","type":"book-chapter","created":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T11:03:25Z","timestamp":1761217405000},"page":"36-50","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Toppled Realities: Challenges in\u00a0Generation and\u00a0Validation of\u00a0Synthetic Data"],"prefix":"10.1007","author":[{"given":"Percy","family":"Lam","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiwei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lavindra","family":"de Silva","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ioannis","family":"Brilakis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,24]]},"reference":[{"key":"3_CR1","doi-asserted-by":"publisher","unstructured":"Acharya, P., et al.: Using synthetic data generation to probe multi-view stereo networks. In: Proceedings of the IEEE International Conference on Computer Vision. vol. 2021-October, pp. 1583\u20131591. Institute of Electrical and Electronics Engineers Inc. (2021). https:\/\/doi.org\/10.1109\/ICCVW54120.2021.00183","DOI":"10.1109\/ICCVW54120.2021.00183"},{"key":"3_CR2","unstructured":"AgileAssets: How AgileAssets PMS Predicts Pavement Preservation and Deterioration (2020). https:\/\/www.youtube.com\/watch?v=cEZJyxLFAlk"},{"key":"3_CR3","doi-asserted-by":"publisher","first-page":"22051","DOI":"10.1109\/ACCESS.2023.3251988","volume":"11","author":"E Branikas","year":"2023","unstructured":"Branikas, E., Murray, P., West, G.: A novel data augmentation method for improved visual crack detection using generative adversarial networks. IEEE Access 11, 22051\u201322059 (2023). https:\/\/doi.org\/10.1109\/ACCESS.2023.3251988","journal-title":"IEEE Access"},{"key":"3_CR4","unstructured":"Chiang, W.L., et al.: Chatbot arena: an open platform for evaluating LLMs by human preference. In: Proceedings of the 41st International Conference on Machine Learning. ICML\u201924, JMLR.org (2024)"},{"key":"3_CR5","doi-asserted-by":"publisher","unstructured":"Damian, A., Filip, C., Nistor, A., Petrariu, I., Mariuc, C., Stratan, V.: Experimental results on synthetic data generation in unreal engine 5 for real-world object detection. In: 2023 17th International Conference on Engineering of Modern Electric Systems, EMES 2023. Institute of Electrical and Electronics Engineers Inc. (2023). https:\/\/doi.org\/10.1109\/EMES58375.2023.10171761","DOI":"10.1109\/EMES58375.2023.10171761"},{"key":"3_CR6","doi-asserted-by":"publisher","first-page":"97228","DOI":"10.1109\/ACCESS.2021.3094201","volume":"9","author":"C Dewi","year":"2021","unstructured":"Dewi, C., Chen, R.C., Liu, Y.T., Jiang, X., Hartomo, K.D.: Yolo V4 for advanced traffic sign recognition with synthetic training data generated by various GAN. IEEE Access 9, 97228\u201397242 (2021). https:\/\/doi.org\/10.1109\/ACCESS.2021.3094201","journal-title":"IEEE Access"},{"key":"3_CR7","unstructured":"Esser, P., et al.: Scaling rectified flow transformers for high-resolution image synthesis (2024). http:\/\/arxiv.org\/abs\/2403.03206"},{"key":"3_CR8","unstructured":"Google: Gemini 2.0 Flash (2025). https:\/\/console.cloud.google.com\/vertex-ai\/publishers\/google\/model-garden\/gemini-2.0-flash-001?inv=1&invt=Abwxcg"},{"key":"3_CR9","unstructured":"Google: Gemini 2.0 Flash Image Generation (2025). https:\/\/cloud.google.com\/vertex-ai\/generative-ai\/docs\/models\/gemini\/2-0-flash?hl=en&authuser=1#image-generation"},{"key":"3_CR10","unstructured":"Google: Gemini 2.5 Pro Preview (2025). https:\/\/console.cloud.google.com\/vertex-ai\/publishers\/google\/model-garden\/gemini-2.5-pro-preview-03-25"},{"key":"3_CR11","unstructured":"Google Imagen 3 Team: Imagen 3. Tech. rep., Google DeepMind (2024)"},{"key":"3_CR12","unstructured":"Hugging Face: Inpainting. https:\/\/huggingface.co\/docs\/diffusers\/en\/using-diffusers\/inpaint"},{"key":"3_CR13","unstructured":"Kaji\u0107, I., et al.: Evaluating numerical reasoning in text-to-image models. In: Proceedings of the 38th Conference on Neural Information Processing Systems (NeurIPS 2024) (2024). http:\/\/arxiv.org\/abs\/2406.14774"},{"key":"3_CR14","doi-asserted-by":"publisher","unstructured":"Kanaeva, I.A., Ivanova, J.A.: Road pavement crack detection using deep learning with synthetic data. In: IOP Conference Series: Materials Science and Engineering. vol.\u00a01019. IOP Publishing Ltd (2021). https:\/\/doi.org\/10.1088\/1757-899X\/1019\/1\/012036","DOI":"10.1088\/1757-899X\/1019\/1\/012036"},{"key":"3_CR15","doi-asserted-by":"publisher","unstructured":"Karras, T., et al.: Alias-free generative adversarial networks. In: Proceedings of the 35th International Conference on Neural Information Processing Systems, pp. 852\u2013863. Curran Associates Inc., Red Hook, NY, USA (2021). https:\/\/doi.org\/10.48550\/arXiv.2106.12423, https:\/\/nvlabs.github.io\/stylegan3","DOI":"10.48550\/arXiv.2106.12423"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything (2023). https:\/\/segment-anything.com","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"3_CR17","doi-asserted-by":"publisher","unstructured":"Lam, P., Chen, W., De\u00a0Silva, L., Brilakis, I.: Integrating multi-source visual synthetic data for multi road defect detection (2025). https:\/\/doi.org\/10.17863\/CAM.118150","DOI":"10.17863\/CAM.118150"},{"key":"3_CR18","doi-asserted-by":"publisher","unstructured":"Lam, P.H., Chen, W., Brilakis, I.: Analysing the conditions of road assets with a network thinking. In: Kassim, M., Tagliabue, L.C., Amor, R., Sreckovic, M., Chassiakos, A. (eds.) Proceedings of the 2023 European Conference on Computing in Construction and the 40th International CIB W78 Conference. Heraklion, Greece (2023). https:\/\/doi.org\/10.35490\/EC3.2023.169","DOI":"10.35490\/EC3.2023.169"},{"key":"3_CR19","doi-asserted-by":"publisher","unstructured":"Lee, J.H., Shin, J.: How to optimize prompting for large language models in clinical research (2024). https:\/\/doi.org\/10.3348\/kjr.2024.0695","DOI":"10.3348\/kjr.2024.0695"},{"key":"3_CR20","doi-asserted-by":"publisher","unstructured":"Lee, J.G., Hwang, J., Chi, S., Seo, J.: Synthetic image dataset development for vision-based construction equipment detection. J. Comput. Civil Eng. 36(5) (2022). https:\/\/doi.org\/10.1061\/(asce)cp.1943-5487.0001035","DOI":"10.1061\/(asce)cp.1943-5487.0001035"},{"key":"3_CR21","unstructured":"Liu, F., AlDahoul, N., Eady, G., Zaki, Y., Rahwan, T.: Self-reflection makes large language models safer, less biased, and ideologically neutral (2024). http:\/\/arxiv.org\/abs\/2406.10400"},{"key":"3_CR22","doi-asserted-by":"publisher","unstructured":"Mohanty, S., Su, E., Ho, C.C.: Reinforcement learning optimized digital twin based synthetic data generation for defect detection of titanium spacer, p.\u00a06. SPIE-Intl. Soc. Optical Eng. (2023). https:\/\/doi.org\/10.1117\/12.2673529","DOI":"10.1117\/12.2673529"},{"key":"3_CR23","doi-asserted-by":"publisher","unstructured":"Mu, J., Qiu, W., Hager, G., Yuille, A.: Learning from synthetic animals. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12383\u201312392. Seattle, WA, USA (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01240, https:\/\/github.com\/JitengMu\/","DOI":"10.1109\/CVPR42600.2020.01240"},{"key":"3_CR24","unstructured":"National Highways: Connecting the Country: Our Long Term Strategic Plan to 2050. Tech. rep., National Highways, Guildford, UK (2023)"},{"issue":"1","key":"3_CR25","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1109\/MIS.2024.3513992","volume":"40","author":"DE O\u2019Leary","year":"2025","unstructured":"O\u2019Leary, D.E.: Confirmation and specificity biases in large language models: an explorative study. IEEE Intell. Syst. 40(1), 63\u201368 (2025). https:\/\/doi.org\/10.1109\/MIS.2024.3513992","journal-title":"IEEE Intell. Syst."},{"key":"3_CR26","doi-asserted-by":"publisher","unstructured":"Pinaya, W., et al.: Brain imaging generation with latent diffusion models. In: Mukhopadhyay, A., Oksuz, I., Engelhardt, S., Zhu, D., Yuan, Y. (eds.) DGM4MICCAI 2022. Lecture Notes in Computer Science, vol. 13609. Springer Nature Switzerland, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-18576-2, https:\/\/link.springer.com\/10.1007\/978-3-031-18576-2","DOI":"10.1007\/978-3-031-18576-2"},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Razavi, A., Soltangheis, M., Arabzadeh, N., Salamat, S., Zihayat, M., Bagheri, E.: Benchmarking prompt sensitivity in large language models (2025). http:\/\/arxiv.org\/abs\/2502.06065","DOI":"10.1007\/978-3-031-88714-7_29"},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"Song, Y., Chong, N.Y.: S-CycleGAN: semantic segmentation enhanced CT-ultrasound image-to-image translation for robotic ultrasonography (2024). http:\/\/arxiv.org\/abs\/2406.01191","DOI":"10.1109\/CBS61689.2024.10860598"},{"key":"3_CR29","unstructured":"Stability AI: Stable Diffusion 3.5 Medium (2024). https:\/\/huggingface.co\/stabilityai\/stable-diffusion-3.5-medium"},{"key":"3_CR30","unstructured":"The Secretary\u00a0of State\u00a0Science, I., by\u00a0Command\u00a0of His\u00a0Majesty, T.: AI Opportunities Action Plan (2025). https:\/\/www.gov.uk\/government\/publications\/ai-opportunities-action-plan\/ai-opportunities-action-plan"},{"key":"3_CR31","unstructured":"Trimble Inc.: Trimble MX9 Mobile Mapping Solution. Tech. rep., USA (2022). www.trimble.com"},{"key":"3_CR32","unstructured":"Wang, X., et al.: Self-consistency improves chain of thought reasoning in language models. In: ICLR 2023. arXiv preprint (2022). http:\/\/arxiv.org\/abs\/2203.11171"},{"key":"3_CR33","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. In: Proceedings of the 36th International Conference on Neural Information Processing Systems, pp. 24824\u201324837. Curran Associates Inc., New Orleans, LA, USA (2022). http:\/\/arxiv.org\/abs\/2201.11903"},{"key":"3_CR34","doi-asserted-by":"crossref","unstructured":"Wolleb, J., Bieder, F., Sandk\u00fchler, R., Cattin, P.C.: Diffusion models for medical anomaly detection (2022). http:\/\/arxiv.org\/abs\/2203.04306","DOI":"10.1007\/978-3-031-16452-1_4"},{"key":"3_CR35","doi-asserted-by":"publisher","unstructured":"Wong, M.Z., Kunii, K., Baylis, M., Ong, W.H., Kroupa, P., Koller, S.: Synthetic dataset generation for object-to-model deep learning in industrial applications. PeerJ Comput. Sci. 2019(10) (2019). https:\/\/doi.org\/10.7717\/peerj-cs.222","DOI":"10.7717\/peerj-cs.222"},{"key":"3_CR36","doi-asserted-by":"crossref","unstructured":"Xiao, B., et al.: Florence-2: advancing a unified representation for a variety of vision tasks (2023). http:\/\/arxiv.org\/abs\/2311.06242","DOI":"10.1109\/CVPR52733.2024.00461"},{"key":"3_CR37","unstructured":"Yang, C., et al.: Large language models as optimizers. In: ICLR 2024. arXiv preprint (2023). http:\/\/arxiv.org\/abs\/2309.03409"},{"key":"3_CR38","unstructured":"Ye, H., Zhang, J., Liu, S., Han, X., Yang, W.: IP-Adapter: text compatible image prompt adapter for text-to-image diffusion models (2023). http:\/\/arxiv.org\/abs\/2308.06721"},{"key":"3_CR39","unstructured":"Zhang, Y., Yuan, Y., Yao, A.C.C.: Meta Prompting for AI Systems (2023). http:\/\/arxiv.org\/abs\/2311.11482"},{"key":"3_CR40","doi-asserted-by":"publisher","unstructured":"Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision. vol. 2017-October, pp. 2242\u20132251. Institute of Electrical and Electronics Engineers Inc. (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.244","DOI":"10.1109\/ICCV.2017.244"}],"container-title":["Communications in Computer and Information Science","Annotation of Real-World Data for Artificial Intelligence Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-09117-8_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T17:56:55Z","timestamp":1766426215000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-09117-8_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,24]]},"ISBN":["9783032091161","9783032091178"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-09117-8_3","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2025,10,24]]},"assertion":[{"value":"24 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ARDUOUS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Annotation of Real-World Data for Artificial Intelligence Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bologna","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"arduous2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/Arduous.eu","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}