| 1 |
Frozza, A. A., dos Santos Mello, R., and da Costa, F. d. S. (2018). An approach for schema
extraction of json and extended json document collections. In 2018 IEEE International
Conference on Information Reuse and Integration (IRI), pages 356–363. IEEE.
|
|
| 2 |
Bourhis, P., Reutter, J. L., Su´arez, F., and Vrgoˇc, D. (2017). Json: data model, query lan-
guages and schema specification. In Proceedings of the 36th ACM SIGMOD-SIGACT-
SIGAI symposium on principles of database systems, pages 123–135.
|
|
| 3 |
Abdelhedi, F., Brahim, A. A., Rajhi, H., Ferhat, R. T., and Zurfluh, G. (2021). Automatic
extraction of a document-oriented nosql schema. In ICEIS (1), pages 192–199.
|
|
| 4 |
Kellou-Menouer, K., Kardoulakis, N., Troullinou, G., Kedad, Z., Plexousakis, D., and
Kondylakis, H. (2022). A survey on semantic schema discovery. The VLDB Journal,
31(4):675–710.
|
|
| 5 |
Dagdelen, J., Dunn, A., Lee, S., Walker, N., Rosen, A. S., Ceder, G., Persson, K. A.,
and Jain, A. (2024). Structured information extraction from scientific text with large
language models. Nature Communications, 15(1):1418.
|
|
| 6 |
Baazizi, M.-A., Colazzo, D., Ghelli, G., and Sartiani, C. (2019). Parametric schema
inference for massive JSON datasets. The VLDB Journal, 28:497–521.
|
|
| 7 |
Frozza, A. A., dos Santos Mello, R., and da Costa, F. d. S. (2018). An approach for schema
extraction of json and extended json document collections. In 2018 IEEE International
Conference on Information Reuse and Integration (IRI), pages 356–363. IEEE.
|
|
| 8 |
Klessinger, S., Klettke, M., St¨orl, U., and Scherzinger, S. (2023). Extracting JSON sche-
mas with tagged unions. arXiv preprint arXiv:2306.07085.
|
|
| 9 |
Banhara, N., Schreiner, G. A., da Silva Feitosa, S., and Duarte, D. (2024). Enumeration,
tagged unions, tuples, and collections: A novel approach to extracting json schema. In
Simp´osio Brasileiro de Banco de Dados (SBBD), pages 234–246. SBC
|
|
| 10 |
Kellou-Menouer, K., Kardoulakis, N., Troullinou, G., Kedad, Z., Plexousakis, D., and
Kondylakis, H. (2022). A survey on semantic schema discovery. The VLDB Journal,
31(4):675–710.
|
|
| 11 |
Bender, E. M., Gebru, T., McMillan-Major, A., and Shmitchell, S. (2021). On the dangers
of stochastic parrots: Can language models be too big? In Proceedings of the 2021
ACM conference on fairness, accountability, and transparency, pages 610–623.
|
|
| 12 |
Lima, M., Duarte, D., Schreiner, G., Salton, G., and Feitosa, S. (2024). Automated edge-
case discovery in JSON schema validation: A differential testing approach powered by
LLMs. TCC - UFFS
|
|
| 13 |
Klessinger, S., Klettke, M., St¨orl, U., and Scherzinger, S. (2023). Extracting JSON sche-
mas with tagged unions. arXiv preprint arXiv:2306.07085.
|
|
| 14 |
Bouchou, B. and Duarte, D. (2007). Assisting XML schema evolution that preserve vali-
dity. In Brazilian Database Symposium, pages 270–284.
|
|
| 15 |
Maiwald, B., Riedle, B., and Scherzinger, S. (2019). What are real json schemas like? In
International Conference on Conceptual Modeling, pages 95–105. Springer.
|
|
| 16 |
Lima, M., Duarte, D., Schreiner, G., Salton, G., and Feitosa, S. (2024). Automated edge-
case discovery in JSON schema validation: A differential testing approach powered by
LLMs. TCC - UFFS
|
|
| 17 |
Bourhis, P., Reutter, J. L., Su´arez, F., and Vrgoˇc, D. (2017). Json: data model, query lan-
guages and schema specification. In Proceedings of the 36th ACM SIGMOD-SIGACT-
SIGAI symposium on principles of database systems, pages 123–135.
|
|
| 18 |
Mior, M. J. (2024). Large language models for json schema discovery. arXiv preprint
arXiv:2407.03286.
|
|
| 19 |
Maiwald, B., Riedle, B., and Scherzinger, S. (2019). What are real json schemas like? In
International Conference on Conceptual Modeling, pages 95–105. Springer.
|
|
| 20 |
Dagdelen, J., Dunn, A., Lee, S., Walker, N., Rosen, A. S., Ceder, G., Persson, K. A.,
and Jain, A. (2024). Structured information extraction from scientific text with large
language models. Nature Communications, 15(1):1418.
|
|
| 21 |
MongoDB Inc. (2024). Mongodb documentation. https://www.mongodb.com/
docs/manual/. Acesso em: 13 maio 2025.
|
|
| 22 |
Mior, M. J. (2024). Large language models for json schema discovery. arXiv preprint
arXiv:2407.03286.
|
|
| 23 |
Frozza, A. A., dos Santos Mello, R., and da Costa, F. d. S. (2018). An approach for schema
extraction of json and extended json document collections. In 2018 IEEE International
Conference on Information Reuse and Integration (IRI), pages 356–363. IEEE.
|
|
| 24 |
Namba, J. (2021). Enhancing json schema discovery by uncovering hidden data. In
PhD@ VLDB.
|
|
| 25 |
MongoDB Inc. (2024). Mongodb documentation. https://www.mongodb.com/
docs/manual/. Acesso em: 13 maio 2025.
|
|
| 26 |
Kellou-Menouer, K., Kardoulakis, N., Troullinou, G., Kedad, Z., Plexousakis, D., and
Kondylakis, H. (2022). A survey on semantic schema discovery. The VLDB Journal,
31(4):675–710.
|
|
| 27 |
Namba, J. (2021). Enhancing json schema discovery by uncovering hidden data. In
PhD@ VLDB.
|
|
| 28 |
Pezoa, F., Reutter, J. L., Suarez, F., Ugarte, M., and Vrgoˇc, D. (2016). Foundations of
json schema. In Proceedings of the 25th international conference on World Wide Web,
pages 263–273.
|
|
| 29 |
Klessinger, S., Klettke, M., St¨orl, U., and Scherzinger, S. (2023). Extracting JSON sche-
mas with tagged unions. arXiv preprint arXiv:2306.07085.
|
|
| 30 |
Pezoa, F., Reutter, J. L., Suarez, F., Ugarte, M., and Vrgoˇc, D. (2016). Foundations of
json schema. In Proceedings of the 25th international conference on World Wide Web,
pages 263–273.
|
|
| 31 |
Silva, L. O., Silva, P. H., and Silva, F. A. (2025). Leis de escala para text-to-sql: Um
estudo sobre a relac¸ ˜ao entre tamanho e desempenho de modelos de linguagem. In
Simp´osio Brasileiro de Banco de Dados (SBBD), pages 140–153. SBC.
|
|
| 32 |
Lima, M., Duarte, D., Schreiner, G., Salton, G., and Feitosa, S. (2024). Automated edge-
case discovery in JSON schema validation: A differential testing approach powered by
LLMs. TCC - UFFS
|
|
| 33 |
Spoth, W., Kennedy, O., Lu, Y., Hammerschmidt, B., and Liu, Z. H. (2021). Reducing
ambiguity in JSON schema discovery. In Proceedings of the 2021 SIGMOD.
|
|
| 34 |
Silva, L. O., Silva, P. H., and Silva, F. A. (2025). Leis de escala para text-to-sql: Um
estudo sobre a relac¸ ˜ao entre tamanho e desempenho de modelos de linguagem. In
Simp´osio Brasileiro de Banco de Dados (SBBD), pages 140–153. SBC.
|
|
| 35 |
Maiwald, B., Riedle, B., and Scherzinger, S. (2019). What are real json schemas like? In
International Conference on Conceptual Modeling, pages 95–105. Springer.
|
|
| 36 |
Spoth, W., Kennedy, O., Lu, Y., Hammerschmidt, B., and Liu, Z. H. (2021). Reducing
ambiguity in JSON schema discovery. In Proceedings of the 2021 SIGMOD.
|
|
| 37 |
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł.,
and Polosukhin, I. (2017). Attention is all you need. Advances in neural information
processing systems, 30.
|
|
| 38 |
Mior, M. J. (2024). Large language models for json schema discovery. arXiv preprint
arXiv:2407.03286.
|
|
| 39 |
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł.,
and Polosukhin, I. (2017). Attention is all you need. Advances in neural information
processing systems, 30.
|
|
| 40 |
Wang, K. and Liu, H. (1997). Schema discovery for semistructured data. In KDD, vo-
lume 97, pages 271–274.
|
|
| 41 |
MongoDB Inc. (2024). Mongodb documentation. https://www.mongodb.com/
docs/manual/. Acesso em: 13 maio 2025.
|
|
| 42 |
Wang, K. and Liu, H. (1997). Schema discovery for semistructured data. In KDD, vo-
lume 97, pages 271–274.
|
|
| 43 |
Wei, J., Tay, Y., Bommasani, R., Raffel, C., Zoph, B., Borgeaud, S., Yogatama, D.,
Bosma, M., Zhou, D., Metzler, D., Chi, E. H., Hashimoto, T., Vinyals, O., Liang,
P., Dean, J., and Fedus, W. (2022). Emergent abilities of large language models. Tran-
sactions on Machine Learning Research.
|
|
| 44 |
Namba, J. (2021). Enhancing json schema discovery by uncovering hidden data. In
PhD@ VLDB.
|
|
| 45 |
Yun, J., Tak, B., and Han, W.-S. (2024). Recg: Bottom-up json schema discovery using a
repetitive cluster-and-generalize framework. Proc. VLDB Endow., 17(11):3538–3550.
|
|
| 46 |
Wei, J., Tay, Y., Bommasani, R., Raffel, C., Zoph, B., Borgeaud, S., Yogatama, D.,
Bosma, M., Zhou, D., Metzler, D., Chi, E. H., Hashimoto, T., Vinyals, O., Liang,
P., Dean, J., and Fedus, W. (2022). Emergent abilities of large language models. Tran-
sactions on Machine Learning Research.
|
|
| 47 |
Pezoa, F., Reutter, J. L., Suarez, F., Ugarte, M., and Vrgoˇc, D. (2016). Foundations of
json schema. In Proceedings of the 25th international conference on World Wide Web,
pages 263–273.
|
|
| 48 |
Yun, J., Tak, B., and Han, W.-S. (2024). Recg: Bottom-up json schema discovery using a
repetitive cluster-and-generalize framework. Proc. VLDB Endow., 17(11):3538–3550.
|
|
| 49 |
Silva, L. O., Silva, P. H., and Silva, F. A. (2025). Leis de escala para text-to-sql: Um
estudo sobre a relac¸ ˜ao entre tamanho e desempenho de modelos de linguagem. In
Simp´osio Brasileiro de Banco de Dados (SBBD), pages 140–153. SBC.
|
|
| 50 |
Spoth, W., Kennedy, O., Lu, Y., Hammerschmidt, B., and Liu, Z. H. (2021). Reducing
ambiguity in JSON schema discovery. In Proceedings of the 2021 SIGMOD.
|
|
| 51 |
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł.,
and Polosukhin, I. (2017). Attention is all you need. Advances in neural information
processing systems, 30.
|
|
| 52 |
Wang, K. and Liu, H. (1997). Schema discovery for semistructured data. In KDD, vo-
lume 97, pages 271–274.
|
|
| 53 |
Wei, J., Tay, Y., Bommasani, R., Raffel, C., Zoph, B., Borgeaud, S., Yogatama, D.,
Bosma, M., Zhou, D., Metzler, D., Chi, E. H., Hashimoto, T., Vinyals, O., Liang,
P., Dean, J., and Fedus, W. (2022). Emergent abilities of large language models. Tran-
sactions on Machine Learning Research.
|
|
| 54 |
Yun, J., Tak, B., and Han, W.-S. (2024). Recg: Bottom-up json schema discovery using a
repetitive cluster-and-generalize framework. Proc. VLDB Endow., 17(11):3538–3550.
|
|