By research area › Methods & resources › Method / resource

Method / resourceobservedoriginal resultmeasured

Claim · model-written summary

Validation of the yield model for rice gave rRMSEs of 16.12%.

Taxon: riceOryza sativat0
Outcome: rRMSEse0
Value: 16.12%e0

Verbatim

e0
“rRMSEs of 16.97%, 16.12%, and 17.26%”
✓ located verbatim in the source · abstract, characters 931–967

t0
“rice”
✓ located verbatim in the source · title, characters 14–18

Title

A 10 m maize, rice and soybean yield dataset from 2016 to 2021 in Northeast China

Fei Teng; Minglei Wang; Wenjiao Shi; et al. Scientific Data 2026. doi:10.1038/s41597-026-06719-0

Other claims from this paper (9)

Method / resource A yield dataset at 10 m resolution was produced for major maize, rice and soybean regions of Northeast China for 2016 to 2021, with a method that estimates yields without field measurements.
Method / resource Validation of the yield model for maize gave r values of 0.39.
Method / resource Validation of the yield model for maize gave MREs of 12.14%.
Method / resource Validation of the yield model for maize gave rRMSEs of 16.97%.
Method / resource Validation of the yield model for rice gave r values of 0.51.
Method / resource Validation of the yield model for rice gave MREs of 11.96%.
Method / resource Validation of the yield model for soybean gave r values of 0.52.
Method / resource Validation of the yield model for soybean gave MREs of 14.06%.
Method / resource Validation of the yield model for soybean gave rRMSEs of 17.26%.

Method / resourceobservedoriginal resultmeasured

Claim · model-written summary

Validation of the yield model for soybean gave r values of 0.52.

Taxon: soybeanGlycine maxt0
Outcome: r valuese0
Value: 0.52e0

Verbatim

e0
“r values of 0.39, 0.51, and 0.52”
✓ located verbatim in the source · abstract, characters 857–889

t0
“soybean”
✓ located verbatim in the source · title, characters 23–30

Title

A 10 m maize, rice and soybean yield dataset from 2016 to 2021 in Northeast China

Fei Teng; Minglei Wang; Wenjiao Shi; et al. Scientific Data 2026. doi:10.1038/s41597-026-06719-0

Other claims from this paper (9)

Method / resource A yield dataset at 10 m resolution was produced for major maize, rice and soybean regions of Northeast China for 2016 to 2021, with a method that estimates yields without field measurements.
Method / resource Validation of the yield model for maize gave r values of 0.39.
Method / resource Validation of the yield model for maize gave MREs of 12.14%.
Method / resource Validation of the yield model for maize gave rRMSEs of 16.97%.
Method / resource Validation of the yield model for rice gave r values of 0.51.
Method / resource Validation of the yield model for rice gave MREs of 11.96%.
Method / resource Validation of the yield model for rice gave rRMSEs of 16.12%.
Method / resource Validation of the yield model for soybean gave MREs of 14.06%.
Method / resource Validation of the yield model for soybean gave rRMSEs of 17.26%.

Method / resourceobservedoriginal resultmeasured

Claim · model-written summary

Validation of the yield model for soybean gave MREs of 14.06%.

Taxon: soybeanGlycine maxt0
Outcome: MREse0
Value: 14.06%e0

Verbatim

e0
“MREs of 12.14%, 11.96%, and 14.06%”
✓ located verbatim in the source · abstract, characters 891–925

t0
“soybean”
✓ located verbatim in the source · title, characters 23–30

Title

A 10 m maize, rice and soybean yield dataset from 2016 to 2021 in Northeast China

Fei Teng; Minglei Wang; Wenjiao Shi; et al. Scientific Data 2026. doi:10.1038/s41597-026-06719-0

Other claims from this paper (9)

Method / resource A yield dataset at 10 m resolution was produced for major maize, rice and soybean regions of Northeast China for 2016 to 2021, with a method that estimates yields without field measurements.
Method / resource Validation of the yield model for maize gave r values of 0.39.
Method / resource Validation of the yield model for maize gave MREs of 12.14%.
Method / resource Validation of the yield model for maize gave rRMSEs of 16.97%.
Method / resource Validation of the yield model for rice gave r values of 0.51.
Method / resource Validation of the yield model for rice gave MREs of 11.96%.
Method / resource Validation of the yield model for rice gave rRMSEs of 16.12%.
Method / resource Validation of the yield model for soybean gave r values of 0.52.
Method / resource Validation of the yield model for soybean gave rRMSEs of 17.26%.

Method / resourceobservedoriginal resultmeasured

Claim · model-written summary

Validation of the yield model for soybean gave rRMSEs of 17.26%.

Taxon: soybeanGlycine maxt0
Outcome: rRMSEse0
Value: 17.26%e0

Verbatim

e0
“rRMSEs of 16.97%, 16.12%, and 17.26%”
✓ located verbatim in the source · abstract, characters 931–967

t0
“soybean”
✓ located verbatim in the source · title, characters 23–30

Title

A 10 m maize, rice and soybean yield dataset from 2016 to 2021 in Northeast China

Fei Teng; Minglei Wang; Wenjiao Shi; et al. Scientific Data 2026. doi:10.1038/s41597-026-06719-0

Other claims from this paper (9)

Method / resource A yield dataset at 10 m resolution was produced for major maize, rice and soybean regions of Northeast China for 2016 to 2021, with a method that estimates yields without field measurements.
Method / resource Validation of the yield model for maize gave r values of 0.39.
Method / resource Validation of the yield model for maize gave MREs of 12.14%.
Method / resource Validation of the yield model for maize gave rRMSEs of 16.97%.
Method / resource Validation of the yield model for rice gave r values of 0.51.
Method / resource Validation of the yield model for rice gave MREs of 11.96%.
Method / resource Validation of the yield model for rice gave rRMSEs of 16.12%.
Method / resource Validation of the yield model for soybean gave r values of 0.52.
Method / resource Validation of the yield model for soybean gave MREs of 14.06%.

Method / resourceobservedoriginal resultpositivemeasured

Claim · model-written summary

Hybrid soft voting achieved accuracy similar to the strongest individual transfer learning model on the cucumber disease dataset.

Taxon: CucumberCucumis sativuse0
Outcome: accuracye1
Comparator: individual modele1

Verbatim

e0
“the Cucumber dataset with multiple diseases”
✓ located verbatim in the source · abstract, characters 822–865

e1
“Hybrid soft voting evaluated similar accuracy to an individual model that is strong accuracy transfer learning trained model, but inference time is much less than that of these strong models”
✓ located verbatim in the source · abstract, characters 1007–1197

Title

Hybrid ensemble framework combining hard and soft voting of deep transfer learning models

Manisha Dumbre; Hiren Dand IET conference proceedings. 2026. doi:10.1049/icp.2025.4754

Other claims from this paper (2)

Method / resource Hybrid soft voting had much shorter inference time than the strong individual transfer learning models.
Recommendation The authors conclude that hybrid soft voting is useful for fast prediction of diseases.

Method / resourceobservedoriginal resultpositivemeasured

Claim · model-written summary

Hybrid soft voting had much shorter inference time than the strong individual transfer learning models.

Taxon: CucumberCucumis sativuse0
Outcome: inference timee1
Direction: much lesse1
Comparator: individual modele1

Verbatim

e0
“the Cucumber dataset with multiple diseases”
✓ located verbatim in the source · abstract, characters 822–865

e1
“Hybrid soft voting evaluated similar accuracy to an individual model that is strong accuracy transfer learning trained model, but inference time is much less than that of these strong models”
✓ located verbatim in the source · abstract, characters 1007–1197

Title

Hybrid ensemble framework combining hard and soft voting of deep transfer learning models

Manisha Dumbre; Hiren Dand IET conference proceedings. 2026. doi:10.1049/icp.2025.4754

Other claims from this paper (2)

Method / resourceobservedoriginal resultpositivemeasured

Claim · model-written summary

Among pre-trained and custom CNN architectures tested for orange disease classification, the custom scratch-built CNN achieved the best results.

Taxon: oranget0
Outcome: best resultse0
Direction: beste0
Comparator: pre-trainede0

Verbatim

t0
“orange fruit diseases”
✓ located verbatim in the source · title, characters 28–49

e0
“both pre-trained and custom CNN architectures were tested, with the custom, scratch-built CNN achieving the best results”
✓ located verbatim in the source · abstract, characters 1135–1255

Title

Automatic classification of orange fruit diseases using deep neural network model

Silvia Sifath; Sajeeb Saha; Sohely Jahan Journal of Agriculture and Food Research 2026. doi:10.1016/j.jafr.2026.102712

Other claims from this paper (1)

Method / resource The proposed CNN model reached an accuracy of 97% in classifying orange fruit diseases.

Method / resourceobservedoriginal resultpositivemeasured

Claim · model-written summary

The proposed CNN model reached an accuracy of 97% in classifying orange fruit diseases.

Taxon: oranget0
Outcome: accuracye0
Value: 97%e0

Verbatim

t0
“orange fruit diseases”
✓ located verbatim in the source · title, characters 28–49

e0
“The proposed model reached an accuracy of 97%”
✓ located verbatim in the source · abstract, characters 1257–1302

Title

Automatic classification of orange fruit diseases using deep neural network model

Silvia Sifath; Sajeeb Saha; Sohely Jahan Journal of Agriculture and Food Research 2026. doi:10.1016/j.jafr.2026.102712

Other claims from this paper (1)

Method / resource Among pre-trained and custom CNN architectures tested for orange disease classification, the custom scratch-built CNN achieved the best results.

Method / resourceobservedoriginal resultpositivemeasured

Claim · model-written summary

GINGER performs on a similar level to human annotators in estimating fine root production while substantially reducing data analysis time.

Outcome: performancee0
Comparator: human annotatorse0

Verbatim

e0
“It exhibits performance on a similar level to that of human annotators while substantially reducing the time required for the data analysis”
✓ located verbatim in the source · abstract, characters 685–824

Title

Automated quantification of fine root production from minirhizotron image time series

Alexander Gillert; Patrick Möhl; Bo Peters; et al. Methods in Ecology and Evolution 2026. doi:10.1111/2041-210x.70257

Other claims from this paper (2)

Method / resourceobservedoriginal resultpositivemeasured

Claim · model-written summary

End to end, GINGER reduced the required human workload from several thousand to less than 40 work hours.

Outcome: required human workloade2
Direction: reducede2
Value: less than 40 work hourse2
Qualifier: from several thousande2

Verbatim

e2
“GINGER reduced the required human workload from several thousand to less than 40 work hours”
✓ located verbatim in the source · abstract, characters 1161–1252

Title

Automated quantification of fine root production from minirhizotron image time series

Alexander Gillert; Patrick Möhl; Bo Peters; et al. Methods in Ecology and Evolution 2026. doi:10.1111/2041-210x.70257

Other claims from this paper (2)

Method / resource 684,532 claims

684,532 claims