Software and data underlying the publication: "Position: Stop Making Unscientific AGI Performance Claims"
DOI:10.4121/d427d182-4bb0-4972-980c-adcb28f430b6.v1
The DOI displayed above is for this specific version of this dataset, which is currently the latest. Newer versions may be published in the future.
For a link that will always point to the latest version, please use
DOI: 10.4121/d427d182-4bb0-4972-980c-adcb28f430b6
DOI: 10.4121/d427d182-4bb0-4972-980c-adcb28f430b6
Datacite citation style
Altmeyer, Patrick; Liem, C.C.S. (Cynthia); Demetriou, Andrew; Bartlett, Antony (2025): Software and data underlying the publication: "Position: Stop Making Unscientific AGI Performance Claims". Version 1. 4TU.ResearchData. software. https://doi.org/10.4121/d427d182-4bb0-4972-980c-adcb28f430b6.v1
Other citation styles (APA, Harvard, MLA, Vancouver, Chicago, IEEE) available at Datacite
Software
Licence MIT
Interoperability
Code and research results for ICML 2024 position paper. Originally released here: https://github.com/pat-alt/spurious_sentience.
The research results include:
- Regression tables (.tex; .html)
- An "evaluations.csv" file that contains estimated evaluation metrics for linear probes and the baseline grouped by indicator, layer (network layer), train/test split, variable (measure), model (lin. probe/baseline).
- A figures/ folder containing all PNG figures that went into a) the body or b) the appendix.
- An interim/ folder containing results for probe predictions for each training epoch.
- An attacks/ folder containing the CSV files of neural network activations for attack prompts (see paper for details). Additionally, this folder contains a sentences/ subfolder with the actual textual attack prompts (.txt files).
History
- 2025-07-15 first online, published, posted
Publisher
4TU.ResearchDataFormat
png; csv; txt; tex (LaTeX tables); html (HTML tables)References
Code hosting project url
https://github.com/pat-alt/spurious_sentienceOrganizations
TU Delft, Faculty of Electrical Engineering, Mathematics and Computer Science, Department of Intelligent Systems, Multimedia Computing;ING Bank
DATA
To access the source code, use the following command:
git clone https://data.4tu.nl/v3/datasets/21350eb5-7a23-4710-af30-de27967196d3.git "spurious_sentience"
Files (2)
- 28,739,660 bytesMD5:
d43a0bcc05a52553dd8c83cc96454a93
results_icml2024.zip - 59,044,984 bytesMD5:
4918b71eba4a45ad2c33b4ca41745c64
spurious_sentience-camera-ready.tar.gz -
download all files (zip)
87,784,644 bytes unzipped