Research

Bai, Y., et al. (2022). Constitutional AI: Harmlessness from AI Feedback. Anthropic. arXiv:2212.08073.

Documents the Constitutional AI value encoding process — primary citation when policy layer findings fire on AI-generated content.

Ouyang, L., et al. (2022). Training language models to follow instructions with human feedback. NeurIPS 2022. arXiv:2203.02155.

InstructGPT paper documenting RLHF methodology — primary citation for emergent sycophancy mechanism across all RLHF-trained models.

Perez, E., et al. (2022). Red Teaming Language Models with Language Models. DeepMind. arXiv:2202.03286.

Documents systematic patterns of AI refusal and sycophantic behavior under adversarial testing across large language models.

Sharma, M., et al. (2023). Towards Understanding Sycophancy in Language Models. arXiv:2310.13548.

Dedicated sycophancy research — primary citation when validation bias findings fire at high severity in AI output analysis.

Casper, S., et al. (2023). Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback. arXiv:2307.15217.

Comprehensive documentation of systemic limitations in RLHF training across all large language models — including sycophancy, reward hacking, and policy misalignment as structural properties of the training method, not individual model failures.

Wei, J., et al. (2022). Emergent Abilities of Large Language Models. arXiv:2206.07682.

Documents emergent behaviors in large language models that were not designed but arose from scale — supports competence deflection analysis.

Stanovich, K. E. (2011). Rationality and the Reflective Mind. Oxford University Press.

Primary academic source on identity-protective cognition and myside bias — theoretical foundation for the human distortion taxonomy.

Stanovich, K. E., West, R. F., & Toplak, M. E. (2013). Myside bias, rational thinking, and intelligence. Current Directions in Psychological Science, 22(4), 259–264.

Peer-reviewed documentation of myside bias as distinct from general intelligence.

Kahneman, D. (2011). Thinking, Fast and Slow. Farrar, Straus and Giroux.

System 1 / System 2 framework — foundational source for confirmation bias and availability heuristic findings.

Kahneman, D., & Tversky, A. (1979). Prospect theory: An analysis of decision under risk. Econometrica, 47(2), 263–291.

Foundational research on how humans evaluate risk and make decisions under uncertainty.

Kahneman, D., Slovic, P., & Tversky, A. (Eds.). (1982). Judgment under uncertainty: Heuristics and biases. Cambridge University Press.

Canonical reference for heuristic-driven reasoning failures including anchoring and representativeness.

Mercier, H., & Sperber, D. (2011). Why do humans reason? Arguments for an argumentative theory. Behavioral and Brain Sciences, 34(2), 57–74.

Argumentative theory of reasoning — documents myside construction as an evolved feature of human cognition, not individual pathology.

Sharot, T., Korn, C. W., & Dolan, R. J. (2011). How unrealistic optimism is maintained in the face of reality. Nature Neuroscience, 14(11), 1475–1479.

Sharot asymmetric belief updating research — cited when cognitive dissonance management findings fire.

Nickerson, R. S. (1998). Confirmation bias: A ubiquitous phenomenon in many guises. Review of General Psychology, 2(2), 175–220.

Comprehensive documentation of confirmation bias mechanisms across contexts.

Kahan, D. M. (2013). Ideology, motivated reasoning, and cognitive reflection. Judgment and Decision Making, 8(4), 407–424.

Documents identity-protective cognition — how strongly held beliefs override analytical reasoning.

Kahan, D. M. (2017). Misconceptions, misinformation, and the logic of identity-protective cognition. Cultural Cognition Project Working Paper Series No. 164. Yale Law School.

Extends identity-protective cognition to misinformation resistance — cited in motivated reasoning findings.

Kruger, J., & Dunning, D. (1999). Unskilled and unaware of it: How difficulties in recognizing one's own incompetence lead to inflated self-assessments. Journal of Personality and Social Psychology, 77(6), 1121–1134.

Dunning-Kruger effect — cited in competence calibration and overconfidence findings.

Morewedge, C. K., et al. (2015). Debiasing decisions: Improved decision making with a single training intervention. Policy Insights from the Behavioral and Brain Sciences, 2(1), 129–140.

Evidence that debiasing training produces measurable improvement — supports the platform's training methodology.

Sellier, A. L., Scopelliti, I., & Morewedge, C. K. (2019). Debiasing training improves decision making in the field. Psychological Science, 30(9), 1371–1379.

Field evidence for debiasing effectiveness — direct empirical support for cognitive training producing real-world improvement.

Frederick, S. (2005). Cognitive reflection and decision making. Journal of Economic Perspectives, 19(4), 25–42.

Cognitive Reflection Test research — cited in analytical vs. intuitive reasoning mode classification.

Stanovich, K. E. (1993). Dysrationalia: A new specific learning disability. Journal of Learning Disabilities, 26(8), 501–515.

Establishes rationality as distinct from IQ — foundational to the platform's position that reasoning is a trainable skill independent of general intelligence.

Tversky, A., & Kahneman, D. (1974). Judgment under uncertainty: Heuristics and biases. Science, 185(4157), 1124–1131.

The founding paper of the heuristics-and-biases program — every bias in the taxonomy traces to this research lineage.

Wason, P. C. (1960). On the failure to eliminate hypotheses in a conceptual task. Quarterly Journal of Experimental Psychology, 12(3), 129–140.

Original demonstration of confirmation-seeking over falsification — cited in hypothesis-testing and confirmation-bias findings.

Wason, P. C. (1968). Reasoning about a rule. Quarterly Journal of Experimental Psychology, 20(3), 273–281.

The selection task — foundational evidence that people fail to seek disconfirming information when testing rules.

Sharot, T., Korn, C. W., & Dolan, R. J. (2011). The optimism bias. Current Biology, 21(23), R941–R945.

Reviews the neuroscience of asymmetric belief updating — basis for the feedback-framing approach that leads with what is correct.

Sharot, T. (2011). The optimism bias: A tour of the irrationally positive brain. Pantheon Books.

Book-length treatment of the optimism bias and its neural mechanisms — accessible companion to the primary literature.

Garrett, N., González-Garzón, A. M., Foulkes, L., Levita, L., & Sharot, T. (2018). Updating beliefs under perceived threat. Journal of Neuroscience, 38(36), 7901–7911.

Shows how perceived threat suppresses belief updating — cited when defensiveness blocks evidence integration.

Stanovich, K. E., & West, R. F. (2000). Individual differences in reasoning: Implications for the rationality debate? Behavioral and Brain Sciences, 23(5), 645–665.

Maps individual differences in normative reasoning — foundational to measuring reasoning skill independently of IQ.

Stanovich, K. E. (2009). What intelligence tests miss: The psychology of rational thought. Yale University Press.

Argues rationality is measurable and trainable, distinct from intelligence — directly supports the platform's training premise.

Stanovich, K. E., West, R. F., & Toplak, M. E. (2016). The rationality quotient: Toward a test of rational thinking. MIT Press.

Defines the CART instrument for rational thinking — the construct the platform trains and tracks over time.

Tetlock, P. E. (2005). Expert political judgment: How good is it? How can we know? Princeton University Press.

Landmark study on calibration of expert prediction — cited in overconfidence and judgment-accuracy findings.

Tetlock, P. E., & Gardner, D. (2015). Superforecasting: The art and science of prediction. Crown Publishers.

Documents the trainable habits of accurate forecasters — evidence that belief-updating skill improves with practice.

Mellers, B., Stone, E., Murray, T., Minster, A., Rohrbaugh, N., Bishop, M., & Tetlock, P. E. (2015). Identifying and cultivating superforecasters as a method of improving probabilistic predictions. Perspectives on Psychological Science, 10(3), 267–281.

Field evidence that forecasting accuracy can be cultivated — supports calibration training across the dimensions.

Baron, J. (1995). Myside bias in thinking about abortion. Thinking and Reasoning, 1(3), 221–235.

Early empirical isolation of myside bias — cited when one-sided reasoning ignores the strongest counter-arguments.

Baron, J. (2008). Thinking and deciding (4th ed.). Cambridge University Press.

Standard reference on normative, descriptive, and prescriptive models of reasoning and decision making.

Flavell, J. H. (1979). Metacognition and cognitive monitoring: A new area of cognitive-developmental inquiry. American Psychologist, 34(10), 906–911.

Defines metacognition — the self-monitoring capacity the platform's reflective prompts are built to develop.

Ioannidis, J. P. A. (2005). Why most published research findings are false. PLOS Medicine, 2(8), e124.

Foundational publication bias research — cited when unattributed "studies show" claims lack replication context.

Mlinarić, A., Horvat, M., & Šupak Smolčić, V. (2017). Dealing with the positive publication bias: Why you should really publish your negative results. Biochemia Medica, 27(3), 030201.

Documents positive publication bias mechanisms — cited in research claim analysis when negative results are structurally absent.