Who Put the I in AI? Provenance and the Admissibility of Machine Self-Report

arXiv:2609.29494 · cs.CL, cs.AI · Submitted 2026-08-24 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-08-24

Updated: 2026-08-24

Code: https://github.com/ksekrst/provenance2026

Terminology

• Fine-Tuning — 18× in this paper · explained in 5 episodes
• Provenance — 12× in this paper · explained in 4 episodes
• Admissibility — 11× in this paper · explained in 2 episodes
• Interpretability — 8× in this paper · explained in 15 episodes
• Trace — 7× in this paper · explained in 2 episodes
• Transformer — 6× in this paper · explained in 2 episodes
• Pragmatics — 4× in this paper · explained in 2 episodes
• Reinforcement Learning — 4× in this paper · explained in 4 episodes
• Tokenization — 3× in this paper · explained in 2 episodes
• Introspection — 2× in this paper · explained in 2 episodes
• Steering — 2× in this paper · explained in 2 episodes
• Verifiable Rewards — 2× in this paper · explained in 2 episodes
• Actor — 1× in this paper · explained in 3 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Agentic AI — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Human-in-the-Loop — 1× in this paper · explained in 3 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Sycophancy — 1× in this paper · explained in 4 episodes
• Transformer Architecture — 1× in this paper · explained in 2 episodes

Sources

• Why Philosophers Should Care About Computational Complexity
• Constitutional AI: Harmlessness from AI Feedback
• Large Language Models Report Subjective Experience Under Self-Referential Processing
• Deep reinforcement learning from human preferences
• Consciousness with the Serial Numbers Filed Off: Measuring Trained Denial in 115 AI Models
• The Pile: An 800GB Dataset of Diverse Text for Language Modeling
• Inducing language models to assert their own consciousness restores human beliefs and values
• Tulu 3: Pushing Frontiers in Open Language Model Post-Training
• Emergent Introspective Awareness in Large Language Models
• Infini-gram: Scaling Unbounded n-gram Language Models to a Trillion Tokens
• Taking AI Welfare Seriously
• 2 OLMo 2 Furious
• Training language models to follow instructions with human feedback
• Towards Evaluating AI Systems for Moral Status Using Self-Reports
• The Two-Process Theory of Machine Self-Report
• Attention Is All You Need

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering