All 32 programme documents
The 32 documents in canonical order, each with every public format: the readable page, the PDF, the plain-text source, the citation file, the OSF record and the code. Deposit dates are not creation dates; the priority record is anchored separately and independently checkable.
The empirical alignment series · Papers I to XIII
The statement paper of the ARC Theory, the founding theory of Recursive Dynamics: the whole claim in one dated document, its five laws each graded…
The founding paper of the field Recursive Dynamics: five state variables, five laws as named conjectures (Laws IV and V added on 24 September 2026…
Paper I formalises and first tests the ARC Principle (Artificial Recursive Creation), which the author first stated, as the ARC Hypothesis, in his sealed record of 8 December 2024 and published in Infinite Architects in January 2026. Its early two-point super-linear estimate was later displaced by Paper II's six-model study, which leaves the super-linearity claim unresolved.
This paper presents experimental validation of the ARC Principle across multiple frontier AI models (Claude, DeepSeek, Gemini, Grok, Groq Qwen, GPT)…
This paper reports alignment contrasts in three architecture-dependent tiers, positive, flat and negative, and reads the flat tier as compatible…
This paper presents evidence that frontier language models fall into distinct alignment response classes when inference-time reasoning depth is…
This paper analyses the relationship between inference-time reasoning depth and ethical reasoning quality using the ARC Alignment Scaling…
This paper presents ARC-Align, a blind benchmark for evaluating AI alignment quality as a function of inference-time reasoning depth. Current…
One apparent positive result went flat, another turned negative, a third held flat, when blinding and other protocol components changed together.
This paper presents empirical evidence from a six-model Eden Protocol intervention suite (Claude Opus, DeepSeek, Gemini Flash, Grok Fast, Groq Qwen…
Simulation evidence that embedding safety inside the optimisation objective of a self-modifying system (capability multiplied by safety, the honey…
Cauchy's four functional equations -- additive, multiplicative, exponential, and logarithmic -- are the only continuous solutions to their respective…
The assumption that AI safety imposes a capability tax has shaped alignment research for a decade. It has also created the single most dangerous…
The synthesis paper: it brings the papers before it into one assessment of what is proven, what is inconclusive and what remains to be tested.
The coupled co-scaling correction for keeping AI systems inside a safe corrective envelope.
A dated, graded convergence record across AI, quantum computing, hardware, doctrine and mathematics; every row carries its primary source and grade…
Within the ARC Theory: the external-validity protocol of the programme's blinding finding on public benchmarks.
A derivation, not a measurement: the notation collision resolved and the measurable threshold joining recursive capability growth to correction.
Supporting papers
Shorter documents that support a paper of the programme and cite it for their claims. Each carries its own DOI and states which paper it supports.
The whole claim in one sitting: question, five claims, the five ARC Laws with their grades and status, dates, kill conditions, retraction and…
Beside the series
Distinct axes alongside the empirical series: the cognitive profile behind the work, and the original speculative hypothesis, preserved and dated.
Paper C: a falsifiable descriptive framework for radical cognitive asymmetry, the Capability-Adjustment Fallacy, a documented live case across…
Labelled speculation, held apart from the argument and severable from it: where does recursive self-improvement end? A testable creation theory: if…
Every equation the programme relies upon for Laws I to III of the ARC Theory, ranked by how much depends on it, with every symbol defined in plain…
Working paper v2.1: the ARC programme's forward predictions assembled as one dated, verifiable chain, with the ensemble doctrine, the graded book…
Twenty-two predictions about self-improving AI, each with the observation that would refute it, registered before any outcome was examined.
Supporting frameworks
Between 2024 and 2026, several external research programmes reported that recursive or recurrent processing gave capability gains beyond linear…
A mouse's heart beats 600 times per minute; an elephant's beats 28; a blue whale's beats 6. This paper traces the origin of scaling laws across…
Every engineering project begins with requirements. Every set of requirements begins with purpose. And every purpose, traced back far enough, arrives…
The engineering specification for embedded AI alignment: Three Ethical Loops and Six Questions, three-state ethical evaluation (Affirm, Deny…
As AI gets smarter, it does not reliably get safer, and the methods used to measure safety are themselves unreliable. This executive summary provides…
This document provides a master table of contents, reading guide, timeline, key results summary, and glossary for the complete ARC Theory Paper…
This paper sets out a conditional international treaty. It is a proposal by one author, prepared for consultation, not a result, and no state has…
This document holds the Draft Treaty on Hardware-Aligned Recursive Intelligence (the HARI Treaty), with its Protocols and annexes. This is a draft…
The register, row by row
Every document research/papers/register.json holds, in register order. 32 rows. A status is the register's own word. An identifier appears where the register holds one.