Paper II first released 22 January 2026

The claim - verbatim

Michael Darius Eastwood first published Paper II on 22 January 2026, with a one-model study of the ARC Principle (DeepSeek R1, twelve problems), under OSF DOI 10.17605/OSF.IO/6C5XB (sister DOI 10.17605/OSF.IO/8FJMA), as 'The ARC Principle - Experimental Validation of Super-Linear Error Suppression Through Sequential Recursive Processing'; its replication on five frontier models (DeepSeek, Gemini, Grok, Groq Qwen and GPT, with Claude cross-checking answers) was run on 11 and 12 March 2026 and first public by GitHub push on 16 March 2026 (results; code on OSF from 17 March), and the paper is now titled 'Blinded Cross-Architecture Replication and the Retraction of a Super-Linear Estimate'. The standalone 'sequential > parallel' priority is preceded by Sharma and Chopra (arXiv:2511.02309, 4 November 2025), who precede Paper II's formalisation by about 2.5 months.

Anchored evidence

• DOI 10.17605/OSF.IO/6C5XB and sister DOI 10.17605/OSF.IO/8FJMA (both listed in the Paper II HTML)
• research/priority.json priorityChain position 6
• research/data/priority-record.json claim_id 'paper-ii-experimental-validation' first_published '2026-01-22'
• research/papers/paper-ii-experimental-validation.html (JSON-LD datePublished 2026-01-22)

Limits and citation guidance - what this claim does not support, and how to cite it

Limits. The early single-model alpha of approximately 2.24 has been publicly retracted, after the author's larger replication on five frontier models did not reproduce it; the surviving estimate, approximately 0.49 from one model (0.59 by endpoint estimate, interval [-1.3, 2.9]), is inconclusive, and the retraction sits at the top of the falsification dashboard. Bare d/(d+1) exponent is prior work.