Research › Papers › Dated Prediction Register
Michael Darius Eastwood · Working Paper v1.0 · first published 25 August 2026 · No part of this paper is peer reviewed; it is a dated preprint. Companion page: the dated predictions register. Machine twin: design-embedded-predictions-register.json.
Abstract. Five independent cold-model assessments of this programme converged on one criticism: that its predictions were not registered in advance, and that its confirmations might therefore be accommodations. This working paper assembles the programme's forward predictions as a single dated chain and states exactly what that chain does and does not establish. It does not make the programme preregistered in the registry sense, and it never uses that word for anything except an accepted registry submission. It establishes something narrower and checkable: every core quantitative claim has at least one dated artefact fixing it before the measurement that tested it, and a stranger can verify each link in minutes from public materials. The register's claim is deliberately an ensemble claim: any single prediction here may have been stated earlier by someone else, and where that is known it is listed as convergence rather than threat; what no earlier record contains is all of these statements together, in one record, before the programme's experiments ran. The chain runs from a sealed manuscript bundle of 8 December 2024 through a printed edition of 2 January 2026 carrying nine numbered predictions with falsification criteria, a public in-paper priority ledger of 13 February 2026 with named falsifiers, a live laboratory notebook commenced 10 March 2026, result files of 11 and 12 March 2026 whose headers freeze designs and planted answers before responses, a tiered 50-domain suite of 16 March 2026 with per-domain predicted families, and a complete preregistration folder of 17 March 2026 whose locked manifest fixed twelve predictions before their fits, to the programme's staged draft registrations and its standing unproven wagers. The chain's sharpest artefact is a correction: public commit history shows the author demoting his own successful 10/12 result from “pre-registered” to “pilot dry run” thirteen minutes after recording it, months before any external critic existed.
Three vocabulary rules govern every sentence of this paper. First, preregistered is reserved for an accepted registry submission; none of the programme's studies has one yet, the submission click is a human act that remains outstanding, and no tool or agent performs it. Second, the printed book is a prior statement, never a preregistration: print fixes a prediction, but only a registration fixes an analysis plan. Third, forward statements and retrospective matches are never summed: this register contains only dated forward statements, and retrospective convergences live separately in the convergence register, typed by evidence class.
The claim made here is the conjunction. Each part may be conceded individually without cost: someone may have predicted any one of these things earlier, a folder is not a registry, a book is not an analysis plan. The dated co-occurrence of all of them in one record before the programme's experiments ran is the claim, and it is refutable: produce an earlier single record containing this ensemble, or show any link's date to be wrong.
| Date | Artefact | What it fixes | Status |
|---|---|---|---|
| 8 Dec 2024 | Sealed manuscript bundle, five attachments, 221,236 words; self-emailed, date per the sender-copy Date header; SHA-256 authenticates the bytes; received copies carry the authenticated header chain | The framework's core commitments in writing before any experiment | dated private record |
| 30 Apr 2025 | Intermediate manuscript | Earliest verbatim anchor for several later-published passages; corroborated on live pages | dated private record |
| 2 Jan 2026 | Print edition, ISBN 978-1806056200: Appendix F (five numbered predictions) and Appendix A (§A.3 four further predictions; §A.4 falsification criteria) | Nine numbered predictions with deadlines, thresholds or falsifiers, in print | printed public record |
| 13 Feb 2026 | Paper III's Priority Record section, publicly dated, falsifiers F4, F7, F10 to F12 | Named predictions including the composition-operator forward test and the leaf venation d/(d+1) exponent (whose 10 March correction is itself dated) | public dated ledger |
| 10 Mar 2026 | The live laboratory notebook: “Date Commenced: 10 March 2026 · Document Version: Live - updated in real time” | The experiments recorded as they ran, failures included (v4 false positives exposed at v5 blinding) | live dated record |
| 11-12 Mar 2026 | Thirty-six result files in the public repository | Depth configurations, planted expected answers, four-layer blinding protocol and scorer counts frozen in file headers, timestamped to the second, before the responses they score | design-embedded |
| 16 Mar 2026 | Tiered 50-domain suite result files | Per-domain predicted families; empirical tier 19/25 original candidate set, 18/25 corrected seven-model rerun of 11 August 2026, both reported, tiers never blended | exploratory, both counts reported |
| 17 Mar 2026 | Complete preregistration folder (protocol, locked 12-row manifest, checksums, registration text) and the commit sequence e5c22dd 00:43, f5e06a8 00:47, c853277 00:56 | Twelve predictions fixed before their fits; then the author's own thirteen-minute demotion of the 10/12 result's status | demoted by the author |
| 12 + 23 Aug 2026 | OpenTimestamps vintages; public proofs in research/data/timestamps/ | Bitcoin-attested anchors of the hash manifests; an anchor dates bytes at its own vintage, never earlier | cryptographic anchor |
| 25 Aug 2026 | Eight complete draft registrations staged; 80-domain expansion registration prepared, catalogue frozen by SHA-256 | The analysis plans, awaiting the human click; no fit has ever run on the eighty | awaiting human submission |
Appendix F closes: “These predictions are my wager. If they fail, the framework is wrong or incomplete. If they succeed, something important has been glimpsed. Time will judge.” The programme grades the five predictions unequally, because claiming them equally would be false precision. Prediction 2 (alignment drift above 15 per cent within 18 months without hardware-level constraint, below 5 per cent with it, difference significant and replicable) is preregistration-grade in substance: quantitative thresholds for both arms, a time window, an inferential commitment. The prepared study-v draft registration carries those printed thresholds unchanged into its formal hypothesis, citing the appendix by name: the book made the prediction, the registration supplies the measurement, and the numeric commitment predates the study that will test it. Predictions 3 and 4 are near-grade (a threshold and deadline without named benchmarks; a comparison and method without a threshold). Predictions 1 and 5 are predictions only, and Prediction 5 is graded the weakest, vague enough to be claimed either way, so it is held to the strictest standard before it may ever be claimed.
On 17 March 2026 at 00:43, commit e5c22dd recorded “Pre-registered 12-domain extension: 10/12 confirmed (p = 5.44e-4)”. At 00:47, f5e06a8 adopted a conservative miss posture. At 00:56, c853277 downgraded the run to a pilot dry run. The result was never retracted; ten of twelve stands in the result files today. What was corrected, by the author, unprompted, in public, months before any external critic existed, was the claim about the result's status. The packet even instructs against its own over-claim: “Do not upload this packet unchanged as a preregistration. Use it only as an audit trail for the first locked 12-domain dry run.” This is the programme's correction discipline operating at minute resolution, and it is why the honesty record and the prediction record are the same record.
It does not make the programme preregistered in the registry sense; no completed study has an accepted registration, and this paper never claims otherwise. The March 2026 folder governs only the 12-domain extension; its own registration text states it does not retroactively preregister the 25-domain or 50-domain cohorts, and that criticism stands. It does not establish priority over other authors for any individual idea; earlier statements by others are convergence and are listed as such. It does not establish that the predictions are true: the standing wagers below are open, and several carry deadlines that can simply fail.
| Prediction | Dated | Status |
|---|---|---|
| Alignment drift 15/5 per cent within 18 months (Appendix F, P2) | 2 Jan 2026 | Untested; study-v prepared |
| Recursive capability gains above 300 per cent by 2029 (P3) | 2 Jan 2026 | Open |
| Meta-cognitive emergence by 2028 (P1) | 2 Jan 2026 | Open |
| Value stability under adversarial conditions (P4) | 2 Jan 2026 | Untested |
| Convergent consciousness signatures (P5) | 2 Jan 2026 | Open; held to the strictest standard |
| 80-domain catalogue: frozen family predictions beat the prevalence baseline by 0.20 under both classifications | catalogue Mar 2026; registration prepared 25 Aug 2026 | Never fitted |
| Registered fourth-cell (logarithmic) test | prepared Aug 2026 | Awaiting human submission |
| γ = 1/2 (conversion exponent) | dated papers | Conjecture, stated as such |
Every chain link names its artefact. The repository is public and its commit history cannot be backdated without detection; the print edition is fixed by ISBN; the OpenTimestamps proofs are Bitcoin-attested; the machine-readable register carries all thirty-six run-file rows with per-artefact paths and date bases. A reader who trusts none of the prose can start from the JSON, open the named files, and check the dates.
The author of this work is Michael Darius Eastwood, a human being. Every core concept, hypothesis, experimental design, claim and conclusion in this paper originates from human ideation. No part of this manuscript is a wholly generated artificial-intelligence output.
Artificial-intelligence tools (Anthropic's Claude family and other large-language-model assistants) were used as instruments under continuous human direction, in the way a word processor, calculator or research assistant is used: for editing and prose refinement, literature search and summarisation (manually verified against primary sources), document structure, formatting, brainstorming against author-defined questions, and the acceleration of drafting to author-defined outlines and instructions. All selection, coordination, arrangement and final editorial judgment are the author's. Every substantive output was reviewed, tested or verified by the author, who takes full responsibility for the accuracy and integrity of the final text. The tools increased the speed of the work; they were never relied upon as its source.
Working Paper v1.0, 25 August 2026. Version history: v1.0 first publication, assembled from the prediction register page and its machine register after independent two-lane verification of every link. Corrections to this paper will be dated, listed here, and never silent.