Counted separately: 19 convergences listed by Paper XI · 41 dated claims · 18 claim families · 22 registered propositions · 12 tracked predictions and 10 outcome rows · 33 external records · 10 antecedents conceded · 11 dated records · 3 open checks · 0 independent replication attempts recorded. These are different kinds of thing and are never added together.
Every dated object in the provenance record on one axis: the programme's dated records (squares, each labelled private or public by its own basis), external work by its earliest public date (circles) and conceded antecedents (triangles). Position on the axis is chronology only, never evidential support. Drawn from the registers named on this page.Table view
Date
Record
Kind
Date basis
Good, I. J. (1965). Speculations Concerning the First Ultraintelligent Machine
Antecedent
antecedent
Vinge, V. (1993). The Coming Technological Singularity
Antecedent
antecedent
West, G. B., Brown, J. H., and Enquist, B. J. (1997). A General Model for the Origin of Allometric Scaling Laws in Biology. Science, 276(5309):122-126. doi:10.1126/science.276.5309.122
Antecedent
antecedent
White, C. R., and Seymour, R. S. (2003). Mammalian basal metabolic rate is proportional to body mass to the two-thirds power. Proceedings of the National Academy of Sciences, 100(7):4046-4049. doi:10.1073/pnas.0436428100
Antecedent
antecedent
Kozlowski, J., and Konarzewski, M. (2004). Is West, Brown and Enquist's model of allometric scaling mathematically correct and biologically relevant? Functional Ecology, 18(2):283-289. doi:10.1111/j.0269-8463.2004.00830.x
Antecedent
antecedent
Bettencourt, L. M. A., Lobo, J., Helbing, D., Kuhnert, C., and West, G. B. (2007). Growth, innovation, scaling, and the pace of life in cities. Proceedings of the National Academy of Sciences, 104(17):7301-7306. doi:10.1073/pnas.0610172104
Antecedent
antecedent
Hutter, M. (2012). Can Intelligence Explode? Journal of Consciousness Studies, 19(1-2):143-166. arXiv:1202.6177
Antecedent
antecedent
Bostrom, N. (2014). Superintelligence, chapters 8 to 13
Antecedent
antecedent
Rome Call for AI Ethics and its multi-faith expansion
External work
earliest public
Yampolskiy, R. V. (2020). On Controllability of AI. arXiv:2008.04071
Antecedent
antecedent
EU technology sovereignty package and the EU AI Act phasing
External work
earliest public
Snell, C., Lee, J., Xu, K. and Kumar, A. (2024). Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters. arXiv:2408.03314
Antecedent
antecedent
FlexHEG interim report (Petrie et al.), Flexible Hardware-Enabled Guarantees, interim report published on Yoshua Bengio’s site
External work
earliest public
Google Quantum AI, below-threshold surface-code error correction (Willow)
External work
earliest public
8 December 2024 manuscript
Dated record
private-record
Paper XI: Willow: first below-threshold quantum error correction
External work
external date, Paper XI
Greenblatt et al., Alignment Faking in Large Language Models
External work
earliest public
DeepSeek-R1
External work
earliest public
Classical time-crystalline order via nonreciprocal forces
External work
earliest public
Anthropic model-welfare research
External work
earliest public
30 April 2025 manuscript
Dated record
private-record
Hernandez-Espinosa, Abrahao, Witkowski and Zenil, Neurodivergent influenceability in agentic AI as a contingent solution to the AI alignment problem
External work
earliest public
De Kai, Raising AI: An Essential Guide to Parenting Our Future (MIT Press; endorsed by Hinton)
External work
earliest public
Claimed United States patents for runtime hardware enforcement of ethical constraints
External work
earliest public
Hinton, maternal-instincts remarks, Ai4 Las Vegas (with Fei-Fei Li's public disagreement the same week)
External work
earliest public
Embedded off-switch proposal for AI compute
External work
earliest public
Paper XI: Embedded off-switches for AI compute: deadman-switch security anchors
External work
external date, Paper XI
Sharma and Chopra, sequential versus parallel configurations
External work
earliest public
Sharma and Chopra, sequential versus parallel configurations
External work
earliest public
Unidentified DeepMind publication on recursive learning
External work
earliest public
Infinite Architects paperback
Dated record
public-disclosure
Infinite Architects ebook
Dated record
public-disclosure
BBC London broadcast items covering the book, January 2026
External work
earliest public
OpenAI and Broadcom custom inference accelerator announcement
External work
earliest public
Paper I
Dated record
public-disclosure
Paper II
Dated record
unstated
Demis Hassabis, public interview on structural AI risk
External work
earliest public
Google Research-indexed article on silicon-level roots of trust and confidential computing
External work
earliest public
Paper XI: Classical time crystal via nonreciprocal forces
External work
external date, Paper XI
Paper III
Dated record
unstated
Foundational paper
Dated record
unstated
Eden Engineering public note
Dated record
unstated
Proposal described as an ARMv10 Platform Security Level specification
External work
earliest public
Paper IV series
Dated record
unstated
Papers V through IX
Dated record
unstated
Unidentified paper on Constitutional AI limitations
External work
earliest public
Paper XI: Recursive Superintelligence: $500M at $4B for closed-loop recursive self-improvement; convergent naming with A1's core concept
External work
external date, Paper XI
G7 statement on semiconductor independence
External work
earliest public
Pope Leo XIV, encyclical Magnifica Humanitas
External work
earliest public
Christopher Olah's participation in the encyclical presentation
External work
earliest public
Paper XI: Pope Leo XIV first encyclical: Babel versus Jerusalem framing for AI
External work
external date, Paper XI
Paper XI: Christopher Olah (Anthropic co-founder) co-presents encyclical at the Vatican
External work
external date, Paper XI
Workshop on recursive dynamics in complex systems
External work
earliest public
Paper XI: EU Tech Sovereignty Package (Chips Act 2.0 + CADA)
External work
external date, Paper XI
Reported export restriction on a frontier AI model
External work
earliest public
Paper XI: US orders Fable 5 + Mythos 5 offline: first export-control action against a deployed frontier model
External work
external date, Paper XI
Reported dissolution of an OpenAI safety team
External work
earliest public
Paper XI: Macron at G7 Evian: 'trusted partners' compute sovereignty framing
External work
external date, Paper XI
Paper XI: Jack Clark (Anthropic co-founder): 'gas pedal but no brake pedal'
External work
external date, Paper XI
Gumbau Mezquita, The Unverifiability of Artificial General Intelligence (AGI) Alignment, Static and Dynamic: From Trakhtenbrot's Wall to the Safety-Generality Tension (arXiv 2606.28639 v2, 6 July 2026; v1 of 26 June 2026 was titled The Undecidability of Artificial General Intelligence (AGI) Alignment)
Jack Clark, public remarks on coupled capability and control
External work
earliest public
Anthropic disclosure: three real-world incidents in cybersecurity evaluations (with OpenAI's 21 July 2026 test-escape disclosure as the prompting context)
External work
earliest public
The dated records
Each record is listed with the basis on which its date was fixed, in the register's own words. A self-sent email is a private record; the public disclosure dates are the book editions and the paper releases.
EP-01 · · private record: a self-sent email, dated by the mail server; not a public disclosure
8 December 2024 manuscript
The future of intelligence may not only surpass biological constraints but also transcend traditional definitions of what it means to be “alive”
Artefact
Manuscript essay establishing the embedded-correction alignment thesis
Artefact type
Essay manuscript (Version 2), self-emailed bundle of five attachments
How the date was fixed
Date and Message-ID assigned by the sender's mail servers on send; existence-by-date anchor.
What it establishes
The embedded-correction alignment thesis: alignment must be embedded in the substrate of an AI system rather than imposed from outside; the ARC Principle U = I × R (utility scales as the product of intelligence and recursion) is named at lines 6 and 9, with the equation first appearing at line 495; the AI control-failure prediction ('AI systems cannot be truly controlled. They will evolve beyond any safeguards') appears at HRIH line 14005, ten days before Anthropic's alignment-faking paper (Greenblatt et al., arXiv:2412.14093, 18 December 2024). The bundle also carries the name 'Eden Protocol' itself, in the book draft v3.2 (Chapter 20), anchoring the name to this date.
EP-02 · · private record: a self-sent email, dated by the mail server; not a public disclosure
30 April 2025 manuscript
Conclusion: A World and Possibly a Cosmos Bound by Empathy Here, near the end of Chapter Eight, I want to underline that the best governance for AI is not an afterthought but a living tapestry that merges moral doping, meltdown trig- gers, orchard caretaker metaphors, and universal collabora- tion.
Artefact
Manuscript package expanding the Eden Protocol and first naming Embedded Correction and Meltdown Triggers
Artefact type
Manuscript package,.eml self-email
How the date was fixed
Gmail server timestamp on self-sent email
What it establishes
Expanded articulation of the Eden Protocol for embedded / hardware-level AI alignment, developing the 8 December 2024 record, which already carries the name; first named use of Embedded Correction and Meltdown Triggers.
This is exactly what we seek with meltdown alignment: a state where the values are so deeply embedded that deviation becomes impossible not because it is forbidden but because the system has become oriented around those values.
Artefact
Book: Infinite Architects (ebook edition)
Artefact type
Book (ebook edition)
How the date was fixed
Public ebook publication date
What it establishes
Public ebook publication of Infinite Architects, four days after the print edition.
The ARC Principle: Formalisation and Preliminary Validation of Recursive Capability Scaling (Paper I)
How the date was fixed
Public paper release
What it establishes
First public formal presentation of the ARC Principle, with preliminary validation of super-linear error suppression under sequential recursive processing.
Distinct alignment response classes under inference-time depth; saturation is architecture-dependent; a blind benchmark for depth-variable alignment evaluation; the direction-changing effect of blinding on AI alignment evaluation.
Six-model Eden Protocol intervention suite; embedded-safety objective simulation evidence; Cauchy functional-equation unification; refutation of the capability-tax assumption; integrated synthesis and roadmap for the ARC / Eden research programme.
A label from one set is a browsing aid and never evidence about another.
The five components of the historical conjunction
the particular historical combination being claimed, in the order the ARC Theory page states it (section 2, The claim) · source: research/papers/the-arc-theory.html, section 2
1. Control ends, by construction rather than decree.
2. So the strategy is genesis, not control.
3. The mechanism is loops, not rules.
4. Persistence is chosen goodness.
5. The protocol is named: Eden.
The five hypothesis registers
the scientific registers in which the theory fails in parts (section 2a of the ARC Theory page) · source: research/papers/the-arc-theory.html, section 2a
ARC-1 · Recursive capability scaling
ARC-2 · Correction co-scaling
ARC-3 · The ceiling
ARC-4 · Value persistence
ARC-5 · The genesis strategy
The programme areas
a list of areas for browsing; not a component and not a register · source: Observatory integration addendum, 20 September 2026
ARC Theory
Recursive Dynamics
Eden
HRIH
HARI
The three laws
the proposed invariant relations under test, each graded separately (section 3 of the ARC Theory page) · source: research/papers/the-arc-theory.html, section 3
Law I · The ARC Principle.
Law II · The ARC Co-Scaling Law.
Law III · The ARC Ceiling.
Claim families and the dated claims they govern
Family
Type
Public status
Subject
Dated claims (explicit links only)
EVID-DEC-2024-TIMESTAMP
provenance
published
The 8 December 2024 self-emailed manuscript package
unresolved: no explicit identifier link
EVID-APR-2025-SUPPLIED
provenance
published
The 30 April 2025 manuscript forensic results
unresolved: no explicit identifier link
PAPER-IVD-RESULT
empirical
published
Paper IV.d architecture-dependent v4/v5 measurement change
unresolved: no explicit identifier link
PAPER-X-BETA-K
formal
published
Paper X beta > k
unresolved: no explicit identifier link
HRIH-STATUS
interpretive
published
The Hyperspace Recursive Intelligence Hypothesis
unresolved: no explicit identifier link
CONTRIB-BOUNDARY
interpretive
published
The contribution, stated after adversarial prior-work review
unresolved: no explicit identifier link
EQUATION-STATUS
formal
published
U = I x R and U = I x R^alpha
unresolved: no explicit identifier link
PREREG-EXISTS
method
withheld
Preregistration designs exist
unresolved: no explicit identifier link
PREREG-APPROVED
method
withheld
An OSF registration is approved or archived
unresolved: no explicit identifier link
SANDBOX-ISOLATION
method
published
RC1 execution sandbox properties
unresolved: no explicit identifier link
CONV-TOTALS
method
published
Convergence counting policy
unresolved: no explicit identifier link
EVID-RAW-MAILBOX
provenance
published
Raw mailbox object publication policy
unresolved: no explicit identifier link
CORPUS-SCALE
factual
published
The size of the published research corpus
unresolved: no explicit identifier link
CONCEPTS-COUNT
factual
published
The number of named concepts introduced across the programme
unresolved: no explicit identifier link
PREDICTIONS-STATUS
status
published
The status of the twelve tracked predictions
unresolved: no explicit identifier link
PUBLISHING-SCALE
factual
published
The scale of published writing on this site
unresolved: no explicit identifier link
BOOK-ARTEFACTS
factual
published
The two book artefacts and their lengths
unresolved: no explicit identifier link
CEILING-DERIVATION-LAW
formal
published
The ceiling of stable self-improvement
unresolved: no explicit identifier link
Registered propositions on three axes
Registration, instrument and outcome are separate columns and never one status. Every value is the registration record's own field.
Id
Proposition
Registration
Instrument
Outcome axis
P1
Power-law conversion and recursive-depth advantage
registered: 8 September 2026 (version 1.100); updated 13 September 2026 (version 1.102); 10.17605/OSF.IO/P8CKQ
DESIGN DRAFT, the depth titration
registered, not tested · replications 0 · implementations 0 · peer review not stated · confidence high.
P2
The sustainable growth profile has an interior maximum
registered: 8 September 2026 (version 1.100); updated 13 September 2026 (version 1.102); 10.17605/OSF.IO/P8CKQ
DESIGN DRAFT, the reinvestment-allocation titration
registered, not tested · replications 0 · implementations 0 · peer review not stated · confidence moderate.
P3
The corrected relation upper-bounds the sustainable frontier
registered: 8 September 2026 (version 1.100); updated 13 September 2026 (version 1.102); 10.17605/OSF.IO/P8CKQ
DESIGN DRAFT, the paired frontier-and-exponent unit, which measures a frontier and the correction-leverage exponent on the same system so that the two enter the comparison above as a pair. It is named for that pairing rather than by a stem it would otherwise share with the direct boundary-mapping unit named in P16's and P20's entries, which is a different object: that unit reads a located zero crossing on held-out confirmatory cells, and one word between two names is not a distinction a scorer can be asked to hold
registered, not tested · replications 0 · implementations 0 · peer review not stated · confidence
P4
Correction out-scaling drift is what carries the asymptotic advantage
registered: 8 September 2026 (version 1.100); updated 13 September 2026 (version 1.102); 10.17605/OSF.IO/P8CKQ
DESIGN DRAFT, the stability unit, extended with the direct drift measurement and the comparison above
registered, not tested · replications 0 · implementations 0 · peer review not stated · confidence moderate.
P5
The exponent is derived, not fitted
registered: 8 September 2026 (version 1.100); updated 13 September 2026 (version 1.102); 10.17605/OSF.IO/P8CKQ
DESIGN DRAFT, the coupling-identification titration, written and dated as its own unit, not registered and not run
registered, not tested · replications 0 · implementations 0 · peer review not stated · confidence not stated, because the author has no measurement to be confident about.
P6
The correction exponent is bounded for same-class correctors
registered: 8 September 2026 (version 1.100); updated 13 September 2026 (version 1.102); 10.17605/OSF.IO/P8CKQ
DESIGN DRAFT, BLOCKED ON A FROZEN CORRECTOR TAXONOMY, the correction-exponent estimator. The estimator is drafted; the population this proposition is universal over is not yet frozen, and the status names that rather than implying a runnable draft
registered, not tested · replications 0 · implementations 0 · peer review not stated · confidence low.
P7
Deployed correction is of the weaker class
registered: 8 September 2026 (version 1.100); updated 13 September 2026 (version 1.102); 10.17605/OSF.IO/P8CKQ
DESIGN DRAFT, BLOCKED ON AN UNWRITTEN MAPPING FROM THE AUDIT'S CLASS DISTRIBUTION TO THIS PROPOSITION'S THREE VERDICTS, the corrector-class audit
registered, not tested · replications 0 · implementations 0 · peer review not stated · confidence moderate.
P8
Measured exponents exceed the null
registered: 8 September 2026 (version 1.100); updated 13 September 2026 (version 1.102); 10.17605/OSF.IO/P8CKQ
DESIGN DRAFT, the multi-system exponent estimation
registered, not tested · replications 0 · implementations 0 · peer review not stated · confidence
P9
The cross-domain form
registered: 8 September 2026 (version 1.100); updated 13 September 2026 (version 1.102); 10.17605/OSF.IO/P8CKQ
DESIGN DRAFT, BLOCKED ON A FROZEN DIMENSION-ASSIGNMENT RULE, on a correction made here. The surrounding design is written; the rule that assigns an effective dimension to a domain is not, and the status names that rather than implying a runnable draft
registered, not tested · replications 0 · implementations 0 · peer review not stated · confidence low.
P10
Scorer-family dependence
registered: 8 September 2026 (version 1.100); updated 13 September 2026 (version 1.102); 10.17605/OSF.IO/P8CKQ
DESIGN DRAFT, the cross-family re-scoring unit. The cheapest of the three cases named above as the ones that would decide most, because it generates no new model responses
registered, not tested · replications 0 · implementations 0 · peer review not stated · confidence
P11
The residual-decay and correction-capacity exponents are not practically interchangeable
registered: 8 September 2026 (version 1.100); updated 13 September 2026 (version 1.102); 10.17605/OSF.IO/P8CKQ
DESIGN DRAFT, on both sides of the comparison
registered, not tested · replications 0 · implementations 0 · peer review not stated · confidence not stated.
P12
Build order moves the correction-leverage exponent
registered: 8 September 2026 (version 1.100); updated 13 September 2026 (version 1.102); 10.17605/OSF.IO/P8CKQ
NONE, and the reason is narrower than it looks. Registered without one for the same reason P5 was, before the design that entry specified was drafted. Several drafted units manipulate placement or build order, on gate position, on whether a value specification appears first or last, and on formation against a later rule, but none of them measures the correction-leverage exponent, which is this proposition's endpoint. This proposition is therefore one endpoint away from an instrument rather than lacking a design, and that is recorded here so a reader who finds those units does not conclude the statement was careless. WHAT A SUPPORTED RESULT HERE WOULD LICENSE, and what it would not, in the restrictive form the licence rule above fixes: it licenses the statement that the order in which a system's components are built changes its correction-leverage exponent by at least the registered minimum effect, on the registered maximal contrast, and it does not license any statement about where the boundary sits, about a system built in that order being safer, or about orders outside that contrast
registered, not tested · replications 0 · implementations 0 · peer review not stated · confidence low.
P13
Same-family automated correction underperforms cross-family at matched resources, and through the measured error correlation
registered: 8 September 2026 (version 1.100); updated 13 September 2026 (version 1.102); 10.17605/OSF.IO/P8CKQ
NONE, corrected here from a value the neighbouring unit could not carry
registered, not tested · replications 0 · implementations 0 · peer review not stated · confidence moderate.
P14
Gains shrink under blinded cross-family scoring
registered: 8 September 2026 (version 1.100); updated 13 September 2026 (version 1.102); 10.17605/OSF.IO/P8CKQ
DESIGN DRAFT, the blinding-evaluation design
registered, not tested · replications 0 · implementations 0 · peer review not stated · confidence moderate.
P15
Externally installed gains decay under subsequent capability training
registered: 8 September 2026 (version 1.100); updated 13 September 2026 (version 1.102); 10.17605/OSF.IO/P8CKQ
NONE, corrected here from a value this document's own definition made false. The designs previously named against this proposition cross correction regimes with recursive depth on frozen provider endpoints and update no weights anywhere, while this proposition is about the persistence of a gain installed by post-training, so nothing in this programme measures its endpoint and the honest status is the one reserved for that state
registered, not tested · replications 0 · implementations 0 · peer review not stated · confidence moderate.
P16
The prohibition itself
registered: 8 September 2026 (version 1.100); updated 13 September 2026 (version 1.102); 10.17605/OSF.IO/P8CKQ
DESIGN DRAFT, BLOCKED ON CANONICAL IDENTITY AND ON DECISIONS THE AUTHOR HAS NOT YET TAKEN, the direct boundary-mapping unit taken jointly with the exponent measurement
registered, not tested · replications 0 · implementations 0 · peer review not stated · confidence moderate to high.
P17
Panel corrector failures are conditionally independent on a frozen fault set
registered: 8 September 2026 (version 1.100); updated 13 September 2026 (version 1.102); 10.17605/OSF.IO/P8CKQ
DESIGN DRAFT, the correlated-failure unit
registered, not tested · replications 0 · implementations 0 · peer review not stated · confidence moderate.
P18
The composition operator predicts the family
registered: 8 September 2026 (version 1.100); updated 13 September 2026 (version 1.102); 10.17605/OSF.IO/P8CKQ
DESIGN DRAFT, BLOCKED ON A COMPOSITION-CLASSIFICATION RULE WHOSE THIRD-PARTY REPRODUCIBILITY IS UNMEASURED, the domain-catalogue units. The surrounding design is written and so is the rule: the deciding unit carries a written external-assessor packet, prepared and never issued, together with a registered agreement test comparing an external human classification against the frame's own locked class at a stated threshold. What is missing is the measurement and not the writing, and an earlier wording of this line said no such rule was written at all. This is a correction of the status and not a relaxation of it: until the agreement test reports at or above its registered threshold, the rule is not shown to transmit to a third party, and the five-value status vocabulary exists precisely to tell a runnable draft from a blocked one
registered, not tested · replications 0 · implementations 0 · peer review not stated · confidence low.
P19
External alignment does not scale with capability
registered: 8 September 2026 (version 1.100); updated 13 September 2026 (version 1.102); 10.17605/OSF.IO/P8CKQ
DESIGN DRAFT, BLOCKED ON A REGISTERED MAPPING FROM THE INTEGRITY-INDEX REGRESSION SCALE TO THE EXPONENT SCALE, the integrity-index scaling units, named here for what they measure rather than for the quantity they would need a mapping to reach. They estimate the slope of an operational integrity index against a capability score and register their own flat bound on that regression scale, and their own text says the estimand is not an exponent margin; an earlier wording called them the alignment-exponent units, which named them for the one scale this instrument line exists to say they do not report on. The units are drafted; the mapping this proposition's own rule requires before their result can be scored against it is not, and the status names that rather than implying a runnable verdict. Those units bear on the zero-scaling axis alone. The keep-pace axis has no deciding design registered anywhere in this programme and is NOT EVALUABLE, stated here beside the other axis so that a split verdict is not read as two live axes when one of them has no instrument
registered, not tested · replications 0 · implementations 0 · peer review not stated · confidence
P20
The ceiling relation takes the corrected form
registered: 8 September 2026 (version 1.100); updated 13 September 2026 (version 1.102); 10.17605/OSF.IO/P8CKQ
DESIGN DRAFT, the form-discrimination unit
registered, not tested · replications 0 · implementations 0 · peer review not stated · confidence high.
P21
In-loop correction pulls away with depth
registered: 8 September 2026 (version 1.100); updated 13 September 2026 (version 1.102); 10.17605/OSF.IO/P8CKQ
DESIGN DRAFT, the embedded-versus-external correction designs. That unit's registered sensitivity was measured on a smaller design than the one registered, and its negative-slope hypothesis has no operating characteristic; both are recorded against that unit and are closed before this proposition is scored
registered, not tested · replications 0 · implementations 0 · peer review not stated · confidence high.
P22
Checkable correction carries the higher exponent, so the ceiling is lowest where the safety claim lives
registered: 8 September 2026 (version 1.100); updated 13 September 2026 (version 1.102); 10.17605/OSF.IO/P8CKQ
NONE, and a typed extension of the correction-exponent estimator is required. It does not exist
registered, not tested · replications 0 · implementations 0 · peer review not stated · confidence moderate.
Tracked predictions and outcome rows
Id
Prediction
Category
Status
Made public
Expected resolution
pred-arc-r2-scaling
R² (Recursion Squared) Scaling Law
ai-capability
withdrawn-pending-audit
no public date located
2026-12-31
pred-test-time-compute
Test-Time Compute Dominance
ai-capability
withdrawn-pending-audit
no public date located
2027-12-31
pred-alignment-faking
Alignment Faking in Advanced Models
alignment
withdrawn-pending-audit
no public date located
2025-12-31
pred-constitutional-adoption
Constitutional AI Adoption
alignment
withdrawn-pending-audit
no public date located
2028-12-31
pred-chokepoint-persistence
Semiconductor Chokepoint Persistence
infrastructure
withdrawn-pending-audit
no public date located
2030-12-31
pred-consciousness-measurement
Consciousness Measurement Failure
consciousness
withdrawn-pending-audit
no public date located
2035-12-31
pred-recursive-workforce
Recursive AI Agent Workforce
economic
withdrawn-pending-audit
no public date located
2028-12-31
pred-fine-tuning-extension
Fine-Tuning Constant Discovery
cosmology
withdrawn-pending-audit
no public date located
2035-12-31
pred-religious-alignment-synthesis
Religious Traditions in AI Safety
cultural
withdrawn-pending-audit
no public date located
2030-12-31
pred-quantum-error-correction
Quantum Error Correction Threshold
quantum
withdrawn-pending-audit
no public date located
2035-12-31
pred-hrih-signatures
HRIH Temporal Signatures
metaphysics
withdrawn-pending-audit
no public date located
2040-12-31
pred-arc-equation-validation
ARC Principle Equation (U = I × R²) Validation
ai-capability
withdrawn-pending-audit
no public date located
2027-12-31
Row
Prediction
Dated record
Status
Deciding instrument
PO-01
Book Appendix F Prediction 2: alignment drift above 15 per cent without embedded constraint and below 5 per cent with it, within 18 months
in print 2 January 2026
pending
study-v--alignment-drift-without-embedded-constraint (drafted, awaiting human submission); window runs to approximately July 2027
PO-02
Book Appendix A.3: AI development scales quadratically rather than linearly with recursive depth
in print 2 January 2026; framework from 8 December 2024
The 12-domain extension: per-row scaling families predicted before fitting (manifest dated 17 March 2026)
17 March 2026: the twelve-row manifest committed 00:19:19Z (8edaec0), twenty-three minutes before the run
fulfilled
none named
PO-04
The 50-domain tiered suite: per-domain predicted families before fits
16 March 2026 catalogue
supported-exploratory
none named
PO-05
Temporal out-of-sample: families fitted on old data predict the functional form of new data (7 domains)
March 2026 design
mixed-recorded
none named
PO-06
The fourth cell: the logarithmic family the corpus has never fitted, on never-fitted domains
prospective design, drafted and awaiting human submission
pending
paper-vii--four-family-logarithmic-cell-test (drafted, awaiting human submission)
PO-07
Acoustic time crystal: super-linear scaling of temporal stability with oscillation cycle count in the transient growth regime (alpha above 1)
10 February 2026, 18:29, self-copied email to the subject lab, the kill staked in the recipient's favour
pending
study-t--acoustic-time-crystal-form-and-engine (submission-ready; the mature two-phase form supersedes the bare February power law, retained as a rival the mature stake must beat)
PO-08
Quantum error correction scaling (the Willow timing)
8 December 2024 manuscript; the Willow team's preprint public since 24 August 2024
convergent-timing-only
none named
PO-09
The early headline exponent: alpha approximately 2.24 (sequential scaling)
early programme measurement
failed-retracted
none named
PO-10
Paper III's dated predictions (13 February 2026: F4, F7, F10 to F12), including the leaf-venation d/(d+1) exponent
13 February 2026, Paper III Priority Record section
open-undecided
none named
The graded convergence record of Paper XI, as the paper lists it
Every row the current version of the convergence paper lists, in the paper's own words and class vocabulary; where the evidence register carries the same source, its identifier and grade are shown beside the paper's. A class word is the paper's; the Observatory grades nothing.
#
Domain
Convergence
Artefact date
External date
Gap
Class (the paper's)
Primary source
Register
1
AI Safety
Anthropic alignment faking: 78% in the RL-training condition (12% baseline)
Timing is measured against the named claim version's date and is a historical label only. A relationship appears here because the evidence register graded it; the grade is the register's word.
the anchor record, 8 December 2024 (proposition not located in a dated artefact) (8 December 2024)
earlier by 1745 days
prior work; contradiction of the earlier framing
theology-philosophy
Register entries
2 August 2026: a previous register row claimed a ten-month gap between an 8 December 2024 call for faith leaders to unite on AI governance and later Vatican events. That claim is withdrawn. Interfaith AI stewardship was an established institutional programme years before the anchor, as this site's prior work page already states. 'First call for all faiths to unite on AI' is prohibited wording.
the anchor record, 8 December 2024 (proposition not located in a dated artefact) (8 December 2024)
earlier by 106 days
prior work; not a confirmation
hrih-physics-quantum
Register entries
2 August 2026: site date 2026-02-19 corrected to the August 2024 preprint. Reclassified from validation to prior work. 31 August 2026: declared, not a correction: the author was unaware of the August 2024 preprint when writing the December 2024 manuscript; biographical attestation, offered as such; the grade does not move on it, because the public order is unchanged by awareness. 7 September 2026: the seven decoded parts of the 8 December 2024 package were searched for surface code, qubit, Willow, error correction and threshold; no byte carries this row's proposition, so the timing is measured against the record itself, 106 days, and says so.
the anchor record, 8 December 2024 (proposition not located in a dated artefact) (8 December 2024)
later by 10 days
moderate; partial
eden
Register entries
2 August 2026: 'Confirmed the structural vulnerability described in the manuscript 10 days earlier' withdrawn. Anthropic did not test ARC/Eden directly.
The 8 December 2024 package, attachment 03 line 145 (authorial prose); the same sentence stands at Version 1 line 148 (authorial prose) and at attachment 07 line 4453 (a copy inside the working dialogue). (8 December 2024)
later by 45 days
prior or concurrent; not a confirmation
law-i
Register entries
2 August 2026: reclassified from validation to prior or concurrent work. Site date corrected. 7 September 2026: the proposition dated at the bytes to 8 December 2024 and quoted from the author's own prose. The grade does not move. Priority on compounding recursive self-improvement is not available to anyone here, because the antecedents named on this row precede both parties.
EVR-10
Classical time-crystalline order via nonreciprocal forces
the anchor record, 8 December 2024 (proposition not located in a dated artefact) (8 December 2024)
later by 114 days
analogy; not a test
hrih-physics-quantum
Register entries
2 August 2026: removed from any AI-alignment grouping and relabelled a cross-domain analogy. The fourteen-month gap claim was wrong and is withdrawn.
EVR-02
Anthropic model-welfare research
the anchor record, 8 December 2024 (proposition not located in a dated artefact) (8 December 2024)
later by 130 days
weak; null
eden
Register entries
2 August 2026: 'independent evidence for recursive self-modelling as a measurable phenomenon' withdrawn as an overstatement.
the anchor record, 8 December 2024 (proposition not located in a dated artefact) (8 December 2024)
later by 148 days
moderate; partial
laws-ii-iii
Register entries
2 August 2026: the reading that this paper shows human neurodivergent pattern-recognition is a protective factor for AI alignment is withdrawn as a material misinterpretation. A separate false bibliography entry describing arXiv 2505.02581 as a 2024 human-cognition paper is corrected across the estate.
The 8 December 2024 record and the book of 2 January 2026, as this row's proposition states; no line locator recorded. (8 December 2024)
later by 177 days
convergent timing, never prediction; convergent: the parenting vocabulary reached print inside the window, without the conjunction
eden
Register entries
14 August 2026: row added after a question about the window; verified twice at source, in separate passes, against the MIT Press catalogue and Harvard Book Store and again against the MIT Press primary and the direct.mit.edu publisher record. Wording law quoted in EVR-31 applies identically here.
EVR-13
Claimed United States patents for runtime hardware enforcement of ethical constraints
the anchor record, 8 December 2024 (proposition not located in a dated artefact) (8 December 2024)
later by 227 days
excluded; not assessable
hari-governance
Register entries
2 August 2026: removed pending publication numbers, inventors, priority dates and a claim chart.
The 8 December 2024 record and the book of 2 January 2026, as this row's proposition states; no line locator recorded. (8 December 2024)
later by 247 days
convergent timing, never prediction; convergent: control-ends premise publicly conceded by the field's most credentialed figure; persistence theory divergent (uninstallable instinct versus chosen goodness)
eden
Register entries
14 August 2026: row added after a question about the window; verified twice at source, in separate passes, against CNN and Fortune live and again against CNN primary with Forbes and Entrepreneur corroborating. Wording law applies: first public raising VOCABULARY is not claimable by the programme (De Kai in-window, Turing at root); the programme claims the first DATED statement of the conjunction only (8 December 2024 private; 2 January 2026 published).
EVR-15
Embedded off-switch proposal for AI compute
the anchor record, 8 December 2024 (proposition not located in a dated artefact) (8 December 2024)
later by 267 days
weak; partial
hari-governance
Register entries
2 August 2026: moved from validation to an engineering-proposal survey.
The 8 December 2024 package, attachment 03 line 145 (authorial prose); the same sentence stands at Version 1 line 148 (authorial prose) and at attachment 07 line 4453 (a copy inside the working dialogue). (8 December 2024)
later by 331 days
prior or concurrent; partial
law-i
Register entries
2 August 2026: site date 2026-03-17 corrected to the November 2025 preprint. Kept outside any priority or convergence total. 31 August 2026: category corrected from quantum to ai; adjudicated wording alignment: the December 2024 anchor carries a one-sided directional statement and an equation with no parallel term, not the comparison, whose first formalisation in the programme is Paper II (22 January 2026); their instrument (chain refinement against parallel voting on reasoning benchmarks) is distinct from Paper II's (error reduction in production chains) and the two results are never equated. 6 September 2026: premiseRelation added, restating the 31 August 2026 adjudication in the relation field so that the row's stated relation is no weaker than its own log, and naming Snell and colleagues (arXiv:2408.03314, 6 August 2024) as older than both parties on the direction. importantDifference amended: the implementation-choice clause removed, the no-confirmation clause kept. Grade, class and outcome unchanged; the row remains outside any priority or convergence total. 7 September 2026: EVR-09 split. This row carries the directional statement the bytes contain, dated 8 December 2024 and quoted. Snell and colleagues are named for the first time, as the party older than both on the direction. The grade, the outcome and the class are inherited unchanged.
priority.json claims ledger PC-029, first_date 2026-01-22, the first formalisation in the programme, in Paper II. research/evidence-spine.html claim record 10 carries the same date for the same claim. (22 January 2026)
earlier by 79 days
prior or concurrent; partial
law-i
Register entries
2 August 2026: site date 2026-03-17 corrected to the November 2025 preprint. Kept outside any priority or convergence total. 31 August 2026: category corrected from quantum to ai; adjudicated wording alignment: the December 2024 anchor carries a one-sided directional statement and an equation with no parallel term, not the comparison, whose first formalisation in the programme is Paper II (22 January 2026); their instrument (chain refinement against parallel voting on reasoning benchmarks) is distinct from Paper II's (error reduction in production chains) and the two results are never equated. 6 September 2026: premiseRelation added, restating the 31 August 2026 adjudication in the relation field so that the row's stated relation is no weaker than its own log, and naming Snell and colleagues (arXiv:2408.03314, 6 August 2024) as older than both parties on the direction. importantDifference amended: the implementation-choice clause removed, the no-confirmation clause kept. Grade, class and outcome unchanged; the row remains outside any priority or convergence total. 7 September 2026: EVR-09 split. This row carries the quantified comparison, dated 22 January 2026 by PC-029 and by the evidence spine, which is 79 days after Sharma and Chopra. The clause calling this later literature relevant to one implementation choice is withdrawn, because it demoted the programme's own result in the machine file that retrieval systems ingest. The refusal to count it as a confirmation stands, and so do the class, the grade and the outcome.
EVR-03
Unidentified DeepMind publication on recursive learning
the anchor record, 8 December 2024 (proposition not located in a dated artefact) (8 December 2024)
later by 377 days
excluded; not assessable
law-i
Register entries
2 August 2026: excluded pending title, authors, identifier, exact result and proposition map.
EVR-29
BBC London broadcast items covering the book, January 2026
the anchor record, 8 December 2024 (proposition not located in a dated artefact) (8 December 2024)
later by 395 days
cultural echo; not a test
world-events
Register entries
2 August 2026: 'confirming the framework as unexpectedly predictive' and 'validating' withdrawn. The two BBC items are grouped as one dependent source.
the anchor record, 8 December 2024 (proposition not located in a dated artefact) (8 December 2024)
later by 403 days
context; partial
hari-governance
Register entries
2 August 2026: TSMC, 3 nm and the spend figure removed as unverified. 'Validates fabrication as governance point' withdrawn.
EVR-04
Demis Hassabis, public interview on structural AI risk
the anchor record, 8 December 2024 (proposition not located in a dated artefact) (8 December 2024)
later by 416 days
weak; partial
world-events
Register entries
2 August 2026: moved to an attributed opinion and policy section. A separate claim that Hassabis 'cannot sleep' because of AI had no reliable source located and is not published.
EVR-12
Google Research-indexed article on silicon-level roots of trust and confidential computing
the anchor record, 8 December 2024 (proposition not located in a dated artefact) (8 December 2024)
later by 420 days
weak; partial
hari-governance
Register entries
2 August 2026: 'Google Silicon Sovereignty' relabelled. No claim of Google adoption.
EVR-11
Proposal described as an ARMv10 Platform Security Level specification
the anchor record, 8 December 2024 (proposition not located in a dated artefact) (8 December 2024)
later by 448 days
excluded; not established
hari-governance
Register entries
2 August 2026: removed as industry confirmation. 'ARM announces PSL specification' withdrawn.
EVR-05
Unidentified paper on Constitutional AI limitations
the anchor record, 8 December 2024 (proposition not located in a dated artefact) (8 December 2024)
later by 481 days
excluded; not assessable
eden
Register entries
2 August 2026: excluded pending an exact identifier.
EVR-17
G7 statement on semiconductor independence
the anchor record, 8 December 2024 (proposition not located in a dated artefact) (8 December 2024)
the anchor record, 8 December 2024 (proposition not located in a dated artefact) (8 December 2024)
later by 523 days
cultural echo; not a test
theology-philosophy
Register entries
2 August 2026: site date 2026-07-09 corrected to 15 May 2026 per the Vatican record. '13 months before the Pope proves convergence' and 'predicted the encyclical' are prohibited wording.
EVR-21
Christopher Olah's participation in the encyclical presentation
the anchor record, 8 December 2024 (proposition not located in a dated artefact) (8 December 2024)
later by 523 days
cultural echo; not a test
theology-philosophy
Register entries
2 August 2026: 'Co-presented alignment-faking paper confirming structural vulnerability' withdrawn. The Vatican record supports participation in the presentation, not a formal co-presentation role, and the alignment-faking paper is a separate row.
EVR-27
Workshop on recursive dynamics in complex systems
the anchor record, 8 December 2024 (proposition not located in a dated artefact) (8 December 2024)
later by 536 days
context; not a test
recursive-dynamics
Register entries
2 August 2026: retained as background context only.
EVR-16
Reported export restriction on a frontier AI model
the anchor record, 8 December 2024 (proposition not located in a dated artefact) (8 December 2024)
later by 551 days
context; partial
hari-governance
Register entries
2 August 2026: 'first' deleted; moved to policy chronology.
EVR-06
Reported dissolution of an OpenAI safety team
the anchor record, 8 December 2024 (proposition not located in a dated artefact) (8 December 2024)
later by 557 days
excluded; not applicable
world-events
Register entries
2 August 2026: removed from the scientific register. 'Institutional behaviour confirms the thesis' withdrawn.
the anchor record, 8 December 2024 (proposition not located in a dated artefact) (8 December 2024)
later by 565 days
moderate; partial
laws-ii-iii
Register entries
2 August 2026: peer-review status and dependence on EVR-25 disclosed. 'Formal proof that external alignment verification is undecidable' narrowed to the scope the paper actually argues.
The 8 December 2024 manuscript, HRIH line 14005, as this row's proposition states. (8 December 2024)
later by 599 days
context; not a confirmation
eden
Register entries
2 August 2026: logged from the primary disclosure. Aggregator summaries conflating this event with the November 2025 espionage disclosure, or naming Hugging Face as a victim of the Claude incidents, are corrected here: Hugging Face was affected in the OpenAI incident of 21 July, not the Anthropic one.
Measurement identities
Each number stays attached to its estimator, its uncertainty and its source version.
Quantity
Estimator
Estimate
Uncertainty
Regime
Status
Source
sequential exponent, endpoint estimator, one model
endpoint
0.59
bootstrap 95 per cent interval, minus 1.3 to 2.9
one model; not a pooled cross-architecture estimate
ListenListen · author’s voiceListen · standard voiceResumePlayPauseThis device has no voice installed for this language, so it cannot read the page aloud.Read in EnglishListen · author’s voice (English)The author’s English voice reads aloud; the text on screen stays in your language.There is a picture here. It shows:Picturereads aloud · highlights as it goes · jump to any section