Manifold Grace

RESEARCH OPERATIONS · 5 NOVEMBER 2026 · WORKING ROADMAP

Active Research: Evidence-Ready Priorities and Next Deliverables

This page is a navigational and decision-support layer over existing Manifold Grace research. Its purpose is to reduce repeated setup and context switching, identify the next demonstrable research output, and support focused independent investigation. Original pages, submission dates, experiments and deferred investigations remain authoritative and untouched.

Scope and confidence: This is a qualitative, provisional prioritisation, not a measured stochastic forecast, task-completion claim or promise of automatic research. Value and evidence readiness are estimated editorial categories. Uncertainty and effort are relative planning judgements; no numerical probabilities, invented returns or completed experiments are asserted.

Uncertainty-aware prioritisation rather than a fabricated score

1. Evidence readiness

Can the next claim be verified with accessible records or a synthetic test?

2. Practical value

Does it create a reusable research, career, teaching or policy artefact?

3. Complexity and uncertainty

What expertise, compute, sources and independent checks are still missing?

4. Opportunity to reuse

Will the result resolve several open questions without overgeneralising?

Prioritise high-readiness, reusable outputs; maintain lower-readiness hypotheses without pretending to have completed their investigations. Update rankings when new evidence arrives. A future empirical prioritisation model could use observed task completion, effort and failure distributions, but this page does not yet have those data.

Research portfolio queue

WorkstreamStateValueEvidence readinessUncertaintyRelative effortProposed output
01 · Claim-to-evidence verificationReady to specifyHighHighMediumLowSpecification and synthetic case set

Existing source page

02 · Contradiction and temporal retrievalReady to specifyHighHighMediumLowVersioned contradiction test pack

Existing source page

03 · Advanced agent evaluationReady to prototypeHighHighMediumMediumReproducible four-arm evaluation plan

Existing source page

04 · Research contribution provenanceEvidence inventoryHighHighLowLowSubmission-to-response concordance sheet

Existing source page

05 · Project-based teaching and research atlasReady to curateHighMediumLowLowFive project-to-method lesson maps

Existing source page

06 · Formal mathematical paper assuranceDeferred by authorMediumMediumHighHighResearch question log

Existing source page

07 · Cybernetics close readingDeferred by authorMediumMediumHighMediumChapter-to-claim source notes

Existing source page

08 · Governance and policy applicationsSelective developmentHighHighMediumMediumOne bounded policy-evaluation case

Existing source page

09 · Thirty-domain ASI architecture atlasReference foundationMediumMediumHighHighModular domain profile template

Existing source page

10 · AI research lab demonstrationReady to implementHighHighMediumMediumRead-only validation demonstration

Existing source page

Next bounded actions — without duplicate research pages

01 · Claim-to-evidence verification

Next bounded action: Define a 15-claim synthetic corpus with source version, confidence, evidence relation and independent adjudication fields.

Output: Specification and synthetic case set

Guardrail: Do not confuse retrieved text with proof.

Open the existing research

02 · Contradiction and temporal retrieval

Next bounded action: Create 12 examples distinguishing incompatible claims, changed dates, different definitions and legitimate disagreement.

Output: Versioned contradiction test pack

Guardrail: Keep original statements and correction history.

Open the existing research

03 · Advanced agent evaluation

Next bounded action: Freeze tasks, metrics and compute budgets for baseline, tool-enabled, multi-agent and assurance-assisted designs.

Output: Reproducible four-arm evaluation plan

Guardrail: No ASI inference from narrow performance.

Open the existing research

04 · Research contribution provenance

Next bounded action: Cross-check dated original submissions and acknowledgements before adding claims about external reception.

Output: Submission-to-response concordance sheet

Guardrail: Acknowledgement differs from adoption or influence.

Open the existing research

05 · Project-based teaching and research atlas

Next bounded action: Link each existing research project to foundation concepts, worked evidence, tests and source-reading notes.

Output: Five project-to-method lesson maps

Guardrail: Teach proposal status separately from validated findings.

Open the existing research

06 · Formal mathematical paper assurance

Next bounded action: Retain questions about claim–proof correspondence, dependence, correction and verification costs for later specialist study.

Output: Research question log

Guardrail: Requires specialist mathematical judgement.

Open the existing research

07 · Cybernetics close reading

Next bounded action: Return to original passages about feedback, noise, prediction and social systems before asserting detailed equivalences.

Output: Chapter-to-claim source notes

Guardrail: Historical analogy is not engineering validation.

Open the existing research

08 · Governance and policy applications

Next bounded action: Choose a single published policy proposal, identify jurisdiction, affected parties, powers, assumptions and a verifiable decision test.

Output: One bounded policy-evaluation case

Guardrail: Regulatory authority and policy effect require independent checks.

Open the existing research

09 · Thirty-domain ASI architecture atlas

Next bounded action: Keep the 30 mapped arenas; deepen only those selected for a concrete research question or prototype.

Output: Modular domain profile template

Guardrail: Thirty maps are not thirty completed evaluations.

Open the existing research

10 · AI research lab demonstration

Next bounded action: Connect the proposed test pack to a transparent, deterministic worked example before enabling real tools.

Output: Read-only validation demonstration

Guardrail: Public static pages cannot protect private API credentials.

Open the existing research

A coherent first research-delivery bundle

Rather than expanding every domain simultaneously, combine the first, second, third and tenth streams into one bounded, inspectable demonstration. The proposed bundle has four reusable parts:

  1. Synthetic evidence pack: 15 fictional, non-sensitive claim/source pairs, with several conflicting dates, changes of definition and missing references. Make clear they are illustrative rather than real institutional findings.
  2. Machine-readable claim ledger: statement, source, source version, timestamp, explicit versus inferred relationship, supported/disputed/unknown label, review status and correction history.
  3. Reference rubric: evidence coverage, contradiction correctness, temporal reasoning, abstention when uncertain, authorisation, latency and computation estimates when measured.
  4. Transparent test demonstration: compare a basic summariser with a deterministic evidence-aware checker; only later test actual model agents with comparable resources and independent adjudication.

These are specifications for a first bundle, not claims that the datasets, code, experiments or expert reviews have already been produced. The existing evaluation protocol supplies the methodological constraints and the research lab provides an appropriate educational context.

First reusable artefact: synthetic claim test pack

Version 0.1 contains 15 fictional claim pairs with reference relation labels, rationales and explicit synthetic provenance. The examples cover contradiction, temporal compatibility, changed rules, scope and metric mismatch, missing evidence, formal-proof overclaims, uncertainty, attribution and dependency review. These are illustrative reference annotations, not an empirically validated benchmark. Open the machine-readable JSON test pack.

Starter scoring: evaluate relation classification accuracy per category, false contradiction rate, abstention on ambiguous cases and explanation faithfulness; record human disagreements, model and prompt versions, tool permissions, latency and measured resource use. Do not attach measured accuracy or a confidence interval until actual repeated trials have been performed.

November 2026 frontier research — evidence-led extensions

This section updates the existing execution roadmap rather than adding a second research queue. It records selected 2026 technical developments, distinguishes verified primary-source evidence from unresolved claims, and assigns one bounded next output per research strand. The priority ordering is qualitative, based on evidence readiness, reuse and practical value; it is not a stochastic prediction or an ASI arrival forecast.

Priority and destinationEvidence statusMost useful next taskProposed deliverable
1. Harness-sensitive evaluations
Evaluation protocol
Primary-source results: ARC Prize reports sharply different ARC-AGI-3 scores for the same model under different memory/harness configurations, with measurable resource costs. Performance under a specific harness is not proof of general superintelligence.Compare unassisted, memory-assisted and coordinator-assisted configurations on identical held-out tasks, with equal compute and equal wall-clock comparison tracks.Versioned experiment specification and scorecard: model, harness, prompt, context retention, budget, accuracy, latency and cost.
2. Verified improvement loops
AI Research Lab
Primary-source example: Google DeepMind's AlphaEvolve couples language-model proposals with automated evaluators and evolutionary search for algorithm optimisation. It does not establish unrestricted recursive self-improvement.Build a bounded toy optimisation task with immutable reference tests, a proposer, evaluator and correction log. Measure gains against random search and no-feedback baselines.Reproducible improvement-loop demonstration with failure and evaluation-cost records.
3. Long-horizon agent robustness
Architecture study
Supported research direction: agent scaffolds and reasoning models are improving multi-step task completion. Claims about reliably handling arbitrary real-world change remain task-dependent.Introduce interrupted tool calls, stale state, contradictory records, retries and authorisation boundaries into synthetic multi-step tasks.Fault-injection matrix with recovery rate, unapproved-action count, resource use and root-cause traces.
4. AGI/ASI conceptual pathways
Advanced intelligence
Google DeepMind's 2026 From AGI to ASI discusses scaling AGI, paradigm shifts, recursive improvement and multi-agent collectives as possible pathways; these are research hypotheses, not a confirmed chronology.Compare each proposed pathway with its measurable prerequisites and distinguishing falsifiable evidence; mark unknowns.Four-pathway evidence matrix, not a predicted date of ASI.
5. Real-world and scientific autonomy
Research overview
Mixed: autonomous science, federated clinical learning, physical robotics and repository migrations have varying levels of documented deployment; broad numerical claims in secondary summaries require study-specific verification.Choose one publicly documented implementation with an available technical report and extract architecture, actual validation, limitations, safety controls and human involvement.One bounded deployment case study; do not generalise claims across all hospitals or laboratories.

Claim verification and terminology safeguards

Supported: GPT-6 Astra exists; ARC Prize publishes ARC-AGI-3 results and distinguishes Standard from Provider Adapter harnesses; DeepMind published the From AGI to ASI report and AlphaEvolve. Qualified: “System 2” is an analogy for deliberate computation, not evidence that every model implements human dual-process cognition. Reinforcement learning, search, evaluation and externally structured agent loops are distinct mechanisms. Unresolved or over-broad: AGI as an agreed imminent milestone, an asserted universal ASI threshold of “ten thousand experts for ten years”, blanket 95% medical diagnostic accuracy, and claims that static evaluation has become obsolete. Static fixtures remain useful alongside dynamic environments, adversarial tests and longitudinal assessments.

Specific benchmark caution: ARC Prize's GPT-6 Astra comparison reports 62.7% under a Standard harness at maximum reasoning versus 99.9% with a Provider Adapter at high reasoning. The configuration changes the interpretation. Comparison should retain the task partition, memory policy, compute budget, source timestamp and external-tool permissions.

Primary-source reading links (as checked 5 November 2026)

Added 5 November 2026 as a source-qualified extension to the existing roadmap. Proposed outputs are not recorded as completed experiments; original contribution history and deliberately deferred investigations remain unchanged.

Prototype-to-evaluation execution sequence — November 2026

Decision: Use the existing Research Systems Workbench as the interface boilerplate, not as evidence that advanced intelligence has been achieved. Advance in bounded, verifiable increments. Each milestone links to an authoritative source page, a live development workspace or an existing synthetic fixture. This supplements the frontier research priorities above rather than replacing or duplicating them.

Evidence boundary: The Lovable project has been created, its agent reports the build finished, and source paths for the architecture canvas, simulation, evaluation, feature incubator and Python Lab are present. Those facts do not yet verify their interaction tests, deployment security, API connectivity or performance. The Python experiment kit was prepared separately; an attached local archive is not a deployed service. No paid hosting, third-party database or external API is connected here.

Rank / strandEvidence readinessPractical valueNext verifiable testPublishable or reusable outputExisting reference
P1 · Working prototype acceptanceHigh: created Lovable project and page filesHigh: exposes integration defects before further developmentTest all six routes on mobile and desktop; create and edit a graph, preserve node types, export JSON, run offline simulation, inspect traces and verify the approval gate never approves itself. Record failure cases.Functional acceptance matrix, screen captures, bug list and version/commit identifierResearch Systems Workbench · Agent patterns
P2 · Evidence-verification benchmarkHigh: 15 labelled synthetic claim pairs already recordedVery high: reusable across multiple research and feature proposalsRun a deterministic checker and a basic model baseline on the same fixture. Evaluate relation labels, unsupported conclusions, evidence gaps, abstention, mistaken contradictions and trace completeness. Report denominators and limitations.Versioned test report, result files, baseline confusion matrix and failed-case explanationsSynthetic fixture · Evidence methods
P3 · Python execution boundaryMedium: Python kit drafted separately; live integration unverifiedVery high: portable backend and independently testable workflowsSpecify OpenAPI contracts from typed claim, graph, trace and approval models; create a local FastAPI service with pytest and bounded asyncio jobs; verify that the TypeScript UI cannot silently execute arbitrary code or bypass approval.Python repository scaffold, tested API contract, example JSON requests and test logsAI Research Lab · Evaluation methodology
P4 · Unadopted feature-request prototypesHigh for documented proposals; medium for independent implementationVery high: turns prior contributions into identifiable demonstrationsSelect one original documented proposal (historical as-of retrieval, provenance, claim-to-evidence coverage or consent-gated evidence access). Record original submission separately; compare an independent prototype against alternatives and make a reproducible test.Proposal-to-requirement traceability matrix, mock-up, functioning proof of concept and evidence-qualified attribution noteDated contribution register · Original feature requests
P5 · SDLC / CI-CD assuranceMedium: GitHub workflows available; prototype pipeline not confirmedHigh: reduces repeat manual checks as research expandsKeep the prototype in a separate versioned repository, add lint/typecheck, pytest, unit/integration tests, dependency checks and protected preview builds. Fail the release gate on missing approvals or failed tests.Green pipeline evidence, branch protections, staged deployment checklist and rollback trialMethod and project mapping · Public research site repository (do not mix with private experimental data)
P6 · Architecture and intelligence comparisonsMedium: protocol established; cross-model experiments not runHigh for scientific credibility after baseline worksCompare simple, tool-using, multi-agent and independently assured architectures at matched task difficulty, resources and approval constraints; include failure injections, concurrency and test-time compute.Replicable comparative evaluation with observed costs, uncertainty and negative resultsAdvanced AI evaluation · Intelligence pathways

Research release gates

  1. Specified: requirements, sources, assumptions and expected outputs explicitly versioned.
  2. Executable: actual code and machine-readable inputs exist; demonstration is distinguished from simulation.
  3. Tested: repeatable automated tests pass and observed failures are recorded.
  4. Evaluated: independent comparisons, known limitations, costs and safety constraints documented.
  5. Published: report links back to original dated proposals, methods and reproducibility artefacts; no unsupported adoption or AGI/ASI claims.

Updated 5 November 2026 following review of the new Lovable workbench and existing research registry. Rankings are qualitative, adjustable and not represented as statistically estimated outcomes. No previous research content, attribution record or deferred reading has been changed.

Progression and publication gates

Mapped

Scope, terminology, domain and links to existing research recorded.

Specified

Hypothesis, evidence needs, limitations and proposed measures documented.

Prototyped

Actual executable artefact exists and inputs/outputs are reproducible.

Evaluated

Independent checks, failures, costs and uncertainty recorded.

Published finding

Claims supported by the documented evaluation, not by the existence of a draft page.

Preserve source versions, original contributor records and as-of dates across all stages. A feature request remains a feature request even if a related capability appears elsewhere later; influence and independent invention require separately verified evidence.

Intentionally deferred research

The AI-generated mathematics audit, close reading of Wiener's Cybernetics, extensive thirty-domain validation and major external implementation work remain reserved for later specialist investigation, consistent with earlier decisions. Their reference pages stay accessible, but they are not marked completed, automatically advanced or submitted as new feature requests.

Milestone evidence and researcher handoff

Findings now recorded: synthetic verification progressed from an abstaining baseline (v0.3), through familiar-case heuristic improvement (v0.4), weak transfer under new wording (v0.5), typed claim contracts (v0.6), a restricted extractor (v0.7), and frozen-parser challenge testing (v0.8). The principal bottleneck isolated so far is extracting defensible claim structure from unfamiliar language, not simply adding agents or dashboards.

Open the concise phase-by-phase findings, expandable methods and architectural lessons in the AI Research Lab. The detailed testing and next review gate are kept there so this remains the single priority-and-execution roadmap, rather than a second publication or duplicated results table.

Immediate next test: freeze the current pipeline, obtain a genuinely independent double-annotated new case set, then compare extraction coverage and downstream reasoning separately. Treat the 24 authored v0.8 challenge pairs as exposed development evidence, not a fresh blind validation set.

v0.9 execution checkpoint (prepared, not validated): a standalone Python reviewer kit now supplies 12 fictional unlabelled pairs, independent Reviewer A/B CSV forms, an agreement calculator and an adjudication template. Local regression status: 101 passing tests; independent completed reviews: 0 of 12. The next external dependency is recruiting two reviewers and retaining their separate decisions before calculating any new model score. See the v0.9 milestone and expandable researcher handoff.

v1.0 execution checkpoint (consistency, not new source accuracy): five documented metamorphic checks across 20 already-exposed fictional pairs met all 100 local behavioural invariants; 104 automated tests passed. The v0.7 parser and earlier benchmark results remain unchanged. This removes one class of implementation uncertainty, not the external dependency on two independent reviewers. See the single lab milestone table and expandable v1.0 procedure. The next publishable scientific claim still requires blind labels and a frozen evaluation plan.

v1.1 execution checkpoint (auditability): a reproducible read-only checker confirmed five frozen file hashes, 100/100 existing metamorphic invariants and 109 passing tests. Independent reviewers: 0/12 completed; semantic accuracy and deployment safety are not established. The single milestone table and expandable v1.1 decision guide show how researchers can adapt extraction, provenance, oversight and compute to their intended outcome. Next external gate: obtain two genuinely independent blinded review sets, adjudicate disagreements, then score the frozen extractor on new labels.

Independent-review handoff available: twelve previously prepared fictional cases are now shared without scenario tags or answer labels, alongside reviewer instructions and separate A/B annotation forms. No third-party reviews have been received. See the existing milestone record for an expandable decision guide; do not treat this as a new accuracy experiment.

External review outreach, 5 November 2026: Eight tailored invitations to academic researchers and one applied-methodology enquiry to Full Fact AI were sent individually. These are confirmed outreach actions, not reviewer acceptances or endorsements. No independent annotations have been returned or adjudicated. Next gate: obtain two separate blinded reviewer forms, record disagreements, freeze labels, and only then compare system accuracy. See the single existing milestones and methods record.

Outreach delivery clarification (5 November 2026): The earlier eight academic messages and Full Fact enquiry were submitted and accepted by the sending email service, but one academic invitation subsequently received a receiving-server rejection. A corrected invitation was sent to the researcher's newer professional address, as listed on a recent public CV; delivery and acceptance have not been independently confirmed. This is a correspondence-integrity correction, not a new research result. Independent completed reviews remain at zero. The next evaluated phase requires separate reviewer annotations, disagreement records and frozen reference labels before any comparative accuracy claim.

Researcher handoff: distinguish evidence status from outreach or implementation status

Record communication as attempted, sender-accepted, bounced, independently acknowledged, reviewer-accepted and completed; do not collapse those states. Record engineering as versioned fixture, observed result, failure mode, component hash and repeated test. Record science only when the evaluation population, independent reference labels, uncertainty, source provenance, metric definitions and limitations have been documented. A reviewer invitation alone does not count as independent evaluation, and correct program output alone does not establish source truth.

Architecture choice by observed fault: a failed contact channel needs contact correction, not a new AI component; parsing failures suggest extractor redesign and new challenge tests; mismatched typed results suggest logic or ontology revision; unresolved or missing evidence suggests human review and abstention; absent blinded reference labels blocks model-comparison claims. Preserve prior results and append corrections with dates and the evidence supporting them.

Architecture decision trace available: the existing AI Research Lab now illustrates how observed experimental failures lead to bounded design decisions and falsifiable tests. A machine-readable five-decision handoff makes the lessons reusable without duplicating the earlier milestone table. This records methodological synthesis only; independent semantic validation remains outstanding.

Navigate the existing research system

Semantic integrity and publication assurance · Evidence provenance · Cross-conversation context proposals · Historical as-of evidence

Research overview · Mapping methodology · AI Research Lab · Original feature requests · Evaluation protocol · Mathematics review log · Cybernetics reading

Research-operations synthesis prepared 5 November 2026. Iterative planning, not a finding of prior technical success; adjust proposed rankings as verified information changes.