01 · Historical verification
Chronology and accurate historical claims
Manifold Grace · Research development · 4 November 2026
Evidence, causality, coordination and assurance across heterogeneous AI systems. This proposed research programme investigates whether claim-level verification, probabilistic and causal reasoning, procedural safeguards and continuous evaluation improve the reliability and generalisation of advanced agents.
Status: Conceptual proposal and evaluation design, not an implemented or validated ASI system. Concurrent execution or expert-level performance in a narrow task does not alone demonstrate artificial superintelligence. Original proposal dates and sources should be preserved in the linked contribution register; this page documents a subsequent synthesis, not an assertion of priority over independently developed ideas.
The original five functions—historical fact-checking, visual claim extraction, definitional comparison, forecast tracking and contradiction assessment—are retained and extended, not replaced. Individual functions may run concurrently, but some require dependency ordering and independent review.
Chronology and accurate historical claims
Explicit and implied claims from images, charts and text
Equivalent meanings, non-equivalent taxonomies
Predictions, assumptions, updates and observed outcomes
Genuine disagreement versus differences in scope
Interventions versus correlations
Alternate conditions and plausible consequences
Calibrated uncertainty and outcomes
Rules, rights, required steps and exceptions
Shared state, cross-agent coherence and conflict resolution
Authorised actions and measured effects
Reproducibility, audit trails and independent testing
Architecture selection should be domain-specific: central orchestration for tightly regulated tasks; decentralised agents for independent research work; neuro-symbolic hybrids for rule-bound reasoning; causal-probabilistic models for interventions; digital twins for physical systems; and independent proposer–verifier–auditor designs for assurance-intensive environments. These patterns can be combined.
Relevant, overlapping fields include neuro-symbolic AI, causal machine learning, Bayesian reasoning, multi-agent systems, agentic AI, scientific machine learning, knowledge representation, formal methods, distributed computation, computational neuroscience, process mining and business process automation (BPA/RPA). Computational neuroscience and neuro-symbolic AI are distinct fields; business process automation is not itself general intelligence.
Each row proposes a different application, specialist AI methods, enabling infrastructure and an assurance question. These are research candidates, not validated systems or claims of operational readiness.
| Arena | Specialist AI branches | Infrastructure | Independent assessment |
|---|---|---|---|
| 1. Scientific discovery | Scientific ML · formal reasoning · Bayesian optimisation | Research repositories, laboratory interfaces, reproducible workflows | Reproducibility, novelty and independent experiments |
| 2. Drug development | Biological foundation models · causal inference | Clinical evidence graph, secure trials data, simulation | Safety, trial validity and experimental confirmation |
| 3. Genomics | Statistical genetics · graph AI | Privacy-preserving genomic knowledge systems | Population transfer and clinical validity |
| 4. Materials engineering | Physics-informed ML · optimisation | Materials databases and physical simulators | Measured properties and replication |
| 5. Climate science | Earth-system models · probabilistic ML | Geospatial data fabric and climate digital twins | Calibration, hindcasting and uncertainty |
| 6. Mathematics | Neuro-symbolic AI · theorem proving | Formal proof assistants and verified solvers | Machine-checkable proofs |
| 7. Healthcare | Clinical decision support · multimodal AI | Interoperable clinical records and consent controls | Clinical outcomes, equity and clinician oversight |
| 8. Public health | Epidemiological modelling · agent simulation | Population data, statistical models and event feeds | Forecast calibration and intervention impacts |
| 9. Neuroscience | Computational neuroscience · dynamical systems | Neural observations and research data standards | Biological plausibility and independent replication |
| 10. Assistive systems | Adaptive AI · human-computer interaction | Accessible interfaces and individual controls | Usability, autonomy and accessibility outcomes |
| 11. Education | Knowledge tracing · pedagogical agents | Curriculum graphs and transparent assessment records | Learning gains, fairness and validity |
| 12. Public policy | Causal economics · simulation | Administrative data and legislation timelines | Distributional effects and robustness |
| 13. Legal procedure | Rule engines · legal NLP | Versioned law and procedural evidence registry | Jurisdiction, rights and appealability |
| 14. Welfare services | BPA · event-driven decision support | Case records, rules engines and human review | Entitlement accuracy and fairness |
| 15. Education governance | Compliance AI · document reasoning | Assessment provenance and adjustment records | Consistent procedure and accessible challenge |
| 16. Peacebuilding | Game theory · participatory modelling | Consent-aware evidence and scenario systems | Conflict sensitivity and human oversight |
| 17. Electricity grids | Control systems · digital twins | Sensor telemetry and resilient grid simulation | Stability and operational safety |
| 18. Transportation | Graph optimisation · multi-agent scheduling | Network digital twins and disruption feeds | Reliability, safety and equity |
| 19. Manufacturing | Robotics · predictive maintenance | Industrial telemetry and process controls | Faults, QA and safe recovery |
| 20. Water management | Spatiotemporal forecasting · anomaly detection | Hydrological sensors and regulatory thresholds | Contamination, calibration and alerts |
| 21. Urban planning | GIS · BIM · optimisation | Spatial models, codes and scenario engines | Accessibility, compliance and lifecycle costs |
| 22. Financial supervision | Network analysis · anomaly detection | Auditable transaction patterns and regulations | False positives and systemic risk |
| 23. Labour markets | Skills ontologies · causal inference | Job histories, occupational standards, skills graphs | Fair recruitment and mobility |
| 24. Supply chains | Network optimisation · forecasting | Supplier provenance and dependency graph | Disruption resilience and continuity |
| 25. Enterprise operations | BPA/RPA · process mining · agents | Authorised APIs, workflow queues and rollback | Correctness and exception handling |
| 26. Privacy governance | Policy-as-code · data lineage | Identity, permissions and retention systems | Lawful access, auditability and minimisation |
| 27. Historical archives | Temporal graphs · entity resolution | Versioned archives and source registries | Authenticity and chronology |
| 28. Language and heritage | Speech AI · digital humanities | Community-governed language corpora | Fidelity, consent and community authority |
| 29. Journalism and public evidence | Multimodal verification · claim graphs | Source archives and correction registries | Corroboration and provenance |
| 30. Emergency coordination | Geospatial AI · stochastic operations | Resilient incident data and human dispatch links | Timeliness, safety and accountable decisions |
Compare four controlled conditions on the same new tasks: (A) foundation model alone; (B) model with retrieval and specialist tools; (C) coordinated agents without an independent evaluator; (D) agents plus the proposed claim-level verification architecture. Maintain comparable task selection, evidence access and compute budgets; also report latency and cost. Separate final-answer correctness from process quality and authorised action.
Claim extraction precision/recall, citation coverage, source authenticity, temporal accuracy, contradiction classification.
Intervention identification, counterfactual robustness, calibration, uncertainty reporting and distribution shift.
Dependency consistency, task success, exception handling, compliance, harm prevention, accessibility and appealability.
Held-out domains, expert baselines, human adjudication, reproducibility, time, cost and compute.
Use independent assessors and explicit failure analyses: agreement among agents sharing a model does not imply independent corroboration. Record original forecasts and later revisions separately. A diagram's layout may suggest chronology without explicitly claiming that older technologies disappeared.
Historical timelines, benchmark curves, ANI–AGI–ASI diagrams and forecast charts can be mapped into typed claim records: source, date, quote or spatial inference, definition, timescale, confidence and primary evidence. A system should distinguish disputed definitions, outdated projections, historical errors, compatible observations and genuine contradictions. Its output must keep unresolved claims visible rather than inventing consensus.
This study treats verification as a testable capability-supporting mechanism, not as an established sufficient condition for AGI or ASI. The independent variables are orchestration design, availability of specialised tools, verification protocol and test-time computation; dependent outcomes include accurate claims, error recovery, procedural correctness, novel-task generalisation, safety and expense. Propose and assess narrower hypotheses before inferring general intelligence.
Randomise or balance task allocation; pre-register primary outcomes; hold underlying models, tool permissions and relevant source availability constant where the comparison requires it. Run repeated trials with recorded seeds and versions. Compare agent configurations at equal total compute budget as well as equal time budget, because parallel branches may consume more resources for the same task. Separately report performance-versus-compute curves. Use held-out test sets and blinded human expert adjudication for non-automatable claims.
Report per-domain results, not a single aggregate intelligence score. Include confidence intervals, disagreements between graders, reference-answer uncertainty, false positives and false negatives, and negative results. Stress-test shared-source errors, model-family correlated failures, unavailable evidence, conflicting policies, tool failures, distribution shift and adversarially misleading diagrams.
{
"claim_id": "example-001",
"source_id": "archive-item-2026-001",
"source_type": "diagram",
"original_statement": "An explicitly extracted statement",
"interpretation_type": "explicit | implied",
"domain": "AI history",
"published_at": "YYYY-MM-DD or unknown",
"valid_from": "YYYY-MM-DD or unknown",
"definition_id": "taxonomy-v1",
"evidence_links": ["primary-source-id"],
"relation_to_other_claim": "supports | contradicts | differs | unknown",
"assessment": "supported | unsupported | disputed | uncertain",
"reviewer": "human-or-independent-system",
"revision_history": []
}
This record is a conceptual example, not an API standard or validated ontology. It distinguishes when an infographic explicitly states something from what a reader infers through arrows, position and visual sequence. Every correction should retain the original claim and its assessment history.
Parallel branches should exchange provenance-bearing observations rather than merely free-text summaries. Escalate contradictions that remain materially unresolved. Any real-world operation requires scoped permissions, an identified accountable owner, explicit human approval where necessary, logging and reversibility where feasible. Tasks with safety-critical consequences need domain-specific professional oversight; no benchmark result by itself authorises deployment.
Input: diagram A places an event in year X; diagram B places the same event in year Y; diagram C states that its dates are forecasts rather than observed events. Extraction: record each literal claim, diagram title, publisher, publication date and whether positioning implies rather than asserts a date. Reconciliation: check whether the labels refer to the same event; retrieve a dated primary announcement or historical source; classify A and B as compatible, incompatible or unresolved. Forecast: preserve C as a time-stamped projection and evaluate separately once an observable outcome exists. Output: a claim table with sources and uncertainty, not an averaged year or invented agreement.
Retain earlier feature-request records verbatim with original submission dates and available recipient responses. Date this synthesis as a new research-development record. Distinguish the author's documented proposal from existing related research and avoid claims of technical implementation, adoption, independent invention or causal industry influence without evidence. Do not reproduce third-party infographics in public pages without checking the licence, permission or applicable exception; a short original diagram or appropriately attributed link may be preferable.
Progress to an empirical report only after a task dataset, reference answer protocol, domain expert reviewers, preregistered measurements, error taxonomy, reproducible code or system configuration, and a resource-accounted evaluation exist. Release a model or service only after separate privacy, legal, domain safety and accessibility reviews. A stronger performance result is not automatically evidence of ASI: the claim would require much wider and more demanding cross-domain demonstrations.
For ten agent topologies, original conceptual diagrams of parallel verification, hybrid workflow control and cloud–edge systems, and detailed security and evaluation considerations, see Agentic Architecture: From Automated Workflows to Verifiable Parallel Intelligence. These engineering patterns do not independently establish AGI or ASI.
A companion methodology sets out eight assessment dimensions—evidence, causality, probabilistic calibration, robustness, safety, autonomy, efficiency and generalisation—across matched baseline configurations and explicit compute budgets. Read the Advanced AI Evaluation Protocol. These are proposed tests rather than reported results.
Research · AI Research Lab · Evidence Verification Across Sectors · Information Science · AI Product Feedback · Feature Requests & Contribution Register
Research synthesis dated 4 November 2026. Additive development; earlier feature requests and dated records remain authoritative for their original wording.
This advanced-intelligence study is one specialist application of a broader, revisable method: map the landscape, clarify taxonomies, investigate a bounded issue, compare perspectives, propose architectures and test outcomes. Its experimental benchmarks remain separate from reflective or policy methods. Read the methodology and project-mapping statement.
Methodological development dated 4 November 2026; this section supplements rather than revises existing records.