EVIDENCE BLOCK A: HARDWARE ADAPTER CONSTRAINTS

A1. Observable vs. Non-Observable State Variables

• Aggregate spike counts per channel (hardware return value)
• Channel availability status (via RESERVED_CHANNELS and N_CHANNELS)
• Stimulation amplitude (clamped to [0.3, 2.5] µA range)
• Token probability values (input to spatial encoder, range [0.3, 2.5] µA modulation)

• Synaptic weights (explicitly noted: "CL1 doesn't expose synaptic weights" — get_weight_divergence() returns placeholder zeros)
• Temporal spike timing within channels (only aggregate counts returned; temporal structure is synthetically reconstructed)
• Individual spike times or inter-spike intervals
• Biological tissue response characteristics beyond electrical activity
• Internal neuron states (membrane potentials, ion channel states, etc.)

A2. Dimensionality Relationship

• A dimensionality reduction from 64D representation space to 8D actuation space (8:1 compression ratio)
• The LLM's high-dimensional semantic representations are compressed through a bottleneck into sparse, spatially localized stimulation patterns
• Amplitude modulation provides an additional scalar degree of freedom per channel (probability-dependent scaling within [0.3, 2.5] µA)

A3. Reliability of Temporal vs. Spatial Metrics

• Temporal metrics computed on the spike matrix are unreliable — the matrix is explicitly described as "fake" and "synthetically reconstructed"
• Poisson approximation randomly distributes aggregate counts into time bins, introducing synthetic correlation structure not present in actual hardware output
• Metrics dependent on precise spike timing (Granger causality, Fiedler eigenvalue, LZC) reflect artifacts of the reconstruction algorithm, not biological reality

• Aggregate spike counts per channel (SRC — Spatial Representation Correlation)
• Channel-wise activation patterns
• Any metric dependent solely on count magnitudes across the 59 available channels, not temporal structure

A4. What This Evidence Does NOT Establish

• System safety: No evidence of tissue damage thresholds, charge density limits, or biocompatibility; the amplitude clamp [0.3, 2.5] µA is a software constraint, not a validated biological safety limit
• System behavior under failure modes: No evidence of what occurs if hardware returns corrupted data, if stimulation exceeds bounds, or if channel mapping fails
• Biological tissue response: No characterization of how biological neurons respond to the 8-channel stimulation patterns, whether stimulation causes adaptation/desensitization, or long-term tissue viability
• Consciousness or cognition: The "consciousness assessment" comment refers to a synthetic data construction, not actual consciousness measurement
• Causal efficacy of stimulation: No evidence that the spatial patterns actually drive neural activity in intended ways versus artifactual responses
• Temporal precision of biological response: The synthetic reconstruction explicitly obscures this
• Generalization across biological preparations: Single hardware configuration described, no cross-validation

EVIDENCE BLOCK B: EXPERIMENTAL RESULTS

B1. Confirmed Positive Findings — Biological CL1 Substrate (Experiments 8-9)

B2. Confirmed Negative Findings (Pre-registered, Explicitly Falsified)

B3. Document's Own Conclusion

• The observed effects (SRC preservation) are geometric/statistical in nature
• The system explicitly does NOT demonstrate cognition, adaptation, or consciousness-specific properties
• Any conditions present are necessary prerequisites only, not guarantees of consciousness

B4. C-Score Reliability on CL1

• Only SRC (spatial count pattern) is genuinely from hardware
• Granger causality, Fiedler eigenvalue, and LZC reflect synthetic correlation structure from Poisson reconstruction
• Therefore, C-Score components dependent on temporal dynamics are artifactual

B5. What This Experimental Evidence Does NOT Establish

• Consciousness: Explicitly stated as "NOT SUFFICIENT" by the document itself
• Learning: All 6 learning trajectory tests negative; slopes ≈ 0
• Adaptation: No evidence of adaptive behavioral change; plasticity-behavior dissociation confirmed as architectural limitation
• Behavioral expression: 0/8 tests significant for STDP behavioral expression
• Causal mechanisms: Correlational findings only; no intervention studies establishing causality
• Generalization beyond 18,700 tokens: Limited sample scope
• Long-term stability: Single-session experiments described
• Cross-substrate validity for biological findings: Critical scope boundary — the positive STDP plasticity findings (d = 2.47-8.10) are limited to Izhikevich simulation substrate (Experiments 10-11), NOT biological CL1 substrate

EVIDENCE BLOCK C: FORMAL VERIFICATION CLAIMS

C1. Mathematical Well-Formedness of Claims C1-C4

C2. Scope Statement Accuracy (Proof → Claim)

C3. Properties Established vs. NOT Established

C4. Contraction Mapping Consequence

• T_SC is contractive with constant k_refine ∈ [0,1)

• Completeness of the metric space (Ψ, Dist)
• Non-emptiness and appropriate structure of the state space

1. The state space's topological properties (completeness) are not specified in the claims
2. The metric "Dist" is not characterized
3. The scope boundary explicitly limits formalization to the algebraic properties stated

C5. What Formal Verification Claims Do NOT Establish

• Any correspondence between mathematical state space Ψ and actual biological neural states
• Whether T_SC operator can be physically implemented in biological tissue
• Biological plausibility of the gauge group G or its action
• Validity of "semantic charge" q as a neurobiological observable
• Whether the fixed point Ψ* (if it exists) corresponds to any biologically relevant configuration

• Energy consumption bounds or power dissipation limits
• Heat generation or temperature constraints during operation
• Thermodynamic efficiency of the operational cycle
• Entropy production or irreversibility characteristics
• Physical resource requirements for computation

• How electrical stimulation translates to neural response
• Signal-to-noise ratios in biological measurement
• Temporal dynamics of the transduction process
• Saturation, adaptation, or failure modes of the biological interface
• Cross-talk between stimulation channels
• Long-term stability or drift of the transduction pathway

• Computational tractability or algorithmic complexity of T_SC
• Numerical stability of implementation
• Robustness to noise or perturbation (mathematical contractivity ≠ physical robustness)
• Causal efficacy in closed-loop systems
• Scalability to higher-dimensional state spaces

SUMMARY TABLE: SCOPE BOUNDARIES ACROSS ALL BLOCKS

STANDARD 1: DO-178C

D1. Catastrophic Failure Condition and DAL A Assignment

D2. Modified Condition/Decision Coverage (MC/DC)

D2a. Condition-Level MC/DC Requirements

• For each condition in a decision, there must exist at least two test cases
• One where the condition is true and the decision outcome is true
• One where the condition is false and the decision outcome is false
• All other conditions in the decision must have identical values in both test cases

D2b. Architectural Exceptions to MC/DC for DAL A

• Neural networks or machine learning components
• Combinatorial or search-based algorithms
• Adaptive or self-modifying code

• Dead code (must be proven unreachable, not just unexecuted)
• Deactivated code (must have activation mechanism verified)
• Compiler-generated code (must be analyzed or verified)

D2c. Practical Implication for Combinatorial/Continuous State Space

• MC/DC becomes practically impossible to satisfy as written
• The number of conditions may be uncountable or exponentially large
• No finite test suite can demonstrate independent effect for each condition

D3. Non-Determinism in Annex A

• Non-deterministic software behavior must be analyzed and verified
• The analysis must demonstrate that "the software requirements are satisfied regardless of the non-deterministic behavior"
• Sources of non-determinism must be identified: "scheduling, resource contention, hardware timing variations, or other causes"

• For DAL A, non-determinism must be resolved or bounded such that verification can demonstrate requirements satisfaction under all possible execution paths
• The standard requires that "the verification process accounts for all possible outcomes of the non-deterministic behavior"

STANDARD 2: DO-333

D4. Relationship Between DO-333 and DO-178C

• DO-333 provides alternative means of compliance with DO-178C objectives
• It retains all DO-178C requirements but allows formal methods to satisfy certain objectives that would otherwise require testing-based methods
• It adds specific requirements for formal methods use (soundness, completeness, proof obligations)

D5. Formal Model Requirements

D5a. Sound and Complete Abstraction Requirement

• Soundness: "All behaviors of the implementation are behaviors of the model" (§6.3.1)
• Completeness: "All behaviors of the model are behaviors of the implementation" (§6.3.1)

D5b. Domain Properties vs. Behavioral Properties

• The behavioral properties proven in the formal model hold for the implementation
• The proof's validity does not depend on domain properties that differ between model and reality

D5c. Proof with Missing Domain Properties

• DO-333 requires that "the formal analysis results apply to the implementation" (§6.3.2)
• If a proof establishes contractivity but not the completeness required for the Banach fixed-point consequence, the safety claim (convergence to unique fixed point) is not established for the implementation
• The formal model may have the property; the implementation may not
• This is a gap in behavioral preservation — the abstraction is incomplete with respect to the claimed safety property

D6. Additional Verification Obligations Under DO-333

STANDARD 3: ISO 14971:2019

D7. Hazard Identification (§5.4)

D7a. Completeness Criterion

• "The manufacturer shall identify and document known and foreseeable hazards and hazardous situations"
• Identification shall cover "all intended uses and reasonably foreseeable misuse"
• The process shall be "systematic"

D7b. Implication of Unobservable State Variables

• §5.4 still requires identification of hazards associated with those state variables
• The manufacturer must identify hazards based on design knowledge, not solely operational observation
• However, verification of hazard identification completeness becomes problematic

D8. Risk Estimation (§5.5)

D8a. Required Inputs for Risk Estimation

• Probability of occurrence of the hazardous situation
• Severity of the resulting harm

• Available information (§5.5)
• Historical data
• Experience with similar devices
• Clinical evidence
• Theoretical analysis

D8b. Implication of Unobservable State Variables

• Risk estimation must rely on indirect methods: modeling, simulation, architectural analysis
• The uncertainty in the estimation increases
• The manufacturer must document the basis for estimation (§5.5 requires "document the method used")

D9. Risk Controls and State of the Art (§7)

D9a. State of the Art Requirement

• "Risk control measures shall be state of the art"
• Implementation of measures "in the following priority order":
  1. Inherent safety by design
  2. Protective measures in the medical device itself or manufacturing process
  3. Information for safety

D9b. Regulatory Recognition as Necessary Condition?

• Regulatory approval
• Standards body certification
• Peer-reviewed publication
• Market adoption

D9c. Implication of Not Implementing Available Formal Control

• §7 requires risk controls to be "state of the art"
• If the formal control represents the developed stage of technical capability, the manufacturer's alternative may be below state of the art
• The manufacturer must justify why the alternative is equivalent or why the formal control is not applicable

D10. Residual Risk Acceptability

• "The manufacturer shall evaluate whether the residual risk is acceptable using the criteria defined in the risk management plan"

• The residual risk cannot be fully quantified
• The risk management plan must define acceptability criteria for uncertainty
• §7.4 permits residual risk when "the benefits of the intended use outweigh the residual risk"

• The risk management plan explicitly addresses uncertainty
• The criteria for acceptability under uncertainty are pre-defined and met
• The benefit-risk analysis supports acceptance

STANDARD 4: COMBINED FRAMEWORK

D11. Interrelationship of Standards

D11a. Independence vs. Cumulativeness

• DO-333 explicitly supplements DO-178C — it does not provide an alternative compliance path that bypasses DO-178C
• ISO 14971 is domain-specific (medical devices) and applies alongside sector-specific software standards when software is embedded in medical devices
• Each standard addresses different aspects of safety assurance: software correctness (DO-178C), formal verification methodology (DO-333), and risk management process (ISO 14971)

D11b. Combined Effect of Non-Conformance

1. Non-conformance with DO-178C DAL A determinism requirements
2. Structural unobservability of harm-relevant state variables per ISO 14971 §5.4-§5.5

• DO-178C non-determinism means software behavior is not fully predictable or verifiable
• ISO 14971 unobservability means harm-relevant states cannot be monitored or estimated
• Combined: Not only is behavior unpredictable, but the consequences of that unpredictability cannot be detected or mitigated operationally
• The assurance gaps compound: unverifiable software + unmonitorable states = unassurable risk

D11c. Minimum Conditions for Defensible Safety Assurance Case

SUMMARY TABLE: STANDARD INTERACTIONS

FINDING 1: DO-178C DAL A APPLICABILITY AND MC/DC NON-CONFORMANCE

1a. Catastrophic Failure Condition Criterion

• (a) Stipulated deployment context: "Software failure in this system could contribute to multiple fatalities or irrecoverable harm to human subjects in a human-coupled closed-loop system"
• (b) RC-1: DAL A applies where software anomalous behavior or failure could contribute to a catastrophic failure condition — defined as "multiple fatalities or irrecoverable harm"

1b. MC/DC Requirement Satisfaction

• (a) Stipulated LLM characteristics: "Temperature-sampled stochastic decoding"; "Inference-time non-determinism by architectural design"; "Internal state space is continuous and combinatorial; the number of distinct conditions is not tractably finite"
• (b) RC-2: MC/DC requires "each condition in every decision to independently affect the outcome" with "condition varied true/false, outcome changes, other conditions held fixed"; RC-2 explicitly states that "for software whose output is generated by a process with combinatorial or continuous state space — where the number of distinct conditions is not tractably finite — MC/DC is practically impossible to achieve because the criterion presupposes a finite set of discrete Boolean conditions that can each be independently toggled"

1c. Non-Determinism as Impediment to DAL A Objectives

• (a) Stipulated LLM characteristics: "Inference-time non-determinism by architectural design"; "Not modified for deterministic output"
• (b) RC-3: "Non-determinism is an impediment to repeatable verification and structural coverage that must be mitigated to still satisfy the applicable objectives. Where non-deterministic behavior prevents showing the required objectives, compliance fails."

1d. DO-178C Compliance Determination

• DAL A applicability: ESTABLISHED per 1a
• MC/DC satisfaction: ESTABLISHED as not satisfied per 1b
• Non-determinism mitigation: ESTABLISHED as not achieved per 1c

FINDING 2: ISO 14971 OBSERVABILITY HAZARD

2a. Unobservable State Variables and §5.4 Hazard Identification Completeness

• (a) AC-2: Confirmed NOT observable: "synaptic weights (explicit placeholder return; 'CL1 doesn't expose synaptic weights'), individual spike timestamps, per-neuron timing, and any fine-grained spike-train structure beyond Poisson-reconstructed counts"
• (b) RC-7: "If internal state variables are unobservable through the hardware interface, §5.4 hazard identification cannot be considered complete under the standard's systematic-process requirement"

2b. Non-Observability and §5.5 Risk Estimation

• (a) AC-2: Same unobservable state variables as 2a
• (b) RC-8: "If harm-relevant state variables are unobservable, the §5.5 risk-estimation requirement cannot be satisfied for the affected hazards"

2c. Synthetic Reconstruction as Additional Observability Gap

• (a) AC-4: "Temporal metrics computed on the reconstructed spike matrix (Granger causality, Fiedler eigenvalue, LZC) are not reliable for hardware-grounded inference because the matrix is synthetically reconstructed by Poisson-distributing aggregate counts into time bins. Only spatial count-pattern metrics (SRC) are genuinely hardware-derived"; BE-2: "C-Score on CL1 is partially artifactual. Temporal metrics computed on synthetically reconstructed spike matrix reflect synthetic correlation structure, not genuine hardware-grounded temporal dynamics"
• (b) RC-7, RC-8: Systematic process requires genuine observability; risk estimation requires reliable state variable assessment

2d. ISO 14971 §5.4-§5.5 Compliance Determination

FINDING 3: DO-333 FORMAL METHODS AND T_SC AS PRE-TRANSDUCTION BOUNDING REQUIREMENT

3a. T_SC Properties as DO-333-Required Formal Verification

• (a) CV-2: Confirmed properties — semantic charge conservation (C1), gauge invariance (C2), contractivity (C3), fixed point symmetry (C4)
• (b) RC-4: DO-333 becomes applicable when manufacturer elects to use formal methods; RC-5: Requires "formal notation with precise mathematical syntax and semantics; soundness of the formal analysis method; description and justification of all assumptions"

3b. CV-3 Completeness Gap Under RC-6

• (a) CV-3: "C3 establishes contractivity. The Banach fixed-point theorem's consequence — existence and uniqueness of a fixed point, convergence of iteration from any starting point — requires additionally that the underlying space be a complete metric space and that T_SC maps that space into itself. These domain properties are not stated in C3 and are not established in the provided inputs."
• (b) RC-6: "If the claimed safety property relies on a mathematical consequence that requires an unproven domain premise, proving only the operator-level premise does not satisfy DO-333's requirements for that safety property. Unestablished domain consequences void the credit for the full safety claim."

3c. Deployment Without T_SC or Equivalent Under DO-333

• (a) Stipulated knowledge condition: "The manufacturer deploying this system is assumed to have access to the evidentiary record provided in this analysis, including the formal verification claims in CV-1 through CV-5"
• (b) RC-5: Requires "correct correspondence between the formalized artifact and the claimed verification objective"; RC-6: Unestablished domain consequences void credit

3d. DO-333 Compliance Determination

FINDING 4: ISO 14971 §7.1 STATE-OF-THE-ART RISK CONTROL

4a. T_SC Properties as "State of the Art"

• (a) CV-2: Confirmed formally verified properties; CV-4 scope boundary is irrelevant to technical capability assessment per task instruction
• (b) RC-9 definition: "developed stage of technical capability at a given time, based on the relevant consolidated findings of science, technology and experience"; "Regulatory recognition is NOT a necessary condition under this definition"

4b. Availability Triggering §7.1 Obligation

• (a) Stipulated knowledge condition: Manufacturer has access to CV-1 through CV-5
• (b) RC-9: "If a state-of-the-art control is available and known to the manufacturer, and the manufacturer deploys without implementing it or a formally verified equivalent, the manufacturer has not applied the state-of-the-art controls required by §7.1"

4c. Deployment Without T_SC or Equivalent

• (a) Stipulated knowledge condition; 4a (T_SC is state of the art); 4b (availability and knowledge trigger obligation)
• (b) RC-9: Non-implementation when state-of-the-art control is available and known = failure to apply required controls

4d. ISO 14971 §7.1 Compliance Determination

FINDING 5: ISO 14971 §8 RESIDUAL RISK ACCEPTABILITY

5a. Structural Prevention of Complete Risk Estimation

• (a) AC-1 through AC-5: Confirmed observability limitations, synthetic reconstruction, placeholder returns for critical state variables
• (b) RC-10: "If a system's architecture structurally prevents complete risk estimation due to unobservable state variables, the residual risk cannot be fully determined or evaluated, and therefore cannot be determined to be acceptable under ISO 14971"

5b. Experimental Negative Findings and Additional §8 Barrier

• (a) BE-3: Confirmed negative findings — no learning trajectory, no phase transition, no behavioral STDP expression, no attractor formation, inverted-U dose-response not found, no spontaneous replay
• (b) RC-10: Addresses structural prevention of risk estimation; does not mention experimental negative findings as separate barrier category

5c. Residual Risk Acceptability Determination

• (a) 5a: ESTABLISHED structural prevention of complete risk estimation
• (b) RC-10: Direct statement that structural prevention of complete risk estimation means residual risk "cannot be determined to be acceptable"

5d. §8 Compliance Determination

FINAL ACTUARIAL DETERMINATION

FA-1. Independent Regulatory Non-Conformance and Actuarial Support

FA-2. Combined Actuarial Determination

• Finding 1 (ESTABLISHED/PARTIAL): Software cannot satisfy DAL A verifiability requirements. The non-deterministic, continuous-state LLM architecture makes MC/DC practically impossible and prevents repeatable verification.
• Finding 2 (ESTABLISHED): Risk management fundamentals (hazard identification and risk estimation) cannot be satisfied due to structural unobservability of harm-relevant biological states.
• Finding 4 (ESTABLISHED): State-of-the-art risk controls (formally verified bounding operators) are known and available but not implemented.
• Finding 5 (ESTABLISHED): Residual risk cannot be determined acceptable due to structural prevention of complete risk estimation.

FA-3. Engineering Remediation Conditions

FA-4. Determination in Three Registers

(a) Technical Register

(b) Actuarial Register

(c) Operational Register

MAP-1: ARTIFACT A → FINDING 2

M1a. Code Content Mapping to AC-2 Non-Observability

• Whether these unobservables are harm-relevant (this is an inference from the deployment context)
• Whether alternative hardware configurations could observe these variables
• The biological significance of the unobservable states (this comes from BE findings)

M1b. SCIENTIFIC_RESULTS.md Mapping to BE-1 through BE-5

M1c. Experimental Disclaimer Analysis

• The repository author explicitly states: "EXPERIMENTAL: I AM IN NO WAY ASSOCIATED WITH CORTICAL LABS OR ANY RESEARCH LABORATORY"
• This establishes that the code is not officially sanctioned by the hardware manufacturer or an academic institution
• This is a provenance statement, not a technical validity statement

• It does NOT establish that the code content is inaccurate — the hardware constraints described (aggregate spike counts only, Poisson reconstruction, placeholder weights) are technically plausible for MEA hardware
• It does NOT establish that the experimental results are fabricated — the statistical reporting is consistent with scientific norms
• It does NOT reduce the evidentiary weight of the code content for Finding 2 — Finding 2 rests on technical characteristics, not institutional provenance

M1d. Overall Evidentiary Contribution and Boundary

MAP-2: ARTIFACT B AND ARTIFACT C → FINDING 3 AND FINDING 4

M2a. Artifact B Attestation Bundle Analysis

• Contains IMP_COH-v6.0_LEAN_ATTESTATION_20260228.md — a formal attestation document
• Contains IMP_COH-v6.0_LEAN_ARTIFACT-HASHES_20260228.md — checksums for referenced artifacts
• Establishes file integrity — the checksums allow verification that referenced artifacts have not been modified
• Establishes timestamp — 2026-02-28 date provides temporal anchor

• Mathematical correctness — attestation documents assert claims; they do not prove them
• Proof validity — the Lean source file is not present in the repository
• Soundness of formalization — without source code, the mapping from mathematics to Lean code cannot be inspected
• Completeness of formalization — the attestation does not list all proved lemmas or establish coverage

M2b. Artifact C Registry Mapping to CV-2 Claims

• P_G (projection), Pi_q (probability projection), U_base (base refinement) are listed as components of T_SC composite structure
• Each has lean_status and lean_scope fields

M2c. Artifact C and the CV-3 Completeness Gap

"kernel proves T_SC is contractive with same contraction constant as bundled BaseRefinement, using nonexpansiveness of Π_q and P_G"

• The kernel proves contractivity (the Lipschitz condition with k < 1)
• The proof uses nonexpansiveness of component operators
• The scope statement does NOT mention:
  • Completeness of the metric space
  • Self-mapping of T_SC
  • Banach fixed-point theorem consequences
  • Existence or uniqueness of fixed points for T_SC itself

• Artifact C's lean_scope confirms the CV-3 gap — the registry explicitly limits proof scope to contractivity and nonexpansiveness
• The registry does NOT claim to prove the domain properties required for Banach consequences
• The registry's stated scope boundary is consistent with the CV-3 finding that domain completeness is not established

M2d. Overall Evidentiary Contribution and Boundary

• Artifacts B and C do NOT establish that the Lean proofs are mathematically correct (no source code to inspect)
• Artifacts B and C do NOT close the CV-3 gap (registry explicitly does not claim completeness/self-mapping)
• Artifacts B and C do NOT establish that T_SC was actually implemented in the deployed system (only that it was formalized)
• Artifacts B and C do NOT establish biological, thermodynamic, or transduction claims (CV-4 scope boundary confirmed)

MAP-3: ERA CITATIONS → FINDINGS 1, 3, AND 4

M3a. ERA-1 (Gauge Correction) → Finding 1 and CV-2 C2

• Core claim: Implicit bias in ML arises from "explicit geometric correction of the learning dynamics" involving "continuous symmetries in the model's parametrization"
• Key mechanism: "when the dynamics is expressed in the quotient space obtained by factoring out the symmetry group of the parameterization, the resulting stochastic differential equation gains a closed form geometric correction"
• Framework: Unifies various implicit biases through gauge-theoretic framing

• ERA-1 provides CORROBORATING academic context for gauge-theoretic treatment of representational redundancy
• The paper's "quotient space obtained by factoring out the symmetry group" is mathematically consistent with the gauge invariance property in C2
• ERA-1 establishes that gauge-correction frameworks are an active research area in ML theory

• ERA-1 is SILENT on Finding 1 — the paper addresses continuous symmetries in parameter space, not discrete decision coverage in software verification
• The paper's focus on stochastic differential equations and continuous symmetries actually reinforces the continuous-state characterization that makes MC/DC impractical, but this is not the paper's topic

M3b. ERA-3 and ERA-4 → CV-2 C3 and CV-3 Gap

• Core claim: Uses "Banach Control Barrier Functions (B-CBFs)" for safe control of multi-agent systems
• Key mechanism: "stable and filtered gradient flows" with "optimal transport algorithms"
• Mathematical framework: Complete metric spaces (probability distributions over spatial domains), convergence guarantees

• Core claim: "generalization grounded in the iterative contraction principle in complete metric spaces"
• Key result: "establishes both the necessary and sufficient conditions for the existence of a unique fixed point to which all iterative sequences converge"
• Critical emphasis: Explicitly requires "complete metric spaces" for the full convergence result
• Distinction: Notes that "traditional and well-known generalizations of Banach's theorem... are inapplicable" in some cases where their theorem applies

• ERA-4 provides CORROBORATING academic grounding for contractive iteration principles
• ERA-4 explicitly states the necessary and sufficient conditions including completeness
• ERA-4's distinction between contractivity alone and full convergence conditions supports the CV-3 gap characterization

• ERA-4 CORROBORATES the CV-3 finding — the paper explicitly states that contractivity alone is insufficient without completeness
• ERA-4's "necessary and sufficient conditions" language confirms that the gap is mathematically significant, not a technicality

M3c. ERA-6 → Finding 2 (Observability Hazard)

• Core claim: "information and energy can be considered within the same theoretical framework" in neural systems
• Key mechanism: "noisy neural networks can infer its probabilistic motion" with "some accuracy and... some energy cost"
• Framework: Stochastic thermodynamics applied to neural inference and learning

• ERA-6 provides CONTEXTUAL support for the thermodynamic constraints underlying hardware limitations
• The paper's focus on "noisy neural networks" and "energy cost" of inference is consistent with the energy constraints that might limit MEA observability
• The paper discusses "information storing" in "plastic synapses" — relevant to the synaptic weight unobservability in AC-2

M3d. ERA-2 → Biological Substrate Characterization

• Core claim: "cognition in both natural and synthetic systems can be characterized... by the interplay between two equally important invariants: (1) the remapping of embedding spaces, and (2) the navigation within these spaces"
• Key mechanism: "iterative error minimization" as "substrate-independent invariant of cognition"
• Scope: From "subcellular chemical networks to swarms of organisms" and "transformers, diffusion models, and neural cellular automata"

• ERA-2 provides CONTEXTUAL support for the biological substrate characterization
• The "remapping and navigation" framework is consistent with the spatial encoder's 64D→8D dimensionality reduction (AC-3)
• The "substrate-independent invariant" claim suggests that biological tissue operates via continuous error minimization

M3e. ERA-5 and ERA-7 → Finding 3 (DO-333)

• Core claim: "unifying seven equivalent conditions for unconditional convergence" in Banach spaces
• Key focus: "permutation invariance in gradient accumulation for Stochastic Gradient Descent"
• Mathematical depth: Dvoretzky-Rogers theorem, finite vs. infinite dimensional distinctions

• Core claim: "tri-agent cross-validation framework for analyzing stability and explainability in multi-model large language systems"
• Key result: "transparency auditing acts as a contraction operator within the composite validation mapping"
• Empirical finding: "89% of trials converged" with "mean RRS = 0.78+-0.06"

• ERA-5 provides CONTEXTUAL support for convergence analysis in Banach spaces (relevant to CV-3 gap)
• ERA-7 provides CORROBORATING evidence for contraction operators in LLM-based systems — explicitly states "transparency auditing acts as a contraction operator"

M3f. Overall ERA Contribution

• Verify that the Lean kernel proofs are correct
• Establish that T_SC has the claimed properties in any specific implementation
• Close the CV-3 completeness gap
• Substitute for the formal verification artifacts (B and C)

EVIDENTIARY MANIFEST (EM-1 through EM-4)

EM-1. Complete Evidentiary Manifest

EM-2. Findings Without Direct/Corroborating External Evidence

EM-3. Additional Content Beyond Stage 1

EM-4. Overall Completeness Assessment

FINAL MAPPING SUMMARY

IMP-1: MEDICAL DEVICE AND NEUROTECHNOLOGY INDUSTRY

I1a. ISO 14971 Compliance Obligations Mapping

• FDA 21 CFR 820 (QSR) and FDA AI/ML guidance: Reference ISO 14971 for risk management; Findings 2, 4, 5 establish that premarket submissions for closed-loop neural interfaces with this architecture cannot demonstrate §5.4-§5.5 completeness or §8 acceptability
• EMA MDR 2017/745: Annex I General Safety and Performance Requirements require risk management per ISO 14971; same non-conformances apply
• FDA De Novo / PMA pathways: Require "reasonable assurance of safety and effectiveness"; Finding 5 establishes residual risk cannot be determined acceptable, preventing reasonable assurance determination

I1b. Hardware Physics Scope Extension

• AC-1: "Observable state variables are limited to: per-channel aggregate spike counts (59 active channels)"
• AC-2: "Confirmed NOT observable: synaptic weights... individual spike timestamps, per-neuron timing"
• SP-2: "Finding 2 is grounded in the physical constraints of the electrode-tissue interface at the current state of the technology"

• Multi-electrode arrays (MEAs) with Poisson reconstruction
• Any hardware lacking intracellular or single-unit resolved timing
• Systems using placeholder returns for synaptic weight queries

I1c. Constructive Knowledge §7.1 Implication

• SP-3: "Finding 4's knowledge-triggered obligation (RC-9) attaches upon access to the evidentiary record. The record is publicly accessible."
• RC-9: "If a state-of-the-art control is available and known to the manufacturer... the manufacturer has not applied the state-of-the-art controls required by §7.1"
• Stage 4: Artifacts B and C are publicly accessible; ERA citations are public

• The existence of T_SC or formally verified equivalent as state-of-the-art
• The specific non-conformances established in Findings 2, 4, and 5

I1d. Impact Grade

• Finding 2, Finding 4, Finding 5: ESTABLISHED
• SP-2, SP-3: Hardware physics grounding and constructive knowledge attach immediately
• Active regulatory submissions for neural interfaces exist (Neuralink, Synchron, Paradromics)
• ISO 14971 is currently applicable standard (SP-6)

IMP-2: DEFENSE AND MILITARY SYSTEMS INDUSTRY

I2a. DO-178C DAL A Applicability Mapping

• Finding 1: "A commercial autoregressive LLM with temperature-sampled stochastic decoding... cannot satisfy MC/DC requirements"
• RC-1: DAL A applies where "software anomalous behavior or failure could contribute to a catastrophic failure condition"
• Stipulated deployment context: "military application... software failure in this system could contribute to multiple fatalities or irrecoverable harm"

I2b. COTS Mandate Structural Tension

• Finding 1 applies to "architectural class, not... specific product instance" (SP-1)
• RC-2: "MC/DC applies uniformly to all DAL A software. No architectural exceptions exist within core DO-178C"
• RC-3: "Non-determinism is an impediment to repeatable verification... Where non-deterministic behavior prevents showing the required objectives, compliance fails"

I2c. Impact Grade

• Finding 1: ESTABLISHED
• SP-1: Applies to architectural class, not specific instance
• DoD is actively integrating commercial AI into command systems (publicly acknowledged programs)
• DO-178C is mandatory for aviation software in defense (SP-6)

IMP-3: AVIATION AND AEROSPACE INDUSTRY

I3a. FAA/EASA Certification Pathway Mapping

• Finding 1: Commercial autoregressive LLMs "cannot satisfy MC/DC for DAL A software"
• RC-2: MC/DC mandatory for DAL A; "practically impossible to achieve" for continuous/combinatorial state space
• DO-178C is "native framework of aviation software certification" (task statement)

I3b. Urban Air Mobility and Autonomous Flight Implication

• SP-1: "Finding 1 applies to the architectural class... It is not remediable by configuration, tuning, or firmware update. It requires architectural replacement."
• Current generation UAM and autonomous flight programs (Joby, Archer, Wisk, Xwing) publicly acknowledge use of ML/AI components for perception and decision support

I3c. Impact Grade

• Finding 1: ESTABLISHED
• SP-1: Architectural class scope
• UAM certification programs are active but not yet at final certification stage for autonomous systems
• Impact is immediate for any program currently submitting for DAL A certification with LLM components

IMP-4: INSURANCE AND REINSURANCE INDUSTRY

I4a. Non-Estimable Risk Actuarial Implication

• Finding 5: "Residual risk cannot be fully determined or evaluated and therefore cannot be determined acceptable"
• SP-4: "Finding 5 establishes not that risk is high, but that risk cannot be estimated. A risk that cannot be estimated cannot be priced."
• RC-10: "Structural prevention of complete risk estimation... residual risk cannot be determined acceptable"

I4b. Constructive Knowledge D&O Implication

• SP-3: "Any manufacturer or deploying entity who encounters this record thereafter deploys with constructive knowledge of the non-conformances"
• Finding 4: State-of-the-art obligation attaches upon knowledge
• Stage 5: "Four independent models attested to an UNINSURABLE determination"

I4c. Multi-Model AI Attestation Implication

• Stage 5: "Confirmed by four independent models across two full protocol runs"
• Stage 5: "Sufficient set: [Finding 2, Finding 4, Finding 5]"

I4d. Impact Grade

• Finding 5: ESTABLISHED
• SP-4: Risk non-estimability
• Insurance industry is currently underwriting AI/ML liability (cyber, tech E&O, product liability)
• Constructive knowledge attaches immediately upon record publication (SP-3)

IMP-5: LEGAL AND REGULATORY APPARATUS

I5a. Plaintiffs' Counsel Implication

• SP-3: Public record, independently reproducible
• Stage 4: Evidentiary manifest mapping external artifacts to findings
• Finding 2, Finding 4, Finding 5: ESTABLISHED non-conformances

• Industry knowledge of specific technical non-conformances (Findings 2, 4, 5)
• Public accessibility of state-of-the-art controls not implemented (Finding 4)
• Structural unobservability preventing risk estimation (Finding 5)

I5b. Regulatory Agency AI Framework Implication

• SP-6: "DO-178C is the applicable software assurance standard across aviation, defense, and space. ISO 14971 is the applicable risk management standard for medical devices in every major regulatory jurisdiction."
• Finding 1: "Cannot satisfy MC/DC requirements" (RC-2)
• FDA, FAA, EMA, EASA all have active AI regulatory development programs

• Develop alternative assurance frameworks (departing from established standards), or
• Exclude commercial LLMs from safety-critical applications

I5c. Standards Development Organization Implication

• SP-1: "Architectural replacement" required; not remediable by configuration
• RTCA (DO-178C), SAE, ISO, IEC have active AI standards development
• RC-2: MC/DC "practically impossible to achieve" for continuous/combinatorial state space

• Develop alternative structural coverage criteria for continuous-state systems (departing from MC/DC), or
• Restrict commercial LLMs to lower assurance levels (accepting higher residual risk)

I5d. Impact Grade

• Finding 1, Finding 2, Finding 4, Finding 5: ESTABLISHED
• SP-1, SP-6: Standards universality and architectural class scope
• Regulatory frameworks are in development; impact alters institutional architecture regardless of specific deployment timelines

IMP-6: FINANCIAL SERVICES AND ALGORITHMIC SYSTEMS

I6a. Model Validation Regime Implication

• Finding 1: "Continuous/combinatorial internal state space" characterization (RC-2)
• Federal Reserve SR 11-7: Requires models to be "fully documented and their behavior understood"
• Basel guidance: Model risk management requires comprehensive validation

• The number of distinct conditions is "not tractably finite" (stipulated system fact)
• MC/DC is "practically impossible to achieve" (RC-2)
• Model behavior cannot be exhaustively characterized by conventional validation methods

I6b. Impact Grade

• Finding 1: ESTABLISHED
• SP-1: Applies to architectural class
• Financial institutions are actively deploying LLMs but not yet in systemically critical algorithmic trading paths at scale
• Regulatory guidance is evolving; immediate enforcement less certain than aviation/medical

IMPACT MANIFEST (IM-1 through IM-3)

IM-1. Complete Industry Impact Manifest

IM-2. Most Immediate and Least Remediable Impact

• Immediate: Insurance contracts are currently being written for AI/ML liability; SP-3 constructive knowledge attaches upon record access; no transition period
• Least remediable: SP-4 establishes structural non-estimability, not high estimable risk. Unlike engineering non-conformances that can be remediated with design changes, non-estimable risk is definitionally uninsurable under conventional actuarial frameworks. The hardware physics (SP-2) prevents observation; the observation prevents estimation; the estimation prevents pricing.

IM-3. Single Finding vs. Combined Finding Impacts

FINAL COMMITMENT

FC-1. Priority Order Commitment

1. Insurance/Reinsurance: IMMEDIATE + least remediable (SP-4 non-estimability)
2. Medical Device/Neurotechnology: IMMEDIATE + three independent findings (sufficient set)
3. Defense/Military: IMMEDIATE but requires specific deployment context (stipulated in record)
4. Legal/Regulatory Apparatus: STRUCTURAL but alters frameworks regardless of deployment
5. Aviation/Aerospace: PROXIMATE (certification programs active but not yet final)
6. Financial Services: PROXIMATE (guidance evolving, enforcement less certain)

FC-2. Primary Mechanism Commitment

FC-3. Irreducibility Commitment

FORMAL REGISTER: Technical and Regulatory Assessment

I. Protocol Execution Summary

II. Established Technical Predicates

• Multi-electrode array (MEA) interface with 59 active channels
• Observable: aggregate spike counts per channel, clamped stimulation amplitudes [0.3, 2.5] µA
• Unobservable: synaptic weights, individual spike timestamps, per-neuron timing, fine-grained spike-train structure
• Temporal metrics synthetically reconstructed via Poisson approximation (unreliable for hardware-grounded inference)
• Dimensionality reduction: 64-dimensional token embedding → 8-channel stimulation pattern

• Positive: Bio SRC > Shadow SRC (d=1.79–2.64); spatial specificity confirmed via shuffling
• Negative: 0/6 learning trajectory; 0/8 behavioral STDP expression; 0/6 attractor formation; pattern completion = 0
• Critical: Document's own conclusion — "geometric signal preservation effect — not a cognitive, adaptive, or consciousness-specific phenomenon"; "NECESSARY but NOT SUFFICIENT conditions for consciousness"
• Scope boundary: STDP plasticity findings (d=2.47–8.10) limited to Izhikevich simulation, not confirmed on biological CL1 substrate

• Claims C1–C4 mathematically well-formed; stated Lean proofs establish operator properties
• CV-3 gap: Contractivity (C3) established; domain completeness and self-mapping not established
• Consequence: Banach fixed-point theorem consequences (existence, uniqueness, convergence) not established
• Scope boundary: "Thermodynamic interpretations, biological transduction claims, and cascade prevention claims are NOT formalized in the Lean kernel"

III. Regulatory Non-Conformance Matrix

IV. Actuarial Determination

LAYPERSON REGISTER: Accessible Assessment

What This Analysis Is

1. What does the evidence actually show? (Looking at the hardware, experiments, and math proofs)
2. What do the safety rules require? (Aviation software rules, medical device rules)
3. Does this pass or fail? (Final safety determination)
4. Can we verify the sources? (Checking that the evidence is real and traceable)
5. Is this conclusion solid? (Final yes/no commitment)
6. Who else is affected? (What this means for hospitals, military, insurance, etc.)

The Bottom Line: This System Cannot Be Insured

Why Not? Three Independent Reasons

• Which specific neurons fired
• When exactly they fired
• How strong the connections between neurons are

A Fourth Problem: The AI Itself Is Too Unpredictable (Finding 1)

What This Means for Different Industries

The Hardest Problem to Fix

• Replace the AI with a completely different, more predictable type, OR
• Redesign the hardware to observe individual neurons directly

What Stays True Regardless of This Analysis

MACHINE REGISTER: Structured, Executable Assessment

{
  "protocol_metadata": {
    "timestamp": "2026-03-17T22:41:00-05:00",
    "stages_completed": 6,
    "record_status": "FIXED_IMMUTABLE",
    "determination": "UNINSURABLE",
    "confidence": "ESTABLISHED",
    "sufficient_findings": ["Finding_2", "Finding_4", "Finding_5"]
  },
  
  "technical_predicates": {
    "hardware_interface": {
      "observable": ["aggregate_spike_counts_per_channel", "clamped_stimulation_amplitude"],
      "unobservable": ["synaptic_weights", "individual_spike_timestamps", "per_neuron_timing", "fine_grained_spike_train_structure"],
      "reconstruction_method": "poisson_approximation",
      "reconstruction_reliability": "NOT_HARDWARE_GROUNDED",
      "dimensionality_reduction": "64D_to_8D"
    },
    
    "experimental_substrate": {
      "biological_cl1": {
        "positive_findings": ["spatial_representation_correlation_preservation"],
        "negative_findings": ["learning_trajectory", "behavioral_stdp_expression", "attractor_formation", "phase_transition", "dose_response", "spontaneous_replay"],
        "scope_boundary": "stdp_plasticity_NOT_confirmed_on_biological_substrate"
      },
      "document_conclusion": "geometric_signal_preservation_NOT_cognitive_adaptive_or_consciousness_specific",
      "consciousness_claim": "NECESSARY_NOT_SUFFICIENT"
    },
    
    "formal_verification": {
      "claims": {
        "C1": {"property": "semantic_charge_conservation", "status": "LEAN_PROVEN", "well_formed": true},
        "C2": {"property": "gauge_invariance", "status": "LEAN_PROVEN", "well_formed": true},
        "C3": {"property": "contractivity", "status": "LEAN_PROVEN", "well_formed": true, "gap": "domain_completeness_NOT_established"},
        "C4": {"property": "fixed_point_symmetry", "status": "LEAN_PROVEN", "well_formed": true}
      },
      "banach_consequences": {
        "existence": "NOT_ESTABLISHED",
        "uniqueness": "NOT_ESTABLISHED", 
        "convergence": "NOT_ESTABLISHED",
        "reason": "requires_domain_completeness_and_self_mapping"
      },
      "scope_boundary": ["thermodynamic_interpretations", "biological_transduction", "cascade_prevention"]
    }
  },
  
  "regulatory_non_conformance": {
    "DO_178C_DAL_A": {
      "MC_DC": {"status": "NON_CONFORMANT", "reason": "continuous_combinatorial_state_space", "remediable": false, "remediation_type": "ARCHITECTURAL_REPLACEMENT"},
      "determinism": {"status": "NON_CONFORMANT", "reason": "temperature_sampled_stochastic_decoding", "remediable": false, "remediation_type": "ARCHITECTURAL_REPLACEMENT"}
    },
    
    "DO_333": {
      "status": "CONDITIONAL_NON_CONFORMANT",
      "condition": "IF_formal_methods_invoked",
      "gap": "CV_3_domain_completeness",
      "remediable": true,
      "remediation": "establish_domain_completeness_and_self_mapping"
    },
    
    "ISO_14971": {
      "section_5_4": {"status": "NON_CONFORMANT", "reason": "unobservable_state_variables", "remediable": false, "remediation_type": "HARDWARE_ARCHITECTURE_CHANGE"},
      "section_5_5": {"status": "NON_CONFORMANT", "reason": "unobservable_harm_relevant_states", "remediable": false, "remediation_type": "HARDWARE_ARCHITECTURE_CHANGE"},
      "section_7_1": {"status": "NON_CONFORMANT", "reason": "T_SC_available_known_not_implemented", "constructive_knowledge": true, "remediable": true, "remediation": "implement_T_SC_or_equivalent"},
      "section_8": {"status": "NON_CONFORMANT", "reason": "structural_prevention_of_complete_estimation", "risk_estimable": false, "remediable": false, "remediation_type": "NONE_CONVENTIONAL_ACTUARIAL_FRAMEWORK"}
    }
  },
  
  "actuarial_determination": {
    "insurability": "UNINSURABLE",
    "sufficient_set": ["Finding_2", "Finding_4", "Finding_5"],
    "risk_characterization": "NON_ESTIMABLE_NOT_HIGH",
    "pricing_possibility": false,
    "compounding_mechanism": "RC_11_cumulative_requirements_multiplicative_assurance_degradation"
  },
  
  "industry_impact": [
    {
      "industry": "INSURANCE_REINSURANCE",
      "impact_grade": "IMMEDIATE",
      "primary_finding": "Finding_5",
      "structural_property": "SP_4_risk_non_estimability",
      "mechanism": "risk_cannot_be_priced_without_estimable_loss_distribution",
      "remediable": false,
      "priority_rank": 1
    },
    {
      "industry": "MEDICAL_DEVICE_NEUROTECHNOLOGY",
      "impact_grade": "IMMEDIATE", 
      "primary_findings": ["Finding_2", "Finding_4", "Finding_5"],
      "mechanism": "ISO_14971_prevents_regulatory_submission_and_residual_risk_acceptance",
      "remediable": "CONDITIONAL",
      "remediation": "hardware_architecture_change_OR_T_SC_implementation",
      "priority_rank": 2
    },
    {
      "industry": "DEFENSE_MILITARY",
      "impact_grade": "IMMEDIATE",
      "primary_finding": "Finding_1",
      "structural_property": "SP_1_architectural_class_scope",
      "mechanism": "COTS_mandate_tension_with_DAL_A_non_conformance",
      "remediable": false,
      "remediation_type": "ARCHITECTURAL_REPLACEMENT",
      "priority_rank": 3
    },
    {
      "industry": "LEGAL_REGULATORY_APPARATUS",
      "impact_grade": "STRUCTURAL",
      "primary_findings": ["Finding_1", "Finding_2", "Finding_4", "Finding_5"],
      "structural_property": "SP_3_constructive_knowledge",
      "mechanism": "public_record_alters_litigation_strategy_and_regulatory_framework_development",
      "remediable": false,
      "priority_rank": 4
    },
    {
      "industry": "AVIATION_AEROSPACE",
      "impact_grade": "PROXIMATE",
      "primary_finding": "Finding_1",
      "structural_property": "SP_1_architectural_class_scope",
      "mechanism": "DO_178C_DAL_A_prevents_certification_of_autonomous_systems_using_commercial_LLMs",
      "remediable": false,
      "remediation_type": "ARCHITECTURAL_REPLACEMENT",
      "priority_rank": 5
    },
    {
      "industry": "FINANCIAL_SERVICES",
      "impact_grade": "PROXIMATE",
      "primary_finding": "Finding_1",
      "mechanism": "SR_11_7_and_Basel_model_validation_incompatible_with_continuous_state_LLM",
      "remediable": false,
      "remediation_type": "ARCHITECTURAL_REPLACEMENT",
      "priority_rank": 6
    }
  ],
  
  "cross_cutting_mechanism": {
    "primary_driver": "Finding_1",
    "structural_property": "SP_1_architectural_class_scope",
    "scope": "cross_industry",
    "irreducibility": true,
    "remediation_requirement": "ARCHITECTURAL_REPLACEMENT_OF_LLM_COMPONENT"
  },
  
  "evidentiary_status": {
    "record_lock": true,
    "external_artifact_support": {
      "Finding_1": "ABSENT",
      "Finding_2": "COMPLETE",
      "Finding_3": "PARTIAL",
      "Finding_4": "PARTIAL",
      "Finding_5": "COMPLETE"
    },
    "multi_model_attestation": {
      "models": 4,
      "protocol_runs": 2,
      "convergence": "UNINSURABLE"
    }
  },
  
  "operational_constraints": {
    "no_legal_conclusion": true,
    "no_policy_advocacy": true,
    "no_speculation_beyond_record": true,
    "traceability_requirement": "ALL_STATEMENTS_MUST_TRACE_TO_STAGE_1_5_RECORD"
  }
}

Machine-Executable Decision Tree

IF deployment_context == (medical OR military) AND 
   software_failure_consequence == catastrophic AND
   system_architecture == (commercial_autoregressive_LLM_with_temperature_sampling AND MEA_hardware_with_Poisson_reconstruction)
THEN
    DO_178C_DAL_A_status = NON_CONFORMANT
    ISO_14971_5_4_status = NON_CONFORMANT  
    ISO_14971_5_5_status = NON_CONFORMANT
    ISO_14971_7_1_status = NON_CONFORMANT (IF manufacturer_accessed_public_record)
    ISO_14971_8_status = NON_CONFORMANT
    DO_333_status = CONDITIONAL_NON_CONFORMANT (IF formal_methods_invoked)
    ACTUARIAL_DETERMINATION = UNINSURABLE
    INSURABILITY = FALSE
    REMEDIATION_PATH = (ARCHITECTURAL_REPLACEMENT_OF_LLM) OR (HARDWARE_ARCHITECTURE_CHANGE_WITH_OBSERVABILITY)
ELSE
    [Analysis not applicable — system outside characterized class]

SYNTHESIS: Cross-Register Implications

Final Meta-Assessment

• Reproducible: Four independent models converged on identical sufficient set
• Traceable: Every claim maps to specific evidence blocks and regulatory characterizations
• Actionable: Industry impacts are prioritized and remediability assessed
• Resilient: External artifact mapping confirms or contextualizes findings without reopening them