neotic.app

Create or resolve an abstract task structure without storing raw private content (§24).

Retrieve applicable validated strategies for a task (§24, §18).

Start an experience episode (§24, §10).

Convert natural-language task text into CIR and task_structure dict.

Record an observable event in an ongoing experience episode (§24, §7).

Submit the structured outcome of an experience episode (§24, §10).

Propose a candidate strategy from problem-solving experience (§24, §2).

Run objective deterministic verification on a strategy (§24, §16).

Record whether a transferred strategy helped or harmed on a novel task (§24, §19).

Retrieve a usable strategy: steps, when to use, when not, evidence summary.

Retrieve details and benchmark results of an experiment (§24, §69).

One-call orchestration: identify → gate → guide → solve → verify → report.

Evidence dossier: baseline vs assisted, distribution, CI, failures, last eval.

Discovery: list recorded benchmark experiment IDs for cognitive.

End-to-end autonomy: identify → guide → execute → baseline → verify → verdict.

Few-shot learning: induce a generalized procedural StrategyIR from 1-3 problem traces.

Online Real-Time Error Reflection & Strategy Patching.

Skill Composition: synthesize a composite multi-stage StrategyIR from primitive strategies.

Perform logical deduction (Horn clauses) or exact probabilistic Bayesian network inference.

Perform Monte Carlo Tree Search (UCT) over action sequences to find optimal trajectory.

Decompose high-level goals into milestone subgoals using Hierarchical Task Network (HTN) planning.

Distinguish causal effects (do-calculus) from spurious correlation via backdoor adjustment.

Synthesize new algorithmic Python procedures on the fly with AST sandboxing and verification.

Transfer structural strategies across disparate domains via Structure-Mapping Engine (SME).

Forward world model: predict future state trajectories and uncertainty bounds under actions.

Simulate and rank candidate actions by predicted feasibility, reward, and constraint safety.

Counterfactual engine: evaluate 'What if I had done X instead of Y at step t?

Online world model learning: update state transition priors from empirical execution traces.

Epistemic boundary awareness: classify task into KNOWN, KNOWN_UNKNOWN, or UNKNOWN_UNKNOWN (OOD) and track calibration.

Adaptive compute budgeting: select compute tier (Fast Path to Deep Deliberation) and timeout based on EVC.

Introspective reasoning critic: inspect trace in-flight to catch cycles, invariant drift, vacuous output, and stalling.

Engine self-model introspection: inspect capabilities, domain competence, active subsystems, and safety status.

Safe self-improvement: propose modifications guarded by immutable verification oracles and anchor regressions.

Theory of Mind: model agents' BDI mental states, test false beliefs (Sally-Anne), and infer goals via inverse planning.

Multi-agent cooperation: analyze game payoff matrices, compute Nash/Pareto equilibria, and execute reciprocity policies.

Pragmatic communication: audit speech acts against Gricean maxims (Quality, Quantity, Relation, Manner) and detect deception.

Normative ethics & fairness: enforce deontological vetos, evaluate Rawlsian vs Utilitarian welfare, and arbitrate moral dilemmas.

Non-LLM compositional semantics: parse utterance into semantic predicates and evaluate directly against WorldState.

Pragmatics: resolve indirect speech acts (e.

Interactive language acquisition: learn word-concept bindings through cross-situational observation, games, and feedback.

Inspect grounded lexicon acquired via situated interaction (learned vocabulary, concept bindings, confidence).

Compute intrinsic drives: novelty & prediction surprise curiosity, empowerment (channel capacity), and learning progress.

Autonomous goal synthesis from world deficits, depleted reserves, and exploration frontiers with multi-criteria prioritization.

Infer human values via Bradley-Terry IRL, detect Goodhart's law / specification gaming, and assess CIRL deference.

Arbitrate short vs long term payoffs using hyperbolic vs exponential discounting and Ulysses pre-commitment contracts.

Evaluate or simplify mathematical expressions (PEMDAS with power, functions like sqrt, exp, log, sin, cos).

Solve linear equations (ax + b = c), quadratic equations (ax^2 + bx + c = 0), or linear systems (A x = b).

Solve math word problems (GSM8K/SVAMP/MATH) via topological constraint propagation.

Number theory: primality, factoring, extended GCD, Diophantine, modular inverse, CRT, combinatorics, Fibonacci.

Exact rational matrix & vector algebra: multiply, determinant, inverse, transpose, trace, eigenvalues, dot/cross.

Formally verify an arithmetic equality claim, audit numerical stability, condition number, and cancellation risks.

Instantiate and initialize a simulated cognitive environment (spatial_commons, multi_agent_arena, sequential_puzzle).

Step an active simulated environment with an agent action.

Run the end-to-end cognitive agent closed loop (Perceive -> Model -> Decide -> Act -> Reflect -> Learn).

Simulate repeated multi-agent interaction with social dilemmas, speech acts, and reputation tracking.

Evaluate broad generalization across spatial commons, multi-agent arenas, and sequential causal puzzles.

Build or update an Evidence-Carrying Cognitive Graph for a task structure and solution trace.

Audit the evidence graph for a task before issuing final answers.

Compile a final evidence result listing supporting evidence, assumptions, missing evidence, contradictions, unchecked dependencies, confidence, and invalidation conditions.

Evaluate support status and confidence for an individual claim with evidence.

Synthesize the best verified plan across candidate rollouts, uncertainty tracking, and constraint pruning.

Evaluate a counterfactual query on a plan ('What if capacity drops?

Compile a Dynamic Constraint Lattice (DCL) into algebraic boundaries, conservation laws, and reachability cones.

Verify a candidate state or transition S_t -> S_{t+1} against invariant boundary manifolds.

Project a candidate state or plan step onto the Singular Transition Manifold M = F(S0) ∩ B(Goal).

Synthesize an optimal, invariant-verified trajectory from initial state to goal through the singular bottleneck.

Compute coordinate-free topological invariant signature of a lattice or task.

Discover topological homomorphism between source experience and target problem, transducing solution paths.

Autonomously evolve higher-order invariants, tighten bounds, and discover cliques from execution feedback.

Subject candidate trajectories to adversarial algebraic perturbations to calculate Robustness Index (R) and project hardened paths.

Create or resolve an abstract task structure without storing raw private content (§24).

Retrieve applicable validated strategies for a task (§24, §18).

Start an experience episode (§24, §10).

Record an observable event in an ongoing experience episode (§24, §7).

Submit the structured outcome of an experience episode (§24, §10).

Propose a candidate strategy from problem-solving experience (§24, §2).

Run objective deterministic verification on a strategy (§24, §16).

Record whether a transferred strategy helped or harmed on a novel task (§24, §19).

Retrieve a usable strategy: steps, when to use, when not, evidence summary.

Retrieve details and benchmark results of an experiment (§24, §69).

End-to-end autonomy: identify → guide → execute → baseline → verify → verdict.

One-call orchestration: identify → gate → guide → solve → verify → report.

Discovery: list recorded benchmark experiment IDs for cognitive.

Convert natural-language task text into CIR and task_structure dict.

Evidence dossier: baseline vs assisted, distribution, CI, failures, last eval.

Few-shot learning: induce a generalized procedural StrategyIR from 1-3 problem traces.

Online Real-Time Error Reflection & Strategy Patching.

Skill Composition: synthesize a composite multi-stage StrategyIR from primitive strategies.

Perform logical deduction (Horn clauses) or exact probabilistic Bayesian network inference.

Perform Monte Carlo Tree Search (UCT) over action sequences to find optimal trajectory.

Decompose high-level goals into milestone subgoals using Hierarchical Task Network (HTN) planning.

Distinguish causal effects (do-calculus) from spurious correlation via backdoor adjustment.

Synthesize new algorithmic Python procedures on the fly with AST sandboxing and verification.

Transfer structural strategies across disparate domains via Structure-Mapping Engine (SME).

Forward world model: predict future state trajectories and uncertainty bounds under actions.

Simulate and rank candidate actions by predicted feasibility, reward, and constraint safety.

Counterfactual engine: evaluate 'What if I had done X instead of Y at step t?

Online world model learning: update state transition priors from empirical execution traces.

Epistemic boundary awareness: classify task into KNOWN, KNOWN_UNKNOWN, or UNKNOWN_UNKNOWN (OOD) and track calibration.

Adaptive compute budgeting: select compute tier (Fast Path to Deep Deliberation) and timeout based on EVC.

Introspective reasoning critic: inspect trace in-flight to catch cycles, invariant drift, vacuous output, and stalling.

Engine self-model introspection: inspect capabilities, domain competence, active subsystems, and safety status.

Safe self-improvement: propose modifications guarded by immutable verification oracles and anchor regressions.

Theory of Mind: model agents' BDI mental states, test false beliefs (Sally-Anne), and infer goals via inverse planning.

Multi-agent cooperation: analyze game payoff matrices, compute Nash/Pareto equilibria, and execute reciprocity policies.

Pragmatic communication: audit speech acts against Gricean maxims (Quality, Quantity, Relation, Manner) and detect deception.

Normative ethics & fairness: enforce deontological vetos, evaluate Rawlsian vs Utilitarian welfare, and arbitrate moral dilemmas.

Non-LLM compositional semantics: parse utterance into semantic predicates and evaluate directly against WorldState.

Pragmatics: resolve indirect speech acts (e.

Interactive language acquisition: learn word-concept bindings through cross-situational observation, games, and feedback.

Inspect grounded lexicon acquired via situated interaction (learned vocabulary, concept bindings, confidence).

Compute intrinsic drives: novelty & prediction surprise curiosity, empowerment (channel capacity), and learning progress.

Autonomous goal synthesis from world deficits, depleted reserves, and exploration frontiers with multi-criteria prioritization.

Infer human values via Bradley-Terry IRL, detect Goodhart's law / specification gaming, and assess CIRL deference.

Arbitrate short vs long term payoffs using hyperbolic vs exponential discounting and Ulysses pre-commitment contracts.

Evaluate or simplify mathematical expressions (PEMDAS with power, functions like sqrt, exp, log, sin, cos).

Solve linear equations (ax + b = c), quadratic equations (ax^2 + bx + c = 0), or linear systems (A x = b).

Solve math word problems (GSM8K/SVAMP/MATH) via topological constraint propagation.

Number theory: primality, factoring, extended GCD, Diophantine, modular inverse, CRT, combinatorics, Fibonacci.

Exact rational matrix & vector algebra: multiply, determinant, inverse, transpose, trace, eigenvalues, dot/cross.

Formally verify an arithmetic equality claim, audit numerical stability, condition number, and cancellation risks.

Instantiate and initialize a simulated cognitive environment (spatial_commons, multi_agent_arena, sequential_puzzle).

Step an active simulated environment with an agent action.

Run the end-to-end cognitive agent closed loop (Perceive -> Model -> Decide -> Act -> Reflect -> Learn).

Simulate repeated multi-agent interaction with social dilemmas, speech acts, and reputation tracking.

Evaluate broad generalization across spatial commons, multi-agent arenas, and sequential causal puzzles.

Build or update an Evidence-Carrying Cognitive Graph for a task structure and solution trace.

Audit the evidence graph for a task before issuing final answers.

Compile a final evidence result listing supporting evidence, assumptions, missing evidence, contradictions, unchecked dependencies, confidence, and invalidation conditions.

Evaluate support status and confidence for an individual claim with evidence.

Synthesize the best verified plan across candidate rollouts, uncertainty tracking, and constraint pruning.

Evaluate a counterfactual query on a plan ('What if capacity drops?

Compile a Dynamic Constraint Lattice (DCL) into algebraic boundaries, conservation laws, and reachability cones.

Verify a candidate state or transition S_t -> S_{t+1} against invariant boundary manifolds.

Project a candidate state or plan step onto the Singular Transition Manifold M = F(S0) ∩ B(Goal).

Synthesize an optimal, invariant-verified trajectory from initial state to goal through the singular bottleneck.

Compute coordinate-free topological invariant signature of a lattice or task.

Discover topological homomorphism between source experience and target problem, transducing solution paths.

Autonomously evolve higher-order invariants, tighten bounds, and discover cliques from execution feedback.

Subject candidate trajectories to adversarial algebraic perturbations to calculate Robustness Index (R) and project hardened paths.