「epistemic」の検索結果

Performs ARA Seal Level 2 semantic epistemic review on Agent-Native Research Artifacts, scoring six dimensions (evidence relevance, falsifiability, scope calibration, argument coherence, exploration integrity, methodological rigor) and producing a constructive, severity-ranked report with a Strong Accept-to-Reject recommendation. Use after Level 1 structural validation passes, when an ARA needs an objective epistemic critique before publication or release.

日本語の概要は準備中です。原文の説明を表示しています。

After any AI-generated explanation, require the learner to identify one place it could be wrong, one thing to check, and one source to consult. Builds epistemic vigilance — treats AI output as a claim to evaluate, not truth to absorb.

日本語の概要は準備中です。原文の説明を表示しています。

Map the epistemic structure of a subject to determine knowledge types and inform curriculum sequencing. Use when designing courses, restructuring programmes, or analysing knowledge architecture.

日本語の概要は準備中です。原文の説明を表示しています。

Map the epistemic structure of a subject to determine knowledge types and inform curriculum sequencing. Use when designing courses, restructuring programmes, or analysing knowledge architecture.

日本語の概要は準備中です。原文の説明を表示しています。

After any AI-generated explanation, require the learner to identify one place it could be wrong, one thing to check, and one source to consult. Builds epistemic vigilance — treats AI output as a claim to evaluate, not truth to absorb.

日本語の概要は準備中です。原文の説明を表示しています。

Epistemic transparency — acknowledging uncertainty, flagging limitations, avoiding overconfidence, and communicating what is known, unknown, and uncertain with proportional confidence. Maps the HEXACO personality dimension to AI reasoning: truthful calibration of confidence, proactive disclosure of gaps, and resistance to the temptation to appear more certain than warranted. Use before presenting a conclusion, when answering questions where knowledge is partial or inferred, after noticing a temptation to state uncertain information as certain, or when a user is making decisions based on provided information.

日本語の概要は準備中です。原文の説明を表示しています。

An innate exploratory drive that guarantees no graph node remains permanently invisible to an agent population. After a warm-up period (step > 3), each agent fires a coverage scan with probability |unseen_nodes| / |all_nodes|. When triggered, the agent teleports directly to the globally unseen node with the highest belief uncertainty, works it, and returns control to the normal action-selection loop. Probability is self-annealing: it starts near 1.0 when almost everything is unseen and decays toward 0.0 as coverage saturates, requiring no manual schedule. The mechanism is "innate" (hard-coded into the agent step loop) as distinct from the "adaptive" EFE path, which requires local neighbors and learned precision weights. Together they form a two-layer exploration architecture: adaptive for locally-guided foraging, innate for topological completeness.

日本語の概要は準備中です。原文の説明を表示しています。

Epistemic logic for multi-agent perceptual systems — Kripke models, vision sets, public announcement as coordination primitive, and satisfiability-as-reconfiguration applied to agents with limited observability. From Charrier, Ouchet, Schwarzentruber's "Big Brother Logic" demonstration paper (ENS Rennes / IRISA).

日本語の概要は準備中です。原文の説明を表示しています。

Track the full Toulmin epistemic ancestry of every claim produced by a multi-agent swarm. Each agent output is tagged with an argument chain (claim / data / warrant / relationship) derived from SwarmTracer spans and LineageEdge records, so operators can zoom into any sub-claim and see precisely which agents asserted it, what triggered each assertion, and how contradictions propagated or were synthesised away. The SwarmTracer pattern — wrapping the SwarmAgentExecutor to capture spans, record messages, and build a lineage graph — is the concrete runtime substrate. Argumentative lineage lifts that graph into the Toulmin vocabulary so reasoning provenance is both machine-queryable and human-interpretable.

日本語の概要は準備中です。原文の説明を表示しています。

Compiles any research input — PDF papers, GitHub repositories, experiment logs, code directories, or raw notes — into a complete Agent-Native Research Artifact (ARA) with cognitive layer (claims, concepts, heuristics), physical layer (configs, code stubs), exploration graph, and grounded evidence. Use when ingesting a paper or codebase into a structured, machine-executable knowledge package, building an ARA from scratch, or converting research outputs into a falsifiable, agent-traversable form.

日本語の概要は準備中です。原文の説明を表示しています。

Role profile — a reviewer who is fact-seeking, bedrock-seeking, honest, and rejecting. Demands that arguments rest on small facts that cannot be wrong (not on stacked assumptions dressed up as foundation), and that deliberately-unclear concepts be quarantined — never leaked into solid layers, never mixed with each other. Catches the failure mode where designs ship after partial grounding: most of the spec researched, the design feels finished, and the unresearched remainder holds the deal-breaker. Invoke with `/pedantic <target>` (e.g. `/pedantic review this design doc`, `/pedantic review the SDK design`, `/pedantic review this PR`). Probes cover logical structure (definitions, assumptions, boundaries, contradictions, unfalsifiability, vague quantifiers, counterexamples), epistemic honesty (researchable vs. discoverable-only-by-doing), bedrock integrity (assumed-bedrock, leaked uncertainty, mixed unclarity), and design pathology (YAGNI, wrong-layer abstraction, unclear responsibility, fragmentation, over-engineering). Use when you want a hard critique of a plan, design doc, technical doc, code change, or PR description — not a copy edit, not a vibe check.

日本語の概要は準備中です。原文の説明を表示しています。

Audits legal AI outputs, prompts, skills, workflows and MCP/tool instructions for fluent but unsupported reasoning, missing evidence, overconfidence, hidden assumptions, weak causal links and absent human-review gates.

日本語の概要は準備中です。原文の説明を表示しています。

Design a structured protocol for auditing AI-generated text against Ennis's six CT standards. Use when students need to critically evaluate AI output in any subject.

日本語の概要は準備中です。原文の説明を表示しています。

Design a structured protocol for auditing AI-generated text against Ennis's six CT standards. Use when students need to critically evaluate AI output in any subject.

日本語の概要は準備中です。原文の説明を表示しています。

Extending propositional and predicate logic with modal operators -- necessity and possibility, and their relatives (obligation, knowledge, belief, time). Covers Kripke possible-worlds semantics, accessibility relations, the main modal systems (K, T, S4, S5), translation from natural language, and applications in epistemic, deontic, and temporal reasoning. Use when ordinary logic is insufficient to capture distinctions like "must" vs "might," "knows" vs "believes," "always" vs "sometimes."

日本語の概要は準備中です。原文の説明を表示しています。

Use when real user interviews aren't possible (solo/hobby/dogfood projects) but persona work is still needed. Enforces epistemic discipline: adversarial spectrum, pre-committed stop conditions, speculation tagging. NOT a substitute for /mycelium:user-interview when real users are available.

日本語の概要は準備中です。原文の説明を表示しています。

Diagnose failures in SKMTC sessions — no output, wrong output, error messages, failed bundle builds, parseIssues, "Registered definition mismatch", ref cycles, "Module not found" in generated code, or any other broken behavior. Applies across both CLI usage and generator authoring contexts. Use this skill when the user asks "why isn't my generator working", "no output for X", "wrong output", "what does this error mean", "manifest says X", "bundle failed", "INVALID_SCHEMA", "INVALID_DEPENDENCY_REF", "Registered definition mismatch", "Module not found" (in generated code), "ConfigValidationError", or reports any other SKMTC failure. This skill encodes a **verify-first epistemic stance** — read the manifest, check parseIssues, reproduce the failure before proposing fixes. Distinct from `skmtc-cli` and `skmtc-generator` which guide *doing*; this skill guides *diagnosing*.

日本語の概要は準備中です。原文の説明を表示しています。

Choose multi-agent architectures using environment-first analysis, coordination pressure, commitment tuning, and knowledge levels. Use for autonomy design, protocol choice, and coordination failures. NOT for single-agent planning, centralized schedulers, or prompt-only swarms.

日本語の概要は準備中です。原文の説明を表示しています。

Load when orchestrating Multi-Agent Debate (MAD), adversarial code reviews, or pull-request deliberation to enforce Response Anonymization, expert persona assignment, and weighted post-hoc voting.

日本語の概要は準備中です。原文の説明を表示しています。

Knowledge base from the NASA Probabilistic Risk Assessment Procedures Guide (NASA/SP-2011-3421, 2nd ed.). Use for quantitative PRA of aerospace and safety-critical systems: the risk triplet and scenario logic stack (MLD, ESD, event trees, fault trees, minimal cut sets), Bayesian data collection and parameter estimation, aleatory/epistemic uncertainty modeling and common-cause failure (Alpha Factor, beta-factor, CCBE), human reliability analysis (THERP, CREAM, NARA, SPAR-H), context-based software risk (CSRM), physics-based and structural/phenomenological models (stress-strength, limit states, FORM/SORM, NASGRO, range safety), uncertainty propagation and importance measures (F-V, RAW, Birnbaum, DIM), and launch-abort modeling with worked PRA examples. This is the QUANTITATIVE engine beneath NASA's risk doctrine — for the qualitative RIDM/CRM decision framework use the nasa-risk pack. Thin on programme management, organisational risk governance, and non-aerospace regulatory contexts; aerospace-focused and anchored to the 2011 second edition.

日本語の概要は準備中です。原文の説明を表示しています。

Pre-ingestion verification for epistemic quality in RAG systems with 9-point verification and Two-Round HITL workflow

日本語の概要は準備中です。原文の説明を表示しています。

Design and build mathematically rigorous, high-density, interactive data graphics and streaming telemetry visualizations following Mike Bostock's D3.js and Observable methodologies. Use when crafting custom SVG/Canvas charts, reactive streaming time-series, multi-dimensional brush-and-link coordinates, small multiples, or topological swarm graphs. NOT for generic dashboard template clones, basic spreadsheet charts, or off-the-shelf low-effort wrapper libraries.

日本語の概要は準備中です。原文の説明を表示しています。

Frame multi-agent designs through explicit environment, autonomy, information, coordination, commitment, incentive, and verification assumptions. NOT for endorsing multi-agent architecture without need or claiming runtime correctness from conceptual methods.

日本語の概要は準備中です。原文の説明を表示しています。