Didactic terminology guide
Wrapper concepts explained in plain language. Designed for learners, professionals, and critical users.
This glossary explains core Comm-SCI-Control runtime terms without requiring prior implementation knowledge. Each term includes practical relevance for daily wrapper operation.
Part 1
Core wrapper terms
| Term | Meaning | Why it matters |
|---|---|---|
| Anchor | State snapshot refresh command (`Comm Anchor`). | Stabilizes long-session context. |
| Anchor snapshot | Compact state excerpt produced by `Comm Anchor`. | Supports clean chat handover while preserving context continuity. |
| Audit | Compliance scan of prior responses. | Enables systematic quality assurance (quickly visible what in the LLM response is supported, uncertain, or non-compliant). |
| CGI | Cognitive Gain Indicator user-feedback signal. | Tracks perceived clarity/insight/efficiency gain. |
| Color tags | 🟢 [GREEN] / 🟡 [YELLOW] / 🔴 [RED] evidence confidence markers. | Signals confidence level at reading time. |
| Compliance prerequisites | Conditions checked before output is accepted. | Prevents non-compliant responses. |
| Constraints | Binding limits for structure, evidence handling, and style. | Prevents governance drift in long or complex responses. |
| Contract tests | Tests for formal behavioral guarantees. | Checks after changes that interfaces and rules still behave as agreed (no reintroduction of old failures). |
| Control-layer block | Explicit block output on hard contract violations. | Stops unsafe/non-conformant responses. |
| Context-Pressure-Guard | Threshold mechanism against drift under heavy context load. | Prioritizes core rules before relevant content gets diluted. |
| CSC | Comm-SCI-Control governance framework. | Defines rule-based human-LLM interaction discipline. |
| Drift | Deviation from expected governance behavior over time. | Early warning for quality degradation. |
| Explore | Mode with higher tolerance for ideation and hypotheses. | Useful for brainstorming, not for hard claims. |
| Execution pipeline | Fixed runtime stage order from parse to render. | Reduces random drift and keeps behavior predictable. |
| Language policy | Language behavior mode (`production`/`benchmark`). | Separates user operation from comparison experiments. |
| Logs | Persisted runtime and conversation artifacts. | Foundation for diagnosis and reproducibility. |
| Manual test | Guided panel-based manual verification routines. | Covers real operator flows beyond unit tests. |
| Module status | Visible health/status of key wrapper modules. | Supports diagnostics and maintenance. |
| Overlay | Additional mode layer above profile (for example Strict/Explore). | Adjusts behavior without full profile switch. |
| Pending selection | Interim state after `SCI on` until A-H is selected. | Prevents accidental variant switching. |
| Pressure | Context pressure from high token load, many objectives, or conflicting constraints. | Signals when to compress, re-anchor, or switch modes. |
| Provenance | Traceable origin of a claim down to source level. | Required for audit, source-conflict handling, and strong claims. |
| QC footer | Output line that shows QC values (and deltas when applicable). | Provides fast per-answer quality inspection. |
| QC matrix | Quality dimensions with target/actual scoring. | Makes response quality explicit and comparable. |
| QC overrides | Temporary manual deviations from profile QC targets. | Allows controlled adaptation for special cases. |
| R-RAG rules | Robust RAG rules for retrieval-grounded claims. | Blocks strong claims when source quality is insufficient. |
| RAG Governance | Rule set for source-grounded claims with quality classes. | Protects provenance clarity, source quality, and conflict handling. |
| Recurse behavior | Temporary deepening path via `SCI recurse`. | Allows focused deep dives without losing main context. |
| Regression tests | Tests for previously fixed failure patterns. | Prevents reintroduction of old bugs. |
| Runtime contract | Technical contract for allowed output structure. | Enforces deterministic behavior. |
| SCI | Structured answer mode with visible trace steps. | Improves transparency of reasoning output. |
| SCI orchestration | Control logic for SCI activation, variant selection, and trace enforcement. | Keeps SCI behavior deterministic. |
| SCI variants | A-H method profiles for different reasoning styles. | Matches reasoning structure to task type. |
| Self-Debunking | Required block that challenges answer weaknesses. | Reduces overconfidence and blind spots. |
| Strict | Mode with stronger evidence and consistency discipline. | Useful for high-stakes precision output. |
| Token | Smallest processing unit in model context windows. | Defines effective context budget and influences output stability. |
| Timestamp | Output time metadata in rendered response. | Important for audit timeline and traceability. |
| Trace-step requirements | Mandatory SCI steps that must appear in answers. | Enables contract validation and reproducibility. |
| Uncertainty labeling U1-U8 | Standardized uncertainty codes for data, method, and source-quality limits. | Makes uncertainty explicit instead of hiding it in prose. |
| JSON | Machine-readable format for Comm-SCI rules and runtime state. | Keeps governance configuration versioned and reproducible. |
| Verification gates | Rules for strong/risky claims requiring explicit verification route. | Protects against unsupported certainty. |
Part 2
SCI variants A-H with task examples
| Variant | Focus | Best suited for | Example prompt type |
|---|---|---|---|
| A Standard | Plan -> Solution -> Check | General analytical questions with clear objective. | "Compare method X and method Y." |
| B Deep-Dive | Extended dialectical trace (SCIplus) | Complex contentious topics with competing views. | "Evaluate AGI governance tradeoffs." |
| C Branch Evaluation | Branch generation and selection | Multi-option strategy decisions. | "Which of three project paths should we pick?" |
| D Axiomatic Reduction | First-principles derivation | Problems that benefit from base-assumption reduction. | "Derive this decision from fundamental constraints." |
| E Confidence Tracker | Confidence update with counterarguments | Uncertain hypotheses under active challenge. | "How should confidence change after new objections?" |
| F Impact Projection | Second-order effects and feedback loops | Policy/system changes with downstream consequences. | "What second-order effects follow this intervention?" |
| G Failure Mode Analysis | Pre-mortem and mitigation planning | Risk planning and failure prevention. | "How could this project fail, and how do we prevent it?" |
| H Multi-Agent Simulation | Role-based perspective synthesis | Decisions requiring multiple expert viewpoints. | "How do legal, medical, and operations roles disagree here?" |
Part 3
QC matrix: value meanings (0-3)
| Dimension | 0 | 1 | 2 | 3 |
|---|---|---|---|---|
| Clarity | very unclear | partly unclear | clear | very clear and well structured |
| Brevity | far too long | too long | appropriately compact | very compact while still useful |
| Evidence | pure speculation | weakly supported | solid support | strongly supported |
| Empathy | ignores user perspective | low consideration | adequate consideration | highly considerate without flattery |
| Consistency | contradictory | unstable | mostly consistent | highly consistent and justified |
| Neutrality | biased/one-sided | partly one-sided | mostly balanced | actively bias-reducing |
Next steps