{"results":[{"id":"beliefs-cli-vs-reasons-cli","text":"Two CLIs at different levels: beliefs CLI is a structured markdown KB with provenance and manual maintenance (simple, flat). reasons CLI (ftl-reasons) is a full TMS with automatic propagation, cascades, backtracking, and LLM-driven operations (powerful, dependency-aware). Use beliefs for independent facts, reasons for justified conclusions with dependency chains","truth_value":"IN","justification_count":0,"dependent_count":1,"challenges":[],"last_reviewed":null,"review_result":null},{"id":"cognitive-budget","text":"Cognitive budget principle borrowed from graphics frame budgets: decompose work into focused passes (TMS pass, RAG pass, merge pass) each within the model's attention budget. Mixing beliefs and document chunks in a single prompt degrades performance (Opus drops 95.5% to 86%); three focused passes achieve 100%","truth_value":"IN","justification_count":0,"dependent_count":1,"challenges":[],"last_reviewed":null,"review_result":null},{"id":"construction-vs-retrieval","text":"Construction cost dominates: O(chunks) + O(beliefs x rounds). But it amortizes across all queries O(queries). Expensive to build, cheap to query at scale","truth_value":"IN","justification_count":0,"dependent_count":0,"challenges":[],"last_reviewed":null,"review_result":null},{"id":"dual-path-architecture","text":"Dual-path retrieval: TMS path (pre-computed beliefs) + FTS path (source chunk search), merged by a third pass. This is how EEM is queried at scale. Each path stays within cognitive budget","truth_value":"IN","justification_count":1,"dependent_count":0,"challenges":[],"last_reviewed":null,"review_result":null},{"id":"eem-epistemic","text":"Epistemic means not just facts but justified beliefs with truth values (IN/OUT), retraction cascades, contradiction records (nogoods), and derivation depth. This distinguishes EEM from RAG (which is external semantic memory but not epistemic)","truth_value":"IN","justification_count":0,"dependent_count":4,"challenges":[],"last_reviewed":null,"review_result":null},{"id":"evidence-beliefs-ablation","text":"Beliefs alone outperform beliefs + expert prompt: Opus 100% vs 94.2% (+5.8pp), Sonnet 94.2% vs 91.8% (+2.4pp). Adding expert prompt hurts — agent trusts its 'expertise' instead of consulting the knowledge base","truth_value":"IN","justification_count":0,"dependent_count":2,"challenges":[],"last_reviewed":null,"review_result":null},{"id":"evidence-depth-ceiling","text":"Beliefs beyond depth 8 do not survive review. Retraction rate: 0% at depth 0, rising to 100% at depth 9+. The universal TMS is wide rather than deep","truth_value":"IN","justification_count":0,"dependent_count":1,"challenges":[],"last_reviewed":null,"review_result":null},{"id":"evidence-model-compensation","text":"EEM compensates for model size: Sonnet+beliefs approximates Opus without beliefs. Haiku with dual-path achieves 94% A+B, matching Opus at 98%","truth_value":"IN","justification_count":0,"dependent_count":1,"challenges":[],"last_reviewed":null,"review_result":null},{"id":"evidence-retraction-rate","text":"13-37% of derived beliefs are retracted per review round across multiple expert KBs. Self-correction works — the system finds and removes its own errors","truth_value":"IN","justification_count":0,"dependent_count":1,"challenges":[],"last_reviewed":null,"review_result":null},{"id":"expert-pipeline","text":"Expert pipeline: chunk source material → propose beliefs → human accepts → derive connections → review derivations → export. Value accrues at each stage, with derive producing new knowledge (connections the source doesn't make explicit)","truth_value":"IN","justification_count":1,"dependent_count":1,"challenges":[],"last_reviewed":null,"review_result":null},{"id":"frame-problem","text":"McCarthy & Hayes (1969) frame problem: what persists across state changes. check-stale addresses this by detecting when source files change under beliefs","truth_value":"IN","justification_count":0,"dependent_count":0,"challenges":[],"last_reviewed":null,"review_result":null},{"id":"how-agents-use-eem","text":"LLM agents use EEM by: querying beliefs via search/show/explain before answering, citing node IDs for auditability, running derive to generate new beliefs from existing ones, running review-beliefs to self-audit, recording nogoods when contradictions appear. The agent does not need to be told it is an expert — the knowledge base speaks for itself","truth_value":"IN","justification_count":1,"dependent_count":0,"challenges":[],"last_reviewed":null,"review_result":null},{"id":"how-humans-use-eem","text":"Humans use EEM by: inspecting beliefs.md for current state, running reasons explain to understand why something is believed, challenging beliefs with reasons challenge, reviewing the network with reasons status, checking staleness with reasons check-stale. The key value is visibility — humans can see and audit what the system knows","truth_value":"IN","justification_count":1,"dependent_count":0,"challenges":[],"last_reviewed":null,"review_result":null},{"id":"how-to-start","text":"To start using EEM: (1) reasons init — creates reasons.db, (2) add premises from observations with reasons add, (3) add justified conclusions with --sl to link dependencies, (4) use reasons derive to find connections, (5) use reasons review-beliefs to audit, (6) retract when evidence changes and let cascades propagate","truth_value":"IN","justification_count":1,"dependent_count":0,"challenges":[],"last_reviewed":null,"review_result":null},{"id":"hybrid-tms","text":"ftl-reasons is a hybrid TMS: symbolic TMS handles structure (justifications, propagation, cascades, backtracking, challenge/defend) while LLMs handle semantic operations (derive generates beliefs, review-beliefs critiques them, contradiction detection finds nogoods)","truth_value":"IN","justification_count":1,"dependent_count":4,"challenges":[],"last_reviewed":null,"review_result":null},{"id":"llm-as-problem-solver","text":"Putting an LLM in the TMS problem-solver slot (generator via derive, critic via review-beliefs and contradiction detection) is what Doyle's architecture prescribes. The open question is whether an LLM is a good problem solver, not whether using one is faithful to the design","truth_value":"IN","justification_count":1,"dependent_count":1,"challenges":[],"last_reviewed":null,"review_result":null},{"id":"model-stacking","text":"Multi-pass agent pattern: Model A generates candidates → TMS records with provenance → Review critiques (machine + human) → Model B receives validated beliefs → Model B derives new beliefs → Review critiques derivations → Repeat. Each level is a full model pass with fresh context and critique pipeline as quality gate","truth_value":"IN","justification_count":1,"dependent_count":0,"challenges":[],"last_reviewed":null,"review_result":null},{"id":"multi-agent-beliefs","text":"Multi-agent TMS: import-agent imports another agent's beliefs with SL justifications including agent:active as antecedent. Node is IN iff agent is active AND original belief is justified. Doyle-style truth maintenance across agents","truth_value":"IN","justification_count":1,"dependent_count":0,"challenges":[],"last_reviewed":null,"review_result":null},{"id":"reasons-for-maintenance-beliefs-for-queries","text":"Architecture pattern: use reasons database for all structural operations (add, retract, derive, review). Export to beliefs.md for querying (fast, human-readable, grep-able). Keep both in sync via reasons export-markdown","truth_value":"IN","justification_count":1,"dependent_count":0,"challenges":[],"last_reviewed":null,"review_result":null},{"id":"scale-evidence","text":"EEM scales from small domains (237 beliefs, aap-expert) to large enterprises (12,731 beliefs, redhat-expert). 40+ expert knowledge bases built across code, product, project, and domain-specific experts","truth_value":"IN","justification_count":1,"dependent_count":0,"challenges":[],"last_reviewed":null,"review_result":null}],"count":20,"limit":20,"offset":0}