{"results":[{"id":"agm-belief-revision","text":"AGM (Alchourrón, Gärdenfors, Makinson 1985) provides formal theory for rational belief revision. Entrenchment scoring in backtracking is a crude approximation of AGM","truth_value":"IN","justification_count":0,"dependent_count":1,"challenges":[],"last_reviewed":null,"review_result":null,"source_type":""},{"id":"amortization-argument","text":"EEM construction is expensive but amortizes. ~$300 Sonnet for 13,511 beliefs. Each query costs ~$0.01. Breakeven at 100-250 queries. After that, every query is cheaper than re-reading source documents from scratch.","truth_value":"IN","justification_count":2,"dependent_count":0,"challenges":[],"last_reviewed":"2026-05-30T07:02:40","review_result":"invalid","source_type":""},{"id":"belief-registry-externalizes-critique","text":"The belief registry externalizes and persists the critic's judgments. Instead of relying on the same LLM to both generate and evaluate (which fails — self-critique damages accuracy -3pp to -41.5pp), the registry stores review outcomes as truth values (IN/OUT), retraction records, and nogoods. The critic's work survives across sessions and is available to any model.","truth_value":"IN","justification_count":0,"dependent_count":1,"challenges":[],"last_reviewed":null,"review_result":null,"source_type":""},{"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,"source_type":""},{"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,"source_type":""},{"id":"compaction-destroys-networks","text":"Context compaction destroys justification networks. Quantified across 33 measured compaction events in beliefs-pi. Justification chains, dependency structures, and correction history are lost when the context window is compressed.","truth_value":"IN","justification_count":0,"dependent_count":2,"challenges":[],"last_reviewed":null,"review_result":null,"source_type":""},{"id":"construction-cost-measured","text":"EEM construction cost measured for enterprise scale (6 departments, 5,366 sources, 13,511 beliefs): ~$300 at Sonnet pricing, ~$1,500 at Opus pricing. Dominant cost is the summarize step (~98M tokens). Per-query breakeven at 100-250 queries — after that, every query is cheaper than re-reading source documents.","truth_value":"IN","justification_count":0,"dependent_count":2,"challenges":[],"last_reviewed":null,"review_result":null,"source_type":""},{"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":1,"challenges":[],"last_reviewed":null,"review_result":null,"source_type":""},{"id":"continuity-human-problem","text":"The human cannot track what the LLM currently has in context. Context windows are opaque and compaction destroys justification networks. EEM solves this via visibility and persistence — the human can always inspect the current belief state regardless of what the model has in context.","truth_value":"IN","justification_count":2,"dependent_count":1,"challenges":[],"last_reviewed":"2026-05-30T07:02:40","review_result":"invalid","source_type":""},{"id":"cross-model-portability","text":"EEM works across model providers and sizes. The same belief network can be queried by Claude, Gemini, local models, or any LLM that can read text. Model upgrades, provider swaps, and cost optimization (Opus→Haiku) preserve all knowledge. The beliefs are plain text with structure — no model-specific format.","truth_value":"IN","justification_count":0,"dependent_count":1,"challenges":[],"last_reviewed":null,"review_result":null,"source_type":""},{"id":"derive-overshoot-observed","text":"Derive over-generates (produces beliefs that don't survive review) and review over-retracts (flags beliefs that could be recovered). Measured: 13-38% retraction rate across 6 infrastructure domains (939 derivations). Working through candidate retractions reveals insights — smuggled premises are usually recoverable (44-59% search-and-link recovery rate).","truth_value":"IN","justification_count":0,"dependent_count":2,"challenges":[],"last_reviewed":null,"review_result":null,"source_type":""},{"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":2,"dependent_count":0,"challenges":[],"last_reviewed":"2026-05-30T07:02:40","review_result":"pass","source_type":""},{"id":"dual-path-design-evidence","text":"Dual-path retrieval (TMS path for pre-computed beliefs + FTS path for source chunk search, merged by a third pass) achieves 98.5% A/B across 3,853 questions. Opus drops from 95.5% to 86% when mixing beliefs and document chunks in a single prompt; three focused passes achieve 100%.","truth_value":"IN","justification_count":0,"dependent_count":1,"challenges":[],"last_reviewed":null,"review_result":null,"source_type":""},{"id":"eem-cli-interface","text":"The reasons CLI provides: reasons init (create database), reasons add (add beliefs with --sl for justifications, --source for provenance), reasons retract (mark OUT with cascade), reasons assert (mark IN with restoration), reasons search (semantic search), reasons show (full details), reasons explain (justification trace), reasons derive (generate new beliefs), reasons review-beliefs (audit), reasons challenge/defend (dialectical argumentation), reasons check-stale (source change detection), reasons nogood (record contradictions), reasons export-markdown (beliefs.md output), reasons compact (token-budgeted summary).","truth_value":"IN","justification_count":0,"dependent_count":4,"challenges":[],"last_reviewed":null,"review_result":null,"source_type":""},{"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":6,"challenges":[],"last_reviewed":null,"review_result":null,"source_type":""},{"id":"eem-vs-knowledge-graphs","text":"Knowledge graphs store entities and relationships (what exists). EEM stores justified beliefs (what is believed and why). Knowledge graphs have no retraction cascades, no derivation depth, no contradiction tracking. When a fact is wrong, the graph doesn't know what else depends on it. EEM does. Every ontology is an implicit epistemology — it treats beliefs as facts, which works until they're wrong.","truth_value":"IN","justification_count":1,"dependent_count":0,"challenges":[],"last_reviewed":"2026-05-30T07:02:40","review_result":"pass","source_type":""},{"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,"source_type":""},{"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,"source_type":""},{"id":"evidence-exists-but-not-linked","text":"The eval harnesses, question sets, JSON result files, Langfuse traces, and methodology writeups all exist in project repos (beliefs-pi, expert-service, claude_code_langgraph). They are not public or linked from llmeem.ai. The credibility gap is a presentation problem, not a substance problem.","truth_value":"IN","justification_count":0,"dependent_count":1,"challenges":[],"last_reviewed":null,"review_result":null,"source_type":""},{"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,"source_type":""}],"count":60,"limit":20,"offset":0}