Evidence Directory
Type: kb/types/generated-index.md
← Parent
- A five-link cap missed four grounding findings in twelve reviews (note) - A paired Commonplace assay found five capped-versus-uncapped grounding outcome divergences; one reproduced as reviewer noise, while four appeared only after fuller reading reached 6–16 linked artifacts
- A quotes-route rollout grounded more claim uses without earning claim identifiers (note) - A Commonplace grounding rollout recorded 30% grounded claim uses under a paraphrased claims ledger and 75% under verbatim quotes or pinned snapshots, with no case needing claim identifiers; the non-random cohorts make the gap descriptive
- A vibe-noting trace shows persistence enables revision, not certification (note) - Evidence from one Commonplace note history: persistence enabled later semantic development while review exposed omitted risks, attribution drift, a link error, and an unresolved authority boundary
- An independent pass tightened three of four Pirolli grounding verdicts (note) - A Commonplace grounding case changed three of four support verdicts after separating source reconstruction from target-claim judgment, making bilateral isolation a candidate control rather than a proven cause.
- Commonplace as a reflective self-improving system (note) - Commonplace witnesses that a human-inclusive KB can be reflectively self-improving on one pathway despite uneven coverage and human-gated design judgment
- In one episode, recognition appeared only in the corpus-loaded run (note) - One 2026-09-01 episode: a repository-free synthesis re-derived retained notes and reproposed rejected framings while the corpus-loaded session recognized them; an uncontrolled bundle, recorded as a starting point for better contrasts
- Real self-improving systems occupy combinations no single rung captures (note) - Casebook of thirteen placements on selected pathway-profile fields — Homeostat to Commonplace — reflection, cumulativity, allocation, and evidential limit in combinations no rung expresses
- Seven documentation cases left routing and synthesis (note) - A seven-artifact Commonplace sweep found that direct source access removed exact-fact prose while discovery maps and cross-component boundaries survived; it does not establish a universal documentation ratio
- Single-artifact review bundles still cut Claude costs substantially after cache-aware weighting (note) - April 2-4, 2026 review telemetry reweighted with Anthropic Opus 4.6 prompt-caching prices still shows a substantial cost drop from the single-artifact bundle refactor
- Six Commonplace paths establish broad addressability, not completeness (note) - A six-path Commonplace audit establishes broad path-relative addressability without establishing completeness, while exposing separate admission and model-realization gaps in the broader revision affordance
- Six reported self-improvement paths expose bounded redesign surfaces within supplied methods (note) - Comparative evidence separates operative redesign, revision of governing machinery, and contributions to later improvement from declared editability across six reported self-improvement paths including HyperAgents
- The 2026-08-30 Commonplace revision used retained theory to guide computational search (note) - A 2026-08-30 Commonplace revision shows retained project theory guiding computational search while the operator supplied decisive global-fit selection
- The tag-readme change as an observed causal-connection trace (note) - One bounded Commonplace trace establishes that operative self-representation can exert causal force in both directions; it does not establish system-wide reflective coverage
- Three 2026 harnesses retain editable rules or weights, not rationale (note) - Prime Agent and Recuris retain editable rules about their own operation with no reported rationale, and Apodex retains weights; missing rationale neither excludes theory refinement nor establishes its transfer limits
- Three simplification passes exposed different clarity–precision tradeoffs (note) - Evidence from three independent rewrites of one mature article: broad style guidance ranked best overall, a compact style cue improved rhythm but drifted, and exhaustive local review barely changed the text
- Two rewrites exposed a syntax-or-repetition tradeoff (note) - Evidence from two ASD-STE100-inspired passes over one note: unguarded sentence splitting lost semantic relations, while guarded splitting preserved them by adding 4.9% more words