N17Q kept sources, receipts, decisions, artifacts, and unresolved effects outside the shrinking model context, then recompiled only evidence handles and bounded projections needed for the next decision.
#provenance
N17Q stopped asking a second model for an unsupported verdict and built compact evidence packages, citation checks, calibrated uncertainty, and human-readable disagreement into qualitative evaluation.
N17Q pinned server identity, tool schemas, descriptions, mappings, and the exact offered subset so replay and approval referred to the capabilities a run actually saw.
V0M3 connected source revisions, claims, proposal operations, accepted spans, human edits, and review decisions after ordinary citations stopped explaining the writing process.
V0M3 began when a useful generated paragraph lost its sources, task, prompt, and review state the moment I pasted it into a document.
K81R stored immutable question, evidence, model, prompt, claims, and verification revisions so refreshed knowledge produced a new answer instead of rewriting history.
K81R named the corpus, parser, passages, lexical analyzer, embedding model, and ranking policy behind every result and answer.
K81R stopped rewarding answers merely for linking sources and began checking whether each cited passage actually entitled the adjacent claim.
K81R made selected passages a visible, editable, versioned artifact rather than an invisible context window assembled just before generation.