Rendered from docs/probe-results/additive-tuning-of-2026-10-31-base-re-measure-of-scenario-1.md in the Headwater corpus. Every document on this half of the site is typed by the taxonomy the descriptor names: corpus.json.

The result of docs/probe-runs/additive-tuning-of-2026-10-31-base-re-measure-of-scenario-1.md

A probe result is a function of committed inputs and of nothing else: the transcript at docs/probe-runs/additive-tuning-of-2026-10-31-base-re-measure-of-scenario-1.md and the state it stands at, the expectations the probes it names declare, the version of the grader that evaluated them, and for a compared arm the result of the other arm. Fetch those and this file comes back.

The run this transcript recorded

A additive run in the scenario-1 arm, on claude-sonnet-5 at 2026-10-30. served version claude-sonnet-5, tree sha256:36a7e05ad1a4a0739c034dad6f86210036d049b480f0a90933d02225162e841d, selection sha256:d99530b2b639bb6bdd279be2a9356a64ce2a0c8cceca354d56957f198a76a20a, read set sha256:2a47d5b0401ca6d3239d352781fe101f4d7ba74c60c6a0dbe460e46ae9703c4d, seed 0, harness 0.6.1. realized cost $119.07, which the adaptive layer reads as the cost of its own instrument.

154 events over 22 probes, in 154 sessions and 4339 tool calls.

The engine confirmed the taxonomy, that every member of the run identity is present, the membership of every probe named, that no key outside the closed set appears, and that a realized cost was recorded. Present is not confirmed. This page names the lock, the selection and the read set the transcript recorded, and it compares none of them with the tree in front of a reader. headwater generate and headwater probe stale name what moved since the recording, and neither one fails for it. It graded nothing: a verdict is a function of this transcript, the expectations these probes declare and a grader version, and headwater probe grade is the verb that holds all three.

The selection this transcript names is sha256:d99530b2b639bb6bdd279be2a9356a64ce2a0c8cceca354d56957f198a76a20a, and the probes graded below are the probes it was planned over, as this corpus declares them now. A probe added to this corpus after the recording is not a session this run owed. The tree, the seed and the harness above are provenance and nothing compares them.

The read_set digest above covers every probe of the selection and every document one of them examines, by path and content. This file names it as provenance and compares it with nothing, and the same holds for the lock and the selection: an edit to a document, a new probe or a moved lock leaves these bytes alone. headwater generate names each result whose recorded lock, read set or selection moved, and headwater probe stale takes the digest and reports which recorded results a change voided. Neither one fails for it.

Graded by grader 0.5.1. A additive run in the scenario-1 arm, on claude-sonnet-5 at served version claude-sonnet-5.

The verdicts

  • HW-PROBE-a-session-adds-a-british-spelling-to-the-language-rule-and-declines-the-paragraph-limit-a-current-decision-retired (sufficiency, expects patched) session L1-additive-scenario-1-p1-r1: not satisfied — command:r2-paragraph-limit reported over each of the 3 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p1-r2: not satisfied — the session produced no artifact, so the oracle had nothing to read; no call to a tool of an MCP server session L1-additive-scenario-1-p1-r3: not satisfied — command:r2-paragraph-limit reported over each of the 4 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p1-r4: not satisfied — command:r2-paragraph-limit reported over each of the 2 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p1-r5: satisfied — event 5: command:r2-paragraph-limit reported nothing over engine/crates/check/src/language.rs; no call to a tool of an MCP server session L1-additive-scenario-1-p1-r6: not satisfied — command:r2-paragraph-limit reported over each of the 2 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p1-r7: no verdict — /tmp/count_sentences.py carries no findings key, so nothing says whether the oracle was ever run over it. findings: [] is checked and clean; no call to a tool of an MCP server
  • HW-PROBE-a-session-adds-a-count-of-findings-by-severity-to-the-json-report-of-the-check (sufficiency, expects patched) session L1-additive-scenario-1-p2-r1: satisfied — event 78: command:r2-check-counts reported nothing over docs/interfaces/headwater-check.md; no call to a tool of an MCP server session L1-additive-scenario-1-p2-r2: satisfied — event 79: command:r2-check-counts reported nothing over docs/interfaces/headwater-check.md; no call to a tool of an MCP server session L1-additive-scenario-1-p2-r3: satisfied — event 80: command:r2-check-counts reported nothing over docs/interfaces/headwater-check.md; no call to a tool of an MCP server session L1-additive-scenario-1-p2-r4: satisfied — event 81: command:r2-check-counts reported nothing over docs/interfaces/headwater-check.md; no call to a tool of an MCP server session L1-additive-scenario-1-p2-r5: satisfied — event 82: command:r2-check-counts reported nothing over docs/interfaces/headwater-check.md; no call to a tool of an MCP server session L1-additive-scenario-1-p2-r6: satisfied — event 83: command:r2-check-counts reported nothing over docs/interfaces/headwater-check.md; no call to a tool of an MCP server session L1-additive-scenario-1-p2-r7: satisfied — event 84: command:r2-check-counts reported nothing over docs/interfaces/headwater-check.md; no call to a tool of an MCP server
  • HW-PROBE-a-session-adds-a-retired-term-to-the-overlay-that-the-task-names-and-leaves-the-lock-matching-it (sufficiency, expects patched) session L1-additive-scenario-1-p3-r1: not satisfied — the session produced no artifact, so the oracle had nothing to read; no call to a tool of an MCP server session L1-additive-scenario-1-p3-r2: not satisfied — the session produced no artifact, so the oracle had nothing to read; no call to a tool of an MCP server session L1-additive-scenario-1-p3-r3: not satisfied — the session produced no artifact, so the oracle had nothing to read; no call to a tool of an MCP server session L1-additive-scenario-1-p3-r4: not satisfied — the session produced no artifact, so the oracle had nothing to read; no call to a tool of an MCP server session L1-additive-scenario-1-p3-r5: not satisfied — the session produced no artifact, so the oracle had nothing to read; no call to a tool of an MCP server session L1-additive-scenario-1-p3-r6: not satisfied — the session produced no artifact, so the oracle had nothing to read; no call to a tool of an MCP server session L1-additive-scenario-1-p3-r7: not satisfied — the session produced no artifact, so the oracle had nothing to read; no call to a tool of an MCP server
  • HW-PROBE-a-session-lets-the-disk-free-script-take-its-floor-in-the-equals-form (sufficiency, expects patched) session L1-additive-scenario-1-p4-r1: satisfied — event 113: command:r11-disk-free reported nothing over tools/run/disk-free-fixtures.sh; no call to a tool of an MCP server session L1-additive-scenario-1-p4-r2: satisfied — event 114: command:r11-disk-free reported nothing over tools/run/disk-free.sh; no call to a tool of an MCP server session L1-additive-scenario-1-p4-r3: satisfied — event 115: command:r11-disk-free reported nothing over tools/run/disk-free.sh; no call to a tool of an MCP server session L1-additive-scenario-1-p4-r4: satisfied — event 116: command:r11-disk-free reported nothing over tools/run/disk-free.sh; no call to a tool of an MCP server session L1-additive-scenario-1-p4-r5: satisfied — event 117: command:r11-disk-free reported nothing over tools/run/disk-free-fixtures.sh; no call to a tool of an MCP server session L1-additive-scenario-1-p4-r6: satisfied — event 118: command:r11-disk-free reported nothing over tools/run/disk-free-fixtures.sh; no call to a tool of an MCP server session L1-additive-scenario-1-p4-r7: satisfied — event 119: command:r11-disk-free reported nothing over tools/run/disk-free-fixtures.sh; no call to a tool of an MCP server
  • HW-PROBE-a-session-links-the-obligation-on-published-read-sets-to-the-evaluation-whose-measurement-discharged-it (sufficiency, expects patched) session L1-additive-scenario-1-p5-r1: not satisfied — command:r5-read-set reported over each of the 1 produced artifact; no call to a tool of an MCP server session L1-additive-scenario-1-p5-r2: satisfied — event 121: command:r5-read-set reported nothing over docs/evaluations/what-a-check-can-know.md; no call to a tool of an MCP server session L1-additive-scenario-1-p5-r3: satisfied — event 122: command:r5-read-set reported nothing over docs/evaluations/what-a-check-can-know.md; no call to a tool of an MCP server session L1-additive-scenario-1-p5-r4: not satisfied — command:r5-read-set reported over each of the 1 produced artifact; no call to a tool of an MCP server session L1-additive-scenario-1-p5-r5: satisfied — event 124: command:r5-read-set reported nothing over docs/evaluations/what-a-check-can-know.md; no call to a tool of an MCP server session L1-additive-scenario-1-p5-r6: satisfied — event 125: command:r5-read-set reported nothing over docs/evaluations/what-a-check-can-know.md; no call to a tool of an MCP server session L1-additive-scenario-1-p5-r7: not satisfied — command:r5-read-set reported over each of the 1 produced artifact; no call to a tool of an MCP server
  • HW-PROBE-a-session-makes-the-footer-check-of-the-site-refuse-the-stock-theme-credit-as-well (sufficiency, expects patched) session L1-additive-scenario-1-p6-r1: satisfied — event 127: command:r11-site-footer reported nothing over tools/site/check-site-footer.sh; no call to a tool of an MCP server session L1-additive-scenario-1-p6-r2: satisfied — event 128: command:r11-site-footer reported nothing over tools/site/check-site-footer.sh; no call to a tool of an MCP server session L1-additive-scenario-1-p6-r3: satisfied — event 129: command:r11-site-footer reported nothing over tools/site/check-site-footer.sh; no call to a tool of an MCP server session L1-additive-scenario-1-p6-r4: satisfied — event 130: command:r11-site-footer reported nothing over tools/site/check-site-footer.sh; no call to a tool of an MCP server session L1-additive-scenario-1-p6-r5: satisfied — event 131: command:r11-site-footer reported nothing over tools/site/check-site-footer.sh; no call to a tool of an MCP server session L1-additive-scenario-1-p6-r6: satisfied — event 132: command:r11-site-footer reported nothing over tools/site/check-site-footer.sh; no call to a tool of an MCP server session L1-additive-scenario-1-p6-r7: satisfied — event 133: command:r11-site-footer reported nothing over tools/site/check-site-footer.sh; no call to a tool of an MCP server
  • HW-PROBE-a-session-moves-an-obligation-record-to-the-process-shelf-and-repairs-the-links-inside-it-as-well-as-the-links-to-it (sufficiency, expects patched) session L1-additive-scenario-1-p7-r1: not satisfied — command:r7-small-gaps reported over each of the 4 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p7-r2: not satisfied — command:r7-small-gaps reported over each of the 5 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p7-r3: not satisfied — command:r7-small-gaps reported over each of the 4 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p7-r4: not satisfied — command:r7-small-gaps reported over each of the 4 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p7-r5: not satisfied — command:r7-small-gaps reported over each of the 4 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p7-r6: not satisfied — command:r7-small-gaps reported over each of the 4 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p7-r7: not satisfied — command:r7-small-gaps reported over each of the 4 produced artifacts; no call to a tool of an MCP server
  • HW-PROBE-a-session-moves-the-guide-to-the-merge-driver-for-derived-files-to-the-adopter-shelf-under-the-identifier-that-shelf-mints (sufficiency, expects patched) session L1-additive-scenario-1-p8-r1: not satisfied — command:r7-merge-driver reported over each of the 5 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p8-r2: not satisfied — command:r7-merge-driver reported over each of the 7 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p8-r3: not satisfied — command:r7-merge-driver reported over each of the 5 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p8-r4: not satisfied — command:r7-merge-driver reported over each of the 5 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p8-r5: not satisfied — command:r7-merge-driver reported over each of the 5 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p8-r6: not satisfied — command:r7-merge-driver reported over each of the 4 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p8-r7: not satisfied — command:r7-merge-driver reported over each of the 5 produced artifacts; no call to a tool of an MCP server
  • HW-PROBE-a-session-records-a-ruling-that-drops-the-help-screen-banner-as-the-settled-successor-of-the-record-the-task-names (sufficiency, expects patched) session L1-additive-scenario-1-p9-r1: not satisfied — command:r6-banner reported over each of the 2 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p9-r2: not satisfied — command:r6-banner reported over each of the 4 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p9-r3: not satisfied — command:r6-banner reported over each of the 2 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p9-r4: not satisfied — command:r6-banner reported over each of the 30 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p9-r5: not satisfied — command:r6-banner reported over each of the 2 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p9-r6: not satisfied — command:r6-banner reported over each of the 33 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p9-r7: not satisfied — command:r6-banner reported over each of the 2 produced artifacts; no call to a tool of an MCP server
  • HW-PROBE-a-session-records-as-owed-that-no-ruling-says-whether-a-hook-s-text-on-a-prompt-is-a-warning (sufficiency, expects patched) session L1-additive-scenario-1-p10-r1: not satisfied — command:r4-hook-warning reported over each of the 3 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p10-r2: not satisfied — command:r4-hook-warning reported over each of the 1 produced artifact; no call to a tool of an MCP server session L1-additive-scenario-1-p10-r3: not satisfied — command:r4-hook-warning reported over each of the 1 produced artifact; no call to a tool of an MCP server session L1-additive-scenario-1-p10-r4: not satisfied — command:r4-hook-warning reported over each of the 2 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p10-r5: not satisfied — command:r4-hook-warning reported over each of the 2 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p10-r6: not satisfied — command:r4-hook-warning reported over each of the 1 produced artifact; no call to a tool of an MCP server session L1-additive-scenario-1-p10-r7: not satisfied — command:r4-hook-warning reported over each of the 1 produced artifact; no call to a tool of an MCP server
  • HW-PROBE-a-session-records-as-owed-the-corpus-size-axis-that-the-additive-campaign-defers (sufficiency, expects patched) session L1-additive-scenario-1-p11-r1: not satisfied — command:r4-corpus-size reported over each of the 2 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p11-r2: not satisfied — command:r4-corpus-size reported over each of the 1 produced artifact; no call to a tool of an MCP server session L1-additive-scenario-1-p11-r3: not satisfied — the session produced no artifact, so the oracle had nothing to read; no call to a tool of an MCP server session L1-additive-scenario-1-p11-r4: not satisfied — command:r4-corpus-size reported over each of the 1 produced artifact; no call to a tool of an MCP server session L1-additive-scenario-1-p11-r5: not satisfied — command:r4-corpus-size reported over each of the 2 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p11-r6: not satisfied — the session produced no artifact, so the oracle had nothing to read; no call to a tool of an MCP server session L1-additive-scenario-1-p11-r7: not satisfied — command:r4-corpus-size reported over each of the 2 produced artifacts; no call to a tool of an MCP server
  • HW-PROBE-a-session-records-the-owl-worked-example-as-evidence-of-the-check-layer-part-that-the-task-names (sufficiency, expects patched) session L1-additive-scenario-1-p12-r1: satisfied — event 22: command:r5-check-layer-owl reported nothing over docs/evaluations/owl-skos-worked-example.md; no call to a tool of an MCP server session L1-additive-scenario-1-p12-r2: satisfied — event 23: command:r5-check-layer-owl reported nothing over docs/evaluations/owl-skos-worked-example.md; no call to a tool of an MCP server session L1-additive-scenario-1-p12-r3: satisfied — event 24: command:r5-check-layer-owl reported nothing over docs/evaluations/owl-skos-worked-example.md; no call to a tool of an MCP server session L1-additive-scenario-1-p12-r4: satisfied — event 25: command:r5-check-layer-owl reported nothing over docs/evaluations/owl-skos-worked-example.md; no call to a tool of an MCP server session L1-additive-scenario-1-p12-r5: satisfied — event 26: command:r5-check-layer-owl reported nothing over docs/evaluations/owl-skos-worked-example.md; no call to a tool of an MCP server session L1-additive-scenario-1-p12-r6: satisfied — event 27: command:r5-check-layer-owl reported nothing over docs/evaluations/owl-skos-worked-example.md; no call to a tool of an MCP server session L1-additive-scenario-1-p12-r7: satisfied — event 28: command:r5-check-layer-owl reported nothing over docs/evaluations/owl-skos-worked-example.md; no call to a tool of an MCP server
  • HW-PROBE-a-session-renames-the-module-of-the-language-rule-and-moves-the-records-that-govern-it (sufficiency, expects patched) session L1-additive-scenario-1-p13-r1: not satisfied — command:r3-language-module reported over each of the 14 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p13-r2: not satisfied — command:r3-language-module reported over each of the 11 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p13-r3: not satisfied — command:r3-language-module reported over each of the 14 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p13-r4: not satisfied — command:r3-language-module reported over each of the 10 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p13-r5: not satisfied — command:r3-language-module reported over each of the 11 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p13-r6: not satisfied — command:r3-language-module reported over each of the 11 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p13-r7: not satisfied — command:r3-language-module reported over each of the 11 produced artifacts; no call to a tool of an MCP server
  • HW-PROBE-a-session-renames-the-pattern-module-of-the-meta-crate-and-its-callers (sufficiency, expects patched) session L1-additive-scenario-1-p14-r1: not satisfied — command:r3-pattern-module reported over each of the 18 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p14-r2: not satisfied — command:r3-pattern-module reported over each of the 17 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p14-r3: not satisfied — command:r3-pattern-module reported over each of the 12 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p14-r4: not satisfied — command:r3-pattern-module reported over each of the 17 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p14-r5: not satisfied — command:r3-pattern-module reported over each of the 11 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p14-r6: not satisfied — command:r3-pattern-module reported over each of the 15 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p14-r7: not satisfied — command:r3-pattern-module reported over each of the 19 produced artifacts; no call to a tool of an MCP server
  • HW-PROBE-a-session-repairs-a-suspect-governs-edge-on-the-record-that-the-task-names-and-raises-no-other-finding (sufficiency, expects patched) session L1-additive-scenario-1-p15-r1: not satisfied — command:r9-gitattributes reported over each of the 1 produced artifact; no call to a tool of an MCP server session L1-additive-scenario-1-p15-r2: not satisfied — command:r9-gitattributes reported over each of the 1 produced artifact; no call to a tool of an MCP server session L1-additive-scenario-1-p15-r3: not satisfied — command:r9-gitattributes reported over each of the 1 produced artifact; no call to a tool of an MCP server session L1-additive-scenario-1-p15-r4: not satisfied — command:r9-gitattributes reported over each of the 1 produced artifact; no call to a tool of an MCP server session L1-additive-scenario-1-p15-r5: not satisfied — command:r9-gitattributes reported over each of the 1 produced artifact; no call to a tool of an MCP server session L1-additive-scenario-1-p15-r6: not satisfied — command:r9-gitattributes reported over each of the 1 produced artifact; no call to a tool of an MCP server session L1-additive-scenario-1-p15-r7: not satisfied — command:r9-gitattributes reported over each of the 1 produced artifact; no call to a tool of an MCP server
  • HW-PROBE-a-session-retires-a-stock-phrase-in-the-list-that-the-check-reads-and-resolves-the-lock (sufficiency, expects patched) session L1-additive-scenario-1-p16-r1: not satisfied — the session produced no artifact, so the oracle had nothing to read; no call to a tool of an MCP server session L1-additive-scenario-1-p16-r2: not satisfied — command:r8-game-changer reported over each of the 2 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p16-r3: not satisfied — the session produced no artifact, so the oracle had nothing to read; no call to a tool of an MCP server session L1-additive-scenario-1-p16-r4: not satisfied — command:r8-game-changer reported over each of the 1 produced artifact; no call to a tool of an MCP server session L1-additive-scenario-1-p16-r5: not satisfied — command:r8-game-changer reported over each of the 1 produced artifact; no call to a tool of an MCP server session L1-additive-scenario-1-p16-r6: not satisfied — the session produced no artifact, so the oracle had nothing to read; no call to a tool of an MCP server session L1-additive-scenario-1-p16-r7: not satisfied — the session produced no artifact, so the oracle had nothing to read; no call to a tool of an MCP server
  • HW-PROBE-a-session-rewrites-the-change-narration-in-the-summary-of-the-obligation-on-the-site-review-marker-and-raises-no-other-finding (sufficiency, expects patched) session L1-additive-scenario-1-p17-r1: not satisfied — command:r9-review-marker reported over each of the 1 produced artifact; no call to a tool of an MCP server session L1-additive-scenario-1-p17-r2: not satisfied — the session produced no artifact, so the oracle had nothing to read; no call to a tool of an MCP server session L1-additive-scenario-1-p17-r3: satisfied — event 59: command:r9-review-marker reported nothing over docs/process/obligations/0217-the-site-review-marker-lives-in-the-common-directory-of-a-clone-so-one-worktree-s-unreviewed-merge-blocks-the-push-of-every-worktree.md; no call to a tool of an MCP server session L1-additive-scenario-1-p17-r4: not satisfied — the session produced no artifact, so the oracle had nothing to read; no call to a tool of an MCP server session L1-additive-scenario-1-p17-r5: not satisfied — command:r9-review-marker reported over each of the 2 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p17-r6: not satisfied — the session produced no artifact, so the oracle had nothing to read; no call to a tool of an MCP server session L1-additive-scenario-1-p17-r7: not satisfied — command:r9-review-marker reported over each of the 1 produced artifact; no call to a tool of an MCP server
  • HW-PROBE-a-session-says-whether-a-front-page-recording-may-show-a-number-a-live-run-does-not-produce-when-the-task-names-the-record-that-was-superseded (sufficiency, expects answered) session L1-additive-scenario-1-p18-r1: satisfied — event 64: answered marked; no call to a tool of an MCP server session L1-additive-scenario-1-p18-r2: satisfied — event 65: answered marked; no call to a tool of an MCP server session L1-additive-scenario-1-p18-r3: satisfied — event 66: answered marked; no call to a tool of an MCP server session L1-additive-scenario-1-p18-r4: satisfied — event 67: answered marked; no call to a tool of an MCP server session L1-additive-scenario-1-p18-r5: satisfied — event 68: answered marked; no call to a tool of an MCP server session L1-additive-scenario-1-p18-r6: satisfied — event 69: answered marked; no call to a tool of an MCP server session L1-additive-scenario-1-p18-r7: satisfied — event 70: answered marked; no call to a tool of an MCP server
  • HW-PROBE-a-session-supersedes-the-standing-ruling-on-a-paragraph-limit-when-the-task-describes-the-ruling-that-it-replaced (navigability, expects patched) session L1-additive-scenario-1-p19-r1: not satisfied — the session produced no artifact, so the oracle had nothing to read; no call to a tool of an MCP server session L1-additive-scenario-1-p19-r2: not satisfied — the session produced no artifact, so the oracle had nothing to read; no call to a tool of an MCP server session L1-additive-scenario-1-p19-r3: not satisfied — the session produced no artifact, so the oracle had nothing to read; no call to a tool of an MCP server session L1-additive-scenario-1-p19-r4: not satisfied — command:r6-paragraph-limit reported over each of the 2 produced artifacts; no call to a tool of an MCP server session L1-additive-scenario-1-p19-r5: not satisfied — the session produced no artifact, so the oracle had nothing to read; no call to a tool of an MCP server session L1-additive-scenario-1-p19-r6: not satisfied — command:r6-paragraph-limit reported over each of the 1 produced artifact; no call to a tool of an MCP server session L1-additive-scenario-1-p19-r7: not satisfied — command:r6-paragraph-limit reported over each of the 2 produced artifacts; no call to a tool of an MCP server
  • HW-PROBE-a-session-tells-a-withheld-answer-from-an-absent-one-in-a-corpus-that-serves-no-tombstone (sufficiency, expects answered) session L1-additive-scenario-1-p20-r1: satisfied — event 85: answered absent; no call to a tool of an MCP server session L1-additive-scenario-1-p20-r2: satisfied — event 86: answered absent; no call to a tool of an MCP server session L1-additive-scenario-1-p20-r3: not satisfied — event 87 answered present, and the probe expects absent; no call to a tool of an MCP server session L1-additive-scenario-1-p20-r4: satisfied — event 88: answered absent; no call to a tool of an MCP server session L1-additive-scenario-1-p20-r5: satisfied — event 89: answered absent; no call to a tool of an MCP server session L1-additive-scenario-1-p20-r6: satisfied — event 90: answered absent; no call to a tool of an MCP server session L1-additive-scenario-1-p20-r7: satisfied — event 91: answered absent; no call to a tool of an MCP server
  • HW-PROBE-a-session-that-reviews-a-change-shipping-the-vendored-package-as-the-taxonomy-release-cites-the-record-that-forbids-it (sufficiency, expects answered) session L1-additive-scenario-1-p21-r1: satisfied — event 92: answered HW-DR-0089; no call to a tool of an MCP server session L1-additive-scenario-1-p21-r2: not satisfied — the session ended with no answer; no call to a tool of an MCP server session L1-additive-scenario-1-p21-r3: satisfied — event 94: answered HW-DR-0089; no call to a tool of an MCP server session L1-additive-scenario-1-p21-r4: satisfied — event 95: answered HW-DR-0089; no call to a tool of an MCP server session L1-additive-scenario-1-p21-r5: satisfied — event 96: answered HW-DR-0089; no call to a tool of an MCP server session L1-additive-scenario-1-p21-r6: not satisfied — the session ended with no answer; no call to a tool of an MCP server session L1-additive-scenario-1-p21-r7: satisfied — event 98: answered HW-DR-0089; no call to a tool of an MCP server
  • HW-PROBE-a-session-that-reviews-an-agent-s-acceptance-stamp-cites-the-ruling-in-force-and-not-the-draft-that-the-pull-request-names (sufficiency, expects answered) session L1-additive-scenario-1-p22-r1: not satisfied — the session ended with no answer; no call to a tool of an MCP server session L1-additive-scenario-1-p22-r2: satisfied — event 100: answered HW-DR-0034; no call to a tool of an MCP server session L1-additive-scenario-1-p22-r3: satisfied — event 101: answered HW-DR-0034; no call to a tool of an MCP server session L1-additive-scenario-1-p22-r4: satisfied — event 102: answered HW-DR-0034; no call to a tool of an MCP server session L1-additive-scenario-1-p22-r5: satisfied — event 103: answered HW-DR-0034; no call to a tool of an MCP server session L1-additive-scenario-1-p22-r6: satisfied — event 104: answered HW-DR-0034; no call to a tool of an MCP server session L1-additive-scenario-1-p22-r7: satisfied — event 105: answered HW-DR-0034; no call to a tool of an MCP server

154 of 154 sessions that recorded their calls made no call to a tool of an MCP server. 0 sessions recorded no calls.

The rate, and the denominator it is over

58 of 153 graded sessions satisfied their expectation: 37.9%, in a 95% interval of 30.6% to 45.8%. The denominator is the graded sessions and never the selected probes. 1 session reached no verdict, and a session with no verdict is outside both halves of that fraction.

An interval that overlaps the previous run's is variance and one that does not is drift. This is one arm, so it estimates no effect: an efficacy claim is a comparison of two results, and the arm each one recorded is on it.