Result To Claim

# Policy B = warn-and-skip: nothing here may abort the audit. cd is non-fatal, the
# helper run is explicitly non-blocking, no pipefail-fragile pipe.
cd "$(git rev-parse --show-toplevel 2>/dev/null || pwd)" 2>/dev/null || true
if [ -z "${ARIS_REPO:-}" ] && [ -f .aris/installed-skills.txt ]; then
    ARIS_REPO=$(awk -F'\t' '$1=="repo_root"{print $2; exit}' .aris/installed-skills.txt 2>/dev/null) || true
fi
if [ -z "${ARIS_REPO:-}" ] && [ -f "$HOME/.aris/repo" ]; then
    ARIS_REPO=$(cat "$HOME/.aris/repo" 2>/dev/null) || true
fi
EVIDENCE_CHECK=".aris/tools/evidence_check.py"
[ -f "$EVIDENCE_CHECK" ] || EVIDENCE_CHECK="tools/evidence_check.py"
[ -f "$EVIDENCE_CHECK" ] || { [ -n "${ARIS_REPO:-}" ] && EVIDENCE_CHECK="$ARIS_REPO/tools/evidence_check.py"; }
[ -f "$EVIDENCE_CHECK" ] || EVIDENCE_CHECK=""

mkdir -p .aris
if [ -n "$EVIDENCE_CHECK" ]; then
    # NB: evidence_check exits 1 when it FINDS hallucinated evidence (value_not_found /
    # path_missing) — that is the useful signal, NOT a failure. So judge success by
    # whether valid JSON was produced, never by exit code. `|| true` keeps set -e calm.
    python3 "$EVIDENCE_CHECK" . --batch .aris/claims.json > .aris/evidence_precheck.json 2>.aris/evidence_precheck.err || true
    if [ -s .aris/evidence_precheck.json ] && python3 -c "import json,sys;json.load(open('.aris/evidence_precheck.json'))" 2>/dev/null; then
        cat .aris/evidence_precheck.json
    else
        echo "WARN: evidence_check produced no valid output (see .aris/evidence_precheck.err);" >&2
        echo "      pre-check skipped (Policy B); the Codex jury still runs." >&2
    fi
else
    echo "WARN: evidence_check.py not resolved at .aris/tools/, tools/, \$ARIS_REPO/tools/, or via ~/.aris/repo." >&2
    echo "      Pre-check skipped (Policy B); the Codex jury still runs. Fix: rerun" >&2
    echo "      bash tools/install_aris.sh, export ARIS_REPO, or copy the helper to tools/." >&2
fi

mcp__codex__codex:
  model: gpt-5.6-sol
  config: {"model_reasoning_effort": "ultra"}
  prompt: |
    RESULT-TO-CLAIM EVALUATION

    I need you to judge whether experimental results support the intended claim.

    Intended claim: [the claim these experiments test]

    Experiments run:
    [list experiments with method, dataset, metrics]

    Results:
    [paste key numbers, comparison deltas, significance]

    Evidence pre-check (deterministic, from Step 1.5):
    [per-claim: <id> → verified | value_not_found | path_missing.
     A value_not_found/path_missing means the cited number is NOT in its result
     file — treat that claim as having no evidence; do not defend it. `verified`
     means the number exists in the file — YOU still judge whether it supports
     the claim.]

    Baselines:
    [baseline numbers and sources — reproduced or from paper]

    Known caveats:
    [any confounding factors, limited datasets, missing comparisons]

    Please evaluate:
    1. claim_supported: yes | partial | no
    2. what_results_support: what the data actually shows
    3. what_results_dont_support: where the data falls short of the claim
    4. missing_evidence: specific evidence gaps
    5. suggested_claim_revision: if the claim should be strengthened, weakened, or reframed
    6. next_experiments_needed: specific experiments to fill gaps (if any)
    7. confidence: high | medium | low

    Be honest. Do not inflate claims beyond what the data supports.
    A single positive result on one dataset does not support a general claim.

- claim_supported: yes | partial | no
- what_results_support: "..."
- what_results_dont_support: "..."
- missing_evidence: "..."
- suggested_claim_revision: "..."
- next_experiments_needed: "..."
- confidence: high | medium | low

if EXPERIMENT_AUDIT.json exists:
    read integrity_status from file
    attach to verdict output:
        integrity_status: pass | warn | fail

    if integrity_status == "fail":
        append to verdict: "[INTEGRITY CONCERN] — audit found issues, see EXPERIMENT_AUDIT.md"
        downgrade confidence to "low" regardless of Codex judgment

    if integrity_status == "warn":
        append to verdict: "[INTEGRITY: WARN] — audit flagged potential issues"
else:
    integrity_status = "unavailable"
    verdict is labeled "provisional — no integrity audit run"
    (this does NOT block anything — pipeline continues normally)

cd "$(git rev-parse --show-toplevel 2>/dev/null || pwd)" || exit 1
ARIS_REPO="${ARIS_REPO:-$(awk -F'\t' '$1=="repo_root"{print $2; exit}' .aris/installed-skills.txt 2>/dev/null)}"
if [ -z "${ARIS_REPO:-}" ] && [ -f "$HOME/.aris/repo" ]; then
  ARIS_REPO=$(cat "$HOME/.aris/repo" 2>/dev/null) || true
fi
WIKI_SCRIPT=".aris/tools/research_wiki.py"
[ -f "$WIKI_SCRIPT" ] || WIKI_SCRIPT="tools/research_wiki.py"
[ -f "$WIKI_SCRIPT" ] || { [ -n "${ARIS_REPO:-}" ] && WIKI_SCRIPT="$ARIS_REPO/tools/research_wiki.py"; }
[ -f "$WIKI_SCRIPT" ] || {
  echo "WARN: research_wiki.py not found; verdict will be reported but wiki edges/query-pack/log will be skipped. Fix: bash tools/install_aris.sh or smart_update.sh (refreshes ~/.aris/repo), export ARIS_REPO, or cp <ARIS-repo>/tools/research_wiki.py tools/." >&2
  WIKI_SCRIPT=""
}

if research-wiki/ exists:
    # 1. Create/refresh the experiment node FIRST (verdict OWNER → --update-on-exist so
    #    a re-judge overwrites the stale verdict). The supports/invalidates edges in #2
    #    point FROM exp:<id>, and add_edge does NOT verify node existence — so GATE those
    #    edges on the experiment node having been born (EXP_NODE_OK), else they'd dangle
    #    (the exact bug this closes). On failure: warn, skip the wiki edges, still report.
    EXP_NODE_OK=0
    if [ -n "$WIKI_SCRIPT" ]; then
      if python3 "$WIKI_SCRIPT" add_experiment research-wiki/ \
           --slug "<exp_id>" --idea "idea:<active_idea>" \
           --verdict "<yes|partial|no>" --confidence "<high|medium|low>" \
           --date "<date>" --hardware "<hw>" --duration "<dur>" \
           --metrics "<key metrics>" --reasoning "<one-line why this verdict>" \
           --provenance "<EXPERIMENT_AUDIT.md / run dir>" --update-on-exist; then
        EXP_NODE_OK=1   # page written + idea--tested_by-->exp edge + index/query_pack rebuilt
      else
        echo "WARN: add_experiment failed for <exp_id>; skipping wiki edges (verdict still reported)." >&2
      fi
    fi

    # 2. Record empirical support as EDGES ONLY — and ONLY when the exp node was born
    #    ([ "$EXP_NODE_OK" = 1 ]), so no edge dangles off a missing node. Never edit the
    #    claim page's `status`: that is the PROOF axis (verified / refuted / unproven /
    #    sound-modulo-imports / drafted / retracted), owned by /proof-checker (the claim
    #    birth point) — "supported"/"invalidated" are NOT valid claim statuses. The claim
    #    target should ALREADY be born by /proof-checker; add_edge does not verify it.
    for each claim resolved by this verdict (only if [ "$EXP_NODE_OK" = 1 ]):
        if verdict == "yes":
            python3 "$WIKI_SCRIPT" add_edge research-wiki/ --from "exp:<id>" --to "claim:<cid>" --type supports --evidence "<metric>"
        elif verdict == "partial":
            python3 "$WIKI_SCRIPT" add_edge research-wiki/ --from "exp:<id>" --to "claim:<cid>" --type supports --evidence "partial: <metric>"
        else:
            python3 "$WIKI_SCRIPT" add_edge research-wiki/ --from "exp:<id>" --to "claim:<cid>" --type invalidates --evidence "<why>"

    # 3. Update idea outcome (raw markdown, helper-free)
    Update research-wiki/ideas/<idea_id>.md:
      - outcome: positive | mixed | negative
      - If negative: fill "Failure / Risk Notes" and "Lessons Learned"
      - If positive: fill "Actual Outcome" and "Reusable Components"

    # 4. Rebuild + log (only if $WIKI_SCRIPT resolved)
    [ -n "$WIKI_SCRIPT" ] && python3 "$WIKI_SCRIPT" rebuild_query_pack research-wiki/
    [ -n "$WIKI_SCRIPT" ] && python3 "$WIKI_SCRIPT" log research-wiki/ "result-to-claim: exp:<id> verdict=<verdict> for idea:<idea_id>"

    # 5. Re-ideation suggestion
    Count failed/partial ideas since last /idea-creator run.
    If >= 3: print "💡 3+ ideas tested since last ideation. Consider re-running /idea-creator — the wiki now knows what doesn't work."