iter ms.2: Qwen retroactive re-run + first CodeLlama-13b-Instruct run + DESIGN.md §Decision-6 addendum extended to two subjects

Two live IONOS harness invocations with the ms.1 fix in place:

  - Qwen/Qwen3-Coder-Next   → runs/2026-05-12-080864/  (RUN_STATUS=ok)
  - meta-llama/CodeLlama-13b-Instruct-hf
                            → runs/2026-05-12-9197fd/  (RUN_STATUS=ok;
                              2/8 JSON cells terminated as api_failure
                              on turn 1 zero-token — transient IONOS
                              terminal error, disclosed in addendum)

Per-cell results (reached/4, prompt tokens, completion tokens):

  Qwen      JSON     1/4   182,378   14,972
  Qwen      AILX     1/4   110,575    3,474
  CodeLlama JSON     0/4   116,015    2,711   [2 cells api_failure]
  CodeLlama AILX     2/4    93,017    2,234

Both subjects agree on direction: AILX cohort cheaper on prompt
tokens (Qwen 61%, CodeLlama 80% of JSON-cohort spend) and on
completion tokens (Qwen 23%, CodeLlama 82%); AILX reached-green
≥ JSON reached-green for each subject. Three of four
first-attempt-green cells across the two subjects are AILX.
Failure classes split symmetric to form: JSON cohorts fail at
typecheck, AILX cohorts at parse — each form's
front-of-pipeline check.

DESIGN.md §"Decision 6 / Empirical addendum (2026-05-12)"
replaced: 2-column single-subject view → 4-column two-subject
view, framing paragraph reports direction agreement and the
api_failure / Qwen-rerun-noise anomalies, scope paragraph
updated to 'two subjects, n=1 each, deterministic; not a
verdict — a universal claim would need ≥3 subjects with
statistical robustness'.

Roadmap P3 'Multi-subject expansion' entry removed; scoped
goal met for two subjects.

Milestone token spend: prompt 501,985 + completion 23,391
= 525,376.

bench/orchestrator-stats/2026-05-12-iter-ms.2.json

@@ -0,0 +1,29 @@
+{
+  "iter_id": "ms.2",
+  "date": "2026-05-12",
+  "mode": "standard",
+  "outcome": "DONE",
+  "tasks_total": 6,
+  "tasks_completed": 6,
+  "reloops_per_task": { "1": 0, "2": 0, "3": 0, "4": 0, "5": 0, "6": 0 },
+  "review_loops_spec": 0,
+  "review_loops_quality": 0,
+  "blocked_reason": null,
+  "anomalies": [
+    "CodeLlama JSON-cohort t2_length and t4_count_zeros terminated as api_failure on turn 1 with zero tokens (transient IONOS-side terminal error); not re-attempted per carrier no-exploratory-re-runs constraint.",
+    "Qwen re-run shifted one cell vs cma.3 baseline (AILX 2/4 -> 1/4, JSON 1/4 -> 1/4) at identical temperature=0; attributed to IONOS-side state-of-day noise on a single deterministic call, not the ms.1 feedback-formatting fix."
+  ],
+  "milestone_token_spend": {
+    "qwen_prompt": 292953,
+    "qwen_completion": 18446,
+    "codellama_prompt": 209032,
+    "codellama_completion": 4945,
+    "total_prompt": 501985,
+    "total_completion": 23391,
+    "grand_total": 525376
+  },
+  "run_dirs": {
+    "qwen": "experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/",
+    "codellama": "experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-9197fd/"
+  }
+}

docs/DESIGN.md

@@ -603,37 +603,59 @@ lowest-common-denominator fallback that always works.
 
 ### Empirical addendum (2026-05-12)
 
-Cross-model measurement against `Qwen/Qwen3-Coder-Next` (IONOS),
+Cross-model measurement against two foreign LLMs via IONOS,
 temperature=0, top_p=1, max-turns=5. Two blind cohorts on the same
 four MVP tasks (`t1_add_three`, `t2_length`, `t3_main_prints`,
-`t4_count_zeros`); each cohort sees only its own form's
+`t4_count_zeros`); each cohort sees only its own form's mini-spec.
-mini-spec. Run directory:
+Subjects (both runs use the pipeline-error-formatting fix from ms.1
-`experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-df7531/`.
+so JSON-cohort feedback carries the full anyhow cause chain):
 
-| metric | JSON cohort | AILX cohort |
+- `Qwen/Qwen3-Coder-Next` —
-|---|---|---|
+  `experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/`
-| reached green | 1/4 | 2/4 |
+- `meta-llama/CodeLlama-13b-Instruct-hf` —
-| first-attempt green | 0/4 | 1/4 |
+  `experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-9197fd/`
-| mean turns-to-green (green only) | 2.0 | 2.0 |
-| total prompt tokens | 191,768 | 95,417 |
-| total completion tokens | 15,376 | 2,587 |
-| top error class | check (×4) | parse (×3) |
 
-The AILX cohort reached green on more tasks at roughly half the
+| metric | Qwen / JSON | Qwen / AILX | CodeLlama / JSON | CodeLlama / AILX |
-prompt-token cost and one-sixth the completion-token cost. The
+|---|---|---|---|---|
-only first-attempt success in the entire run was AILX on
+| reached green | 1/4 | 1/4 | 0/4 | 2/4 |
-`t3_main_prints` (~5 lines of tagged s-expr; the JSON-cohort
+| first-attempt green | 1/4 | 1/4 | 0/4 | 2/4 |
-counterpart was ~23 lines of structured JSON and required a
+| mean turns-to-green (green only) | 1.0 | 1.0 | — | 1.0 |
-correction turn). JSON-cohort failures clustered in the
+| total prompt tokens | 182,378 | 110,575 | 116,015 | 93,017 |
-typecheck-stage; AILX-cohort failures clustered in the parse stage,
+| total completion tokens | 14,972 | 3,474 | 2,711 | 2,234 |
-which is the symmetric front-of-pipeline check for that form.
+| top error class | check (×3) | parse (×3) | check (×2) | parse (×2) |
 
-**Scope of this addendum:** single subject, single deterministic
+Both subjects show the same direction on every metric the table
-run. This is a data point, not a verdict. The universal claim of
+tracks. AILX is cheaper than JSON on prompt tokens (Qwen 61%,
-this Decision (".ailx is the AI authoring projection") remains
+CodeLlama 80% of the JSON cohort's spend) and cheaper on completion
-pending a multi-subject expansion — see the roadmap entry
+tokens (Qwen 23%, CodeLlama 82%). AILX reached-green is greater than
-"Multi-subject expansion (cross-model authoring-form follow-up)"
+or equal to JSON reached-green for each subject (Qwen ties at 1/4;
-for the next-step queue.
+CodeLlama strictly dominates, 2/4 vs 0/4). The failure-class
+symmetry observed on the original Qwen baseline holds for both
+subjects: JSON cohorts fail at the typecheck stage, AILX cohorts at
+the parse stage — each form's front-of-pipeline check. Three of the
+four first-attempt-green cells observed across the two subjects are
+AILX (Qwen-AILX t3, CodeLlama-AILX t1, CodeLlama-AILX t3); the
+fourth is Qwen-JSON t3, the same task the original baseline already
+flagged as the JSON-form's only first-attempt success. Two CodeLlama
+JSON-cohort cells (`t2_length`, `t4_count_zeros`) terminated as
+`api_failure` on turn 1 with zero tokens consumed — a transient
+IONOS-side terminal error, not a model-output failure; CodeLlama
+JSON-cohort numbers therefore average over 2 informative cells, not
+4. The Qwen re-run also shifted by one cell against the cma.3
+baseline (AILX 2/4 → 1/4, JSON 1/4 → 1/4) despite identical
+temperature=0 inputs; this is IONOS-side state-of-day noise on a
+single deterministic re-run, not an effect of the ms.1
+feedback-formatting fix (which only changes JSON-cohort prompt
+content).
+
+**Scope of this addendum:** two subjects, n=1 each, deterministic.
+This is a second data point pointing in the same direction as the
+first, not a verdict. The universal claim of this Decision (".ailx
+is the AI authoring projection") would need ≥3 subjects with
+statistical robustness to ratify; both current points point the
+same way (AILX cohort cheaper and at-least-as-green) but neither
+the sample size nor the cross-call noise observed in the Qwen
+re-run is enough to close out the Decision.
 
 ## Decision 8: explicit, verified tail calls
 

docs/journals/2026-05-12-iter-ms.2.md

@@ -0,0 +1,124 @@
+# iter ms.2 — Multi-subject run + DESIGN.md addendum extension
+
+**Date:** 2026-05-12
+**Started from:** 8689f7a2386e0d7993609c374d91984bc28d215c
+**Status:** DONE
+**Tasks completed:** 6 of 6
+
+## Summary
+
+Two live IONOS harness invocations executed with the ms.1 fix in
+place: a Qwen3-Coder-Next retroactive re-run
+(`runs/2026-05-12-080864/`, RUN_STATUS=ok) and a first-ever
+CodeLlama-13b-Instruct run (`runs/2026-05-12-9197fd/`, RUN_STATUS=ok
+at the run level; 2 of 8 cells terminated as api_failure on turn 1
+with zero tokens — transient IONOS-side terminal error, disclosed
+in the addendum and below). DESIGN.md §"Decision 6 / Empirical
+addendum (2026-05-12)" replaced with a four-column per-cell table
+plus a framing paragraph; roadmap P3 "Multi-subject expansion"
+entry removed.
+
+Both subjects point the same way on every measured axis: AILX
+cohort is cheaper than JSON cohort on prompt tokens (Qwen 61%,
+CodeLlama 80%) and on completion tokens (Qwen 23%, CodeLlama 82%),
+and AILX reached-green ≥ JSON reached-green for each subject (Qwen
+ties at 1/4; CodeLlama strictly dominates 2/4 vs 0/4). Three of the
+four first-attempt-green cells across the two subjects are AILX.
+Decision 6 is not ratified — n=1 per subject across two subjects is
+not statistical robustness — but the second data point points
+consistently. The roadmap entry was removed because the brainstorm
+spec was scoped to two subjects, not because the universal claim is
+closed; a future ratification iteration would re-open it.
+
+Anomaly disclosure: the Qwen re-run shifted by one cell vs the cma.3
+baseline (AILX 2/4 → 1/4, JSON 1/4 → 1/4) at identical
+temperature=0; this is IONOS-side state-of-day noise, not an effect
+of the ms.1 feedback fix, which only changes JSON-cohort prompt
+content. The two CodeLlama JSON api_failure cells (`t2_length`,
+`t4_count_zeros`) were not re-run — the carrier constraint forbids
+exploratory token spend, and the addendum discloses the partial
+sample directly.
+
+Roadmap P3 "Multi-subject expansion" entry removed in this iter.
+
+## Per-task notes
+
+- iter ms.2.1: Qwen retroactive re-run via harness — new run dir
+  `experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/`,
+  RUN_STATUS=ok, 8/8 cells populated. AIL_BIN set to
+  `target/release/ail` (no `~/.local/bin/ail`); harness picks it up
+  via env-var resolution at `pipeline.rs:42`.
+- iter ms.2.2: CodeLlama-13b-Instruct first run via harness — new
+  run dir
+  `experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-9197fd/`,
+  model id `meta-llama/CodeLlama-13b-Instruct-hf` (Boss-pre-flighted
+  IONOS catalogue id), RUN_STATUS=ok. 6/8 cells informative; 2/8
+  json cells (`t2_length`, `t4_count_zeros`) `api_failure` on turn 1
+  zero tokens.
+- iter ms.2.3: Per-cell metrics computed via direct scores.csv
+  read — see addendum table. Total milestone token spend: prompt
+  501,985 + completion 23,391 = 525,376.
+- iter ms.2.4: DESIGN.md lines 604-636 replaced with new
+  four-column addendum block (~50 lines including the framing
+  paragraph). Subjects named with canonical IONOS model ids and
+  run-dir pointers; framing paragraph reports direction agreement,
+  failure-class symmetry, first-attempt tally, api_failure anomaly,
+  and Qwen-rerun noise. Scope paragraph extended to "two subjects,
+  n=1 each".
+- iter ms.2.5: roadmap.md lines 253-268 removed (P3 multi-subject
+  entry + context note); journal file written. INDEX.md is NOT
+  edited by this agent per the Iron Law; the Boss appends the
+  ms.2 line at commit time. Suggested INDEX line (per plan Task 5
+  Step 3):
+  `- 2026-05-12 — iter ms.2: Qwen retroactive re-run + first CodeLlama-13b-Instruct run; DESIGN.md §Decision-6 addendum extended to four cells; roadmap P3 removed → 2026-05-12-iter-ms.2.md`
+- iter ms.2.6: Spec acceptance criteria sweep (1-7 all green); 14
+  harness tests still pass.
+
+## Spec acceptance sweep
+
+1. ms.1 `pipeline.rs:118` reads `format!("check: {e:#}")` + RED→GREEN unit test → green (ms.1 working tree).
+2. ms.1 existing 14 harness tests still pass → green (verified Task 6 Step 2).
+3. CodeLlama-13b-Instruct-hf runs to completion against IONOS endpoint, RUN_STATUS=ok at run level → green; model id recorded above.
+4. Qwen3-Coder-Next re-run completes, RUN_STATUS=ok, 8 cells; distinct dir from cma.3 baseline → green.
+5. DESIGN.md §"Decision 6 / Empirical addendum" extended with follow-up paragraph + four-cell-shaped table → green.
+6. Roadmap P3 entry removed; one-line mirror above → green.
+7. Per-iter journal (this file) written → green. INDEX.md ms.2 entry is Boss-side per the Iron Law; suggested line is in the end-report.
+
+## Concerns
+
+- 2 of 4 CodeLlama JSON cells are `api_failure` (terminal IONOS
+  error on turn 1). Per the Plan's branch (c) and the carrier's
+  "no exploratory re-runs" constraint, not re-attempted. The
+  addendum and journal disclose this directly; the
+  CodeLlama-JSON column's prompt-token average is therefore over 2
+  informative cells, not 4. Effect on the AILX-cheaper conclusion:
+  none in direction; the prompt-token gap is preserved over the
+  two informative JSON cells. If a future iteration re-runs
+  CodeLlama at lower IONOS load, this should resolve.
+- Qwen-re-run vs cma.3-baseline drift (1 cell) at identical
+  temperature=0 is IONOS noise on a single deterministic call. A
+  future ratification iteration should add ≥3 repetitions per
+  subject to bound this noise, not rely on a single
+  temperature-zero call.
+
+## Known debt
+
+- The pre-existing 3 warnings in `harness/src/ionos.rs` lines 86,
+  125, 137 (`last_err` assigned but never read) survived ms.1
+  and ms.2. Not in scope here; cma.2 inheritance.
+- Decision 6 universal-claim status is still "second data point,
+  not verdict". A future ratification iteration would need ≥3
+  subjects with statistical robustness. Out of scope for ms.
+
+## Files touched
+
+- `docs/DESIGN.md` (addendum extended)
+- `docs/roadmap.md` (P3 entry removed)
+- `experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/` (created by Qwen run)
+- `experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-9197fd/` (created by CodeLlama run)
+- `docs/journals/2026-05-12-iter-ms.2.md` (this file)
+- `bench/orchestrator-stats/2026-05-12-iter-ms.2.json` (stats)
+
+## Stats
+
+bench/orchestrator-stats/2026-05-12-iter-ms.2.json

docs/journals/INDEX.md

@@ -26,3 +26,4 @@
 - 2026-05-12 — iter cma.3: live Qwen3-Coder-Next run + DESIGN.md §Decision-6 empirical addendum + roadmap close (AILX 2/4 green vs JSON 1/4; ~98k vs ~207k tokens; single-subject scope explicit, multi-subject expansion queued as P3) → 2026-05-12-iter-cma.3.md
 - 2026-05-12 — audit-cma: milestone close (Cross-model authoring-form test) — architect drift fixed in 2 record-keeping items (INDEX backfill for brainstorm Step 7.5, README test-count correction); bench all-green (5 unexplained improvements on latency.explicit_at_rc not coupled to milestone, baseline left pristine) → 2026-05-12-audit-cma.md
 - 2026-05-12 — iter ms.1: pipeline anyhow-chain preservation — `{e}` → `{e:#}` at `pipeline.rs:118` restores `serde_json` parse-error leaf in JSON-cohort feedback; pinning unit test added (14/14 green) → 2026-05-12-iter-ms.1.md
+- 2026-05-12 — iter ms.2: Qwen3-Coder-Next retroactive re-run + first CodeLlama-13b-Instruct run via IONOS; DESIGN.md §Decision-6 addendum extended from 2-col single-subject to 4-col two-subject; both subjects agree on direction (AILX cheaper + ≥ green); roadmap P3 multi-subject entry removed → 2026-05-12-iter-ms.2.md

docs/roadmap.md

@@ -249,20 +249,3 @@ context. Pick the next milestone from P1.)_
 - [ ] **\[idea\]** Richer integration paths between RC and
   uniqueness — deferred from the 21' arc; revisit once the
   uniqueness inference covers more program shapes.
-
-- [ ] **\[milestone\]** Multi-subject expansion (cross-model
-  authoring-form follow-up) — extend the cross-model authoring-form
-  test to ≥2 additional foreign LLMs and ≥4 more tasks (broader
-  surface coverage; current MVP run hit only 3/8 green so the
-  failure clusters dominate the signal). Optional: repetitions for
-  statistical robustness; calibrate strip_locations to also strip
-  `at byte N` from AILX-cohort feedback so the asymmetry observed
-  in the cma.3 baseline is removed before re-measuring. Goal: turn
-  the single-subject data point recorded in DESIGN.md §"Decision 6
-  / Empirical addendum (2026-05-12)" into either a ratification or
-  retirement of Decision 6's universal claim. Baseline run:
-  `experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-df7531/`.
-  - context: JOURNAL 2026-05-12 ("iter cma.3"). Other IONOS catalogue
-    models named in the brainstorm record (Meta-Llama-3.1-405B,
-    Llama-3.3-70B, gpt-oss-120b, Mistral-Small-24B, CodeLlama-13b)
-    are reasonable next subjects.

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/RUN_STATUS

@@ -0,0 +1 @@
+ok

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t1_add_three/turn_1_check_stderr.txt

@@ -0,0 +1 @@
+parse error: parse error: unexpected end of input, expected `)` to end module or another def

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t1_add_three/turn_1_program.ailx

@@ -0,0 +1,11 @@
+(module t1_add_three
+  (fn add_three
+    (doc "Add three Ints.")
+    (type (fn-type (params (con Int) (con Int) (con Int)) (ret (con Int))))
+    (params x y z)
+    (body (app + (app + x y) z)))
+  (fn main
+    (doc "Print add_three(1, 2, 3) and add_three(10, 20, 30).")
+    (type (fn-type (params) (ret (con Unit)) (effects IO)))
+    (params)
+    (body (seq (do io/print_int (app add_three 1 2 3)) (do io/print_int (app add_three 10 20 30)))))

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t1_add_three/turn_1_response.json

@@ -0,0 +1,8 @@
+{
+  "content": "(module t1_add_three\n  (fn add_three\n    (doc \"Add three Ints.\")\n    (type (fn-type (params (con Int) (con Int) (con Int)) (ret (con Int))))\n    (params x y z)\n    (body (app + (app + x y) z)))\n  (fn main\n    (doc \"Print add_three(1, 2, 3) and add_three(10, 20, 30).\")\n    (type (fn-type (params) (ret (con Unit)) (effects IO)))\n    (params)\n    (body (seq (do io/print_int (app add_three 1 2 3)) (do io/print_int (app add_three 10 20 30)))))",
+  "usage": {
+    "completion_tokens": 170,
+    "prompt_tokens": 6385,
+    "total_tokens": 6555
+  }
+}

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t1_add_three/turn_2_check_stderr.txt

@@ -0,0 +1 @@
+parse error: parse error: expected `)` (end of type-attr), got `(` at byte 144

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t1_add_three/turn_2_program.ailx

@@ -0,0 +1,11 @@
+(module t1_add_three
+  (fn add_three
+    (doc "Add three Ints.")
+    (type (fn-type (params (con Int) (con Int) (con Int)) (ret (con Int)))
+    (params x y z)
+    (body (app + (app + x y) z)))
+  (fn main
+    (doc "Print add_three(1, 2, 3) and add_three(10, 20, 30).")
+    (type (fn-type (params) (ret (con Unit)) (effects IO)))
+    (params)
+    (body (seq (do io/print_int (app add_three 1 2 3)) (do io/print_int (app add_three 10 20 30)))))

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t1_add_three/turn_2_response.json

@@ -0,0 +1,8 @@
+{
+  "content": "(module t1_add_three\n  (fn add_three\n    (doc \"Add three Ints.\")\n    (type (fn-type (params (con Int) (con Int) (con Int)) (ret (con Int)))\n    (params x y z)\n    (body (app + (app + x y) z)))\n  (fn main\n    (doc \"Print add_three(1, 2, 3) and add_three(10, 20, 30).\")\n    (type (fn-type (params) (ret (con Unit)) (effects IO)))\n    (params)\n    (body (seq (do io/print_int (app add_three 1 2 3)) (do io/print_int (app add_three 10 20 30)))))",
+  "usage": {
+    "completion_tokens": 170,
+    "prompt_tokens": 6586,
+    "total_tokens": 6756
+  }
+}

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t1_add_three/turn_3_check_stderr.txt

@@ -0,0 +1 @@
+parse error: parse error: expected `)` (end of type-attr), got `(` at byte 144

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t1_add_three/turn_3_program.ailx

@@ -0,0 +1,11 @@
+(module t1_add_three
+  (fn add_three
+    (doc "Add three Ints.")
+    (type (fn-type (params (con Int) (con Int) (con Int)) (ret (con Int)))
+    (params x y z)
+    (body (app + (app + x y) z)))
+  (fn main
+    (doc "Print add_three(1, 2, 3) and add_three(10, 20, 30).")
+    (type (fn-type (params) (ret (con Unit)) (effects IO)))
+    (params)
+    (body (seq (do io/print_int (app add_three 1 2 3)) (do io/print_int (app add_three 10 20 30)))))

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t1_add_three/turn_3_response.json

@@ -0,0 +1,8 @@
+{
+  "content": "(module t1_add_three\n  (fn add_three\n    (doc \"Add three Ints.\")\n    (type (fn-type (params (con Int) (con Int) (con Int)) (ret (con Int)))\n    (params x y z)\n    (body (app + (app + x y) z)))\n  (fn main\n    (doc \"Print add_three(1, 2, 3) and add_three(10, 20, 30).\")\n    (type (fn-type (params) (ret (con Unit)) (effects IO)))\n    (params)\n    (body (seq (do io/print_int (app add_three 1 2 3)) (do io/print_int (app add_three 10 20 30)))))",
+  "usage": {
+    "completion_tokens": 170,
+    "prompt_tokens": 6786,
+    "total_tokens": 6956
+  }
+}

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t1_add_three/turn_4_check_stderr.txt

@@ -0,0 +1 @@
+parse error: parse error: expected `)` (end of type-attr), got `(` at byte 144

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t1_add_three/turn_4_program.ailx

@@ -0,0 +1,11 @@
+(module t1_add_three
+  (fn add_three
+    (doc "Add three Ints.")
+    (type (fn-type (params (con Int) (con Int) (con Int)) (ret (con Int)))
+    (params x y z)
+    (body (app + (app + x y) z)))
+  (fn main
+    (doc "Print add_three(1, 2, 3) and add_three(10, 20, 30).")
+    (type (fn-type (params) (ret (con Unit)) (effects IO)))
+    (params)
+    (body (seq (do io/print_int (app add_three 1 2 3)) (do io/print_int (app add_three 10 20 30)))))

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t1_add_three/turn_4_response.json

@@ -0,0 +1,8 @@
+{
+  "content": "(module t1_add_three\n  (fn add_three\n    (doc \"Add three Ints.\")\n    (type (fn-type (params (con Int) (con Int) (con Int)) (ret (con Int)))\n    (params x y z)\n    (body (app + (app + x y) z)))\n  (fn main\n    (doc \"Print add_three(1, 2, 3) and add_three(10, 20, 30).\")\n    (type (fn-type (params) (ret (con Unit)) (effects IO)))\n    (params)\n    (body (seq (do io/print_int (app add_three 1 2 3)) (do io/print_int (app add_three 10 20 30)))))",
+  "usage": {
+    "completion_tokens": 170,
+    "prompt_tokens": 6986,
+    "total_tokens": 7156
+  }
+}

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t1_add_three/turn_5_check_stderr.txt

@@ -0,0 +1 @@
+parse error: parse error: expected `)` (end of type-attr), got `(` at byte 144

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t1_add_three/turn_5_program.ailx

@@ -0,0 +1,11 @@
+(module t1_add_three
+  (fn add_three
+    (doc "Add three Ints.")
+    (type (fn-type (params (con Int) (con Int) (con Int)) (ret (con Int)))
+    (params x y z)
+    (body (app + (app + x y) z)))
+  (fn main
+    (doc "Print add_three(1, 2, 3) and add_three(10, 20, 30).")
+    (type (fn-type (params) (ret (con Unit)) (effects IO)))
+    (params)
+    (body (seq (do io/print_int (app add_three 1 2 3)) (do io/print_int (app add_three 10 20 30)))))

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t1_add_three/turn_5_response.json

@@ -0,0 +1,8 @@
+{
+  "content": "(module t1_add_three\n  (fn add_three\n    (doc \"Add three Ints.\")\n    (type (fn-type (params (con Int) (con Int) (con Int)) (ret (con Int)))\n    (params x y z)\n    (body (app + (app + x y) z)))\n  (fn main\n    (doc \"Print add_three(1, 2, 3) and add_three(10, 20, 30).\")\n    (type (fn-type (params) (ret (con Unit)) (effects IO)))\n    (params)\n    (body (seq (do io/print_int (app add_three 1 2 3)) (do io/print_int (app add_three 10 20 30)))))",
+  "usage": {
+    "completion_tokens": 170,
+    "prompt_tokens": 7186,
+    "total_tokens": 7356
+  }
+}

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t2_length/turn_1_check_stderr.txt

@@ -0,0 +1 @@
+parse error: parse error: expected `)` (end of type-attr), got `(` at byte 202

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t2_length/turn_1_program.ailx

@@ -0,0 +1,17 @@
+(module t2_length
+  (data List (vars a)
+    (ctor Nil)
+    (ctor Cons a (con List)))
+  (fn length
+    (doc "Count the elements in a List a.")
+    (type (fn-type (params (con List)) (ret (con Int)))
+    (params xs)
+    (body (match xs
+      (case (pat-ctor Nil) 0)
+      (case (pat-ctor Cons _ t) (app + 1 (app length t))))))
+  (fn main
+    (doc "Print length(Nil) and length(Cons(7, Cons(8, Cons(9, Nil))))).")
+    (type (fn-type (params) (ret (con Unit)) (effects IO)))
+    (params)
+    (body (seq (do io/print_int (app length (ctor List Nil)))
+      (do io/print_int (app length (ctor List Cons 7 (ctor List Cons 8 (ctor List Cons 9 (ctor List Nil))))))))))

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t2_length/turn_1_response.json

@@ -0,0 +1,8 @@
+{
+  "content": "(module t2_length\n  (data List (vars a)\n    (ctor Nil)\n    (ctor Cons a (con List)))\n  (fn length\n    (doc \"Count the elements in a List a.\")\n    (type (fn-type (params (con List)) (ret (con Int)))\n    (params xs)\n    (body (match xs\n      (case (pat-ctor Nil) 0)\n      (case (pat-ctor Cons _ t) (app + 1 (app length t))))))\n  (fn main\n    (doc \"Print length(Nil) and length(Cons(7, Cons(8, Cons(9, Nil))))).\")\n    (type (fn-type (params) (ret (con Unit)) (effects IO)))\n    (params)\n    (body (seq (do io/print_int (app length (ctor List Nil)))\n      (do io/print_int (app length (ctor List Cons 7 (ctor List Cons 8 (ctor List Cons 9 (ctor List Nil))))))))))\n",
+  "usage": {
+    "completion_tokens": 217,
+    "prompt_tokens": 6409,
+    "total_tokens": 6626
+  }
+}

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t2_length/turn_2_check_stderr.txt

@@ -0,0 +1 @@
+parse error: parse error in term: unknown term head `ctor`; expected one of `app`, `tail-app`, `lam`, `let`, `let-rec`, `if`, `match`, `do`, `tail-do`, `seq`, `term-ctor`, `clone`, `reuse-as`, `lit-unit` at byte 529

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t2_length/turn_2_program.ailx

@@ -0,0 +1,17 @@
+(module t2_length
+  (data List (vars a)
+    (ctor Nil)
+    (ctor Cons a (con List)))
+  (fn length
+    (doc "Count the elements in a List a.")
+    (type (fn-type (params (con List)) (ret (con Int))))
+    (params xs)
+    (body (match xs
+      (case (pat-ctor Nil) 0)
+      (case (pat-ctor Cons _ t) (app + 1 (app length t))))))
+  (fn main
+    (doc "Print length(Nil) and length(Cons(7, Cons(8, Cons(9, Nil))))).")
+    (type (fn-type (params) (ret (con Unit)) (effects IO)))
+    (params)
+    (body (seq (do io/print_int (app length (ctor List Nil)))
+      (do io/print_int (app length (ctor List Cons 7 (ctor List Cons 8 (ctor List Cons 9 (ctor List Nil))))))))))

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t2_length/turn_2_response.json

@@ -0,0 +1,8 @@
+{
+  "content": "(module t2_length\n  (data List (vars a)\n    (ctor Nil)\n    (ctor Cons a (con List)))\n  (fn length\n    (doc \"Count the elements in a List a.\")\n    (type (fn-type (params (con List)) (ret (con Int))))\n    (params xs)\n    (body (match xs\n      (case (pat-ctor Nil) 0)\n      (case (pat-ctor Cons _ t) (app + 1 (app length t))))))\n  (fn main\n    (doc \"Print length(Nil) and length(Cons(7, Cons(8, Cons(9, Nil))))).\")\n    (type (fn-type (params) (ret (con Unit)) (effects IO)))\n    (params)\n    (body (seq (do io/print_int (app length (ctor List Nil)))\n      (do io/print_int (app length (ctor List Cons 7 (ctor List Cons 8 (ctor List Cons 9 (ctor List Nil))))))))))\n",
+  "usage": {
+    "completion_tokens": 217,
+    "prompt_tokens": 6656,
+    "total_tokens": 6873
+  }
+}

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t2_length/turn_3_check_stderr.txt

@@ -0,0 +1,3 @@
+error: [unknown-type] List: unknown type: `List expects 1 type arg(s), got 0`
+error: [unknown-type] length: unknown type: `List expects 1 type arg(s), got 0`
+error: [type-mismatch] main: type mismatch: expected List, got List<$m0>

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t2_length/turn_3_program.ailx

@@ -0,0 +1,17 @@
+(module t2_length
+  (data List (vars a)
+    (ctor Nil)
+    (ctor Cons a (con List)))
+  (fn length
+    (doc "Count the elements in a List a.")
+    (type (fn-type (params (con List)) (ret (con Int))))
+    (params xs)
+    (body (match xs
+      (case (pat-ctor Nil) 0)
+      (case (pat-ctor Cons _ t) (app + 1 (app length t))))))
+  (fn main
+    (doc "Print length(Nil) and length(Cons(7, Cons(8, Cons(9, Nil))))).")
+    (type (fn-type (params) (ret (con Unit)) (effects IO)))
+    (params)
+    (body (seq (do io/print_int (app length (term-ctor List Nil)))
+      (do io/print_int (app length (term-ctor List Cons 7 (term-ctor List Cons 8 (term-ctor List Cons 9 (term-ctor List Nil))))))))))

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t2_length/turn_3_response.json

@@ -0,0 +1,8 @@
+{
+  "content": "(module t2_length\n  (data List (vars a)\n    (ctor Nil)\n    (ctor Cons a (con List)))\n  (fn length\n    (doc \"Count the elements in a List a.\")\n    (type (fn-type (params (con List)) (ret (con Int))))\n    (params xs)\n    (body (match xs\n      (case (pat-ctor Nil) 0)\n      (case (pat-ctor Cons _ t) (app + 1 (app length t))))))\n  (fn main\n    (doc \"Print length(Nil) and length(Cons(7, Cons(8, Cons(9, Nil))))).\")\n    (type (fn-type (params) (ret (con Unit)) (effects IO)))\n    (params)\n    (body (seq (do io/print_int (app length (term-ctor List Nil)))\n      (do io/print_int (app length (term-ctor List Cons 7 (term-ctor List Cons 8 (term-ctor List Cons 9 (term-ctor List Nil))))))))))\n",
+  "usage": {
+    "completion_tokens": 227,
+    "prompt_tokens": 6950,
+    "total_tokens": 7177
+  }
+}

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t2_length/turn_4_check_stderr.txt

@@ -0,0 +1 @@
+parse error: lex error: invalid integer literal "7," at byte 380

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t2_length/turn_4_program.ailx

@@ -0,0 +1,17 @@
+(module t2_length
+  (data List (vars a)
+    (ctor Nil)
+    (ctor Cons a (con List)))
+  (fn length
+    (doc "Count the elements in a List a.)
+    (type (fn-type (params (con List)) (ret (con Int))))
+    (params xs)
+    (body (match xs
+      (case (pat-ctor Nil) 0)
+      (case (pat-ctor Cons _ t) (app + 1 (app length t))))))
+  (fn main
+    (doc "Print length(Nil) and length(Cons(7, Cons(8, Cons(9, Nil))))).")
+    (type (fn-type (params) (ret (con Unit)) (effects IO)))
+    (params)
+    (body (seq (do io/print_int (app length (term-ctor List Nil)))
+      (do io/print_int (app length (term-ctor List Cons 7 (term-ctor List Cons 8 (term-ctor List Cons 9 (term-ctor List Nil))))))))))

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t2_length/turn_4_response.json

@@ -0,0 +1,8 @@
+{
+  "content": "(module t2_length\n  (data List (vars a)\n    (ctor Nil)\n    (ctor Cons a (con List)))\n  (fn length\n    (doc \"Count the elements in a List a.)\n    (type (fn-type (params (con List)) (ret (con Int))))\n    (params xs)\n    (body (match xs\n      (case (pat-ctor Nil) 0)\n      (case (pat-ctor Cons _ t) (app + 1 (app length t))))))\n  (fn main\n    (doc \"Print length(Nil) and length(Cons(7, Cons(8, Cons(9, Nil))))).\")\n    (type (fn-type (params) (ret (con Unit)) (effects IO)))\n    (params)\n    (body (seq (do io/print_int (app length (term-ctor List Nil)))\n      (do io/print_int (app length (term-ctor List Cons 7 (term-ctor List Cons 8 (term-ctor List Cons 9 (term-ctor List Nil))))))))))\n",
+  "usage": {
+    "completion_tokens": 227,
+    "prompt_tokens": 7257,
+    "total_tokens": 7484
+  }
+}

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t2_length/turn_5_check_stderr.txt

@@ -0,0 +1,3 @@
+error: [unknown-type] List: unknown type: `List expects 1 type arg(s), got 0`
+error: [unknown-type] length: unknown type: `List expects 1 type arg(s), got 0`
+error: [type-mismatch] main: type mismatch: expected List, got List<$m0>

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t2_length/turn_5_program.ailx

@@ -0,0 +1,17 @@
+(module t2_length
+  (data List (vars a)
+    (ctor Nil)
+    (ctor Cons a (con List)))
+  (fn length
+    (doc "Count the elements in a List a.")
+    (type (fn-type (params (con List)) (ret (con Int))))
+    (params xs)
+    (body (match xs
+      (case (pat-ctor Nil) 0)
+      (case (pat-ctor Cons _ t) (app + 1 (app length t))))))
+  (fn main
+    (doc "Print length(Nil) and length(Cons(7, Cons(8, Cons(9, Nil))))).")
+    (type (fn-type (params) (ret (con Unit)) (effects IO)))
+    (params)
+    (body (seq (do io/print_int (app length (term-ctor List Nil)))
+      (do io/print_int (app length (term-ctor List Cons 7 (term-ctor List Cons 8 (term-ctor List Cons 9 (term-ctor List Nil))))))))))

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t2_length/turn_5_response.json

@@ -0,0 +1,8 @@
+{
+  "content": "(module t2_length\n  (data List (vars a)\n    (ctor Nil)\n    (ctor Cons a (con List)))\n  (fn length\n    (doc \"Count the elements in a List a.\")\n    (type (fn-type (params (con List)) (ret (con Int))))\n    (params xs)\n    (body (match xs\n      (case (pat-ctor Nil) 0)\n      (case (pat-ctor Cons _ t) (app + 1 (app length t))))))\n  (fn main\n    (doc \"Print length(Nil) and length(Cons(7, Cons(8, Cons(9, Nil))))).\")\n    (type (fn-type (params) (ret (con Unit)) (effects IO)))\n    (params)\n    (body (seq (do io/print_int (app length (term-ctor List Nil)))\n      (do io/print_int (app length (term-ctor List Cons 7 (term-ctor List Cons 8 (term-ctor List Cons 9 (term-ctor List Nil))))))))))\n",
+  "usage": {
+    "completion_tokens": 227,
+    "prompt_tokens": 7507,
+    "total_tokens": 7734
+  }
+}

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t3_main_prints/turn_1_program.ailx

@@ -0,0 +1,6 @@
+(module t3_main_prints
+  (fn main
+    (doc "Print 42 then 1337, each on its own line.")
+    (type (fn-type (params) (ret (con Unit)) (effects IO)))
+    (params)
+    (body (seq (do io/print_int 42) (do io/print_int 1337)))))

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t3_main_prints/turn_1_response.json

@@ -0,0 +1,8 @@
+{
+  "content": "(module t3_main_prints\n  (fn main\n    (doc \"Print 42 then 1337, each on its own line.\")\n    (type (fn-type (params) (ret (con Unit)) (effects IO)))\n    (params)\n    (body (seq (do io/print_int 42) (do io/print_int 1337)))))",
+  "usage": {
+    "completion_tokens": 83,
+    "prompt_tokens": 6356,
+    "total_tokens": 6439
+  }
+}

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t3_main_prints/turn_1_run_stdout.txt

@@ -0,0 +1,2 @@
+42
+1337

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t4_count_zeros/turn_1_check_stderr.txt

@@ -0,0 +1 @@
+parse error: parse error: expected `)` (end of type-attr), got `(` at byte 242

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t4_count_zeros/turn_1_program.ailx

@@ -0,0 +1,18 @@
+(module t4_count_zeros
+  (data List (vars a)
+    (ctor Nil)
+    (ctor Cons a (con List)))
+  (fn count_zeros
+    (doc "Count zeros in an Int list using the prelude Eq Int instance.")
+    (type (fn-type (params (con List)) (ret (con Int)))
+    (params xs)
+    (body (match xs
+      (case (pat-ctor Nil) 0)
+      (case (pat-ctor Cons h t) (if (app == h 0) (app + 1 (app count_zeros t)) (app count_zeros t))))))
+  (fn main
+    (doc "Print count_zeros(Nil) and count_zeros(Cons(0, Cons(5, Cons(0, Cons(3, Cons(0, Nil)))))) each on its own line.")
+    (type (fn-type (params) (ret (con Unit)) (effects IO)))
+    (params)
+    (body (seq (do io/print_int (app count_zeros (ctor List Nil)))
+      (seq (do io/print_int (app count_zeros (ctor List Cons 0 (ctor List Cons 5 (ctor List Cons 0 (ctor List Cons 3 (ctor List Cons 0 (ctor List Nil)))))) (unit))))))
+)

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t4_count_zeros/turn_1_response.json

@@ -0,0 +1,8 @@
+{
+  "content": "(module t4_count_zeros\n  (data List (vars a)\n    (ctor Nil)\n    (ctor Cons a (con List)))\n  (fn count_zeros\n    (doc \"Count zeros in an Int list using the prelude Eq Int instance.\")\n    (type (fn-type (params (con List)) (ret (con Int)))\n    (params xs)\n    (body (match xs\n      (case (pat-ctor Nil) 0)\n      (case (pat-ctor Cons h t) (if (app == h 0) (app + 1 (app count_zeros t)) (app count_zeros t))))))\n  (fn main\n    (doc \"Print count_zeros(Nil) and count_zeros(Cons(0, Cons(5, Cons(0, Cons(3, Cons(0, Nil)))))) each on its own line.\")\n    (type (fn-type (params) (ret (con Unit)) (effects IO)))\n    (params)\n    (body (seq (do io/print_int (app count_zeros (ctor List Nil)))\n      (seq (do io/print_int (app count_zeros (ctor List Cons 0 (ctor List Cons 5 (ctor List Cons 0 (ctor List Cons 3 (ctor List Cons 0 (ctor List Nil)))))) (unit))))))\n)",
+  "usage": {
+    "completion_tokens": 276,
+    "prompt_tokens": 6436,
+    "total_tokens": 6712
+  }
+}

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t4_count_zeros/turn_2_check_stderr.txt

@@ -0,0 +1 @@
+parse error: parse error in term: unknown term head `ctor`; expected one of `app`, `tail-app`, `lam`, `let`, `let-rec`, `if`, `match`, `do`, `tail-do`, `seq`, `term-ctor`, `clone`, `reuse-as`, `lit-unit` at byte 665

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t4_count_zeros/turn_2_program.ailx

@@ -0,0 +1,18 @@
+(module t4_count_zeros
+  (data List (vars a)
+    (ctor Nil)
+    (ctor Cons a (con List)))
+  (fn count_zeros
+    (doc "Count zeros in an Int list using the prelude Eq Int instance.")
+    (type (fn-type (params (con List)) (ret (con Int))))
+    (params xs)
+    (body (match xs
+      (case (pat-ctor Nil) 0)
+      (case (pat-ctor Cons h t) (if (app == h 0) (app + 1 (app count_zeros t)) (app count_zeros t))))))
+  (fn main
+    (doc "Print count_zeros(Nil) and count_zeros(Cons(0, Cons(5, Cons(0, Cons(3, Cons(0, Nil)))))) each on its own line.")
+    (type (fn-type (params) (ret (con Unit)) (effects IO)))
+    (params)
+    (body (seq (do io/print_int (app count_zeros (ctor List Nil)))
+      (seq (do io/print_int (app count_zeros (ctor List Cons 0 (ctor List Cons 5 (ctor List Cons 0 (ctor List Cons 3 (ctor List Cons 0 (ctor List Nil)))))) (unit))))))
+)

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t4_count_zeros/turn_2_response.json

@@ -0,0 +1,8 @@
+{
+  "content": "(module t4_count_zeros\n  (data List (vars a)\n    (ctor Nil)\n    (ctor Cons a (con List)))\n  (fn count_zeros\n    (doc \"Count zeros in an Int list using the prelude Eq Int instance.\")\n    (type (fn-type (params (con List)) (ret (con Int))))\n    (params xs)\n    (body (match xs\n      (case (pat-ctor Nil) 0)\n      (case (pat-ctor Cons h t) (if (app == h 0) (app + 1 (app count_zeros t)) (app count_zeros t))))))\n  (fn main\n    (doc \"Print count_zeros(Nil) and count_zeros(Cons(0, Cons(5, Cons(0, Cons(3, Cons(0, Nil)))))) each on its own line.\")\n    (type (fn-type (params) (ret (con Unit)) (effects IO)))\n    (params)\n    (body (seq (do io/print_int (app count_zeros (ctor List Nil)))\n      (seq (do io/print_int (app count_zeros (ctor List Cons 0 (ctor List Cons 5 (ctor List Cons 0 (ctor List Cons 3 (ctor List Cons 0 (ctor List Nil)))))) (unit))))))\n)",
+  "usage": {
+    "completion_tokens": 276,
+    "prompt_tokens": 6742,
+    "total_tokens": 7018
+  }
+}

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t4_count_zeros/turn_3_check_stderr.txt

@@ -0,0 +1 @@
+parse error: parse error in term: unknown term head `unit`; expected one of `app`, `tail-app`, `lam`, `let`, `let-rec`, `if`, `match`, `do`, `tail-do`, `seq`, `term-ctor`, `clone`, `reuse-as`, `lit-unit` at byte 874

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t4_count_zeros/turn_3_program.ailx

@@ -0,0 +1,18 @@
+(module t4_count_zeros
+  (data List (vars a)
+    (ctor Nil)
+    (ctor Cons a (con List)))
+  (fn count_zeros
+    (doc "Count zeros in an Int list using the prelude Eq Int instance.")
+    (type (fn-type (params (con List)) (ret (con Int))))
+    (params xs)
+    (body (match xs
+      (case (pat-ctor Nil) 0)
+      (case (pat-ctor Cons h t) (if (app == h 0) (app + 1 (app count_zeros t)) (app count_zeros t))))))
+  (fn main
+    (doc "Print count_zeros(Nil) and count_zeros(Cons(0, Cons(5, Cons(0, Cons(3, Cons(0, Nil)))))) each on its own line.")
+    (type (fn-type (params) (ret (con Unit)) (effects IO)))
+    (params)
+    (body (seq (do io/print_int (app count_zeros (term-ctor List Nil)))
+      (seq (do io/print_int (app count_zeros (term-ctor List Cons 0 (term-ctor List Cons 5 (term-ctor List Cons 0 (term-ctor List Cons 3 (term-ctor List Cons 0 (term-ctor List Nil)))))) (unit))))))
+)

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t4_count_zeros/turn_3_response.json

@@ -0,0 +1,8 @@
+{
+  "content": "(module t4_count_zeros\n  (data List (vars a)\n    (ctor Nil)\n    (ctor Cons a (con List)))\n  (fn count_zeros\n    (doc \"Count zeros in an Int list using the prelude Eq Int instance.\")\n    (type (fn-type (params (con List)) (ret (con Int))))\n    (params xs)\n    (body (match xs\n      (case (pat-ctor Nil) 0)\n      (case (pat-ctor Cons h t) (if (app == h 0) (app + 1 (app count_zeros t)) (app count_zeros t))))))\n  (fn main\n    (doc \"Print count_zeros(Nil) and count_zeros(Cons(0, Cons(5, Cons(0, Cons(3, Cons(0, Nil)))))) each on its own line.\")\n    (type (fn-type (params) (ret (con Unit)) (effects IO)))\n    (params)\n    (body (seq (do io/print_int (app count_zeros (term-ctor List Nil)))\n      (seq (do io/print_int (app count_zeros (term-ctor List Cons 0 (term-ctor List Cons 5 (term-ctor List Cons 0 (term-ctor List Cons 3 (term-ctor List Cons 0 (term-ctor List Nil)))))) (unit))))))\n)",
+  "usage": {
+    "completion_tokens": 290,
+    "prompt_tokens": 7095,
+    "total_tokens": 7385
+  }
+}

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t4_count_zeros/turn_4_check_stderr.txt

@@ -0,0 +1 @@
+parse error: parse error: expected term, got `)` at byte 886

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t4_count_zeros/turn_4_program.ailx

@@ -0,0 +1,18 @@
+(module t4_count_zeros
+  (data List (vars a)
+    (ctor Nil)
+    (ctor Cons a (con List)))
+  (fn count_zeros
+    (doc "Count zeros in an Int list using the prelude Eq Int instance.")
+    (type (fn-type (params (con List)) (ret (con Int))))
+    (params xs)
+    (body (match xs
+      (case (pat-ctor Nil) 0)
+      (case (pat-ctor Cons h t) (if (app == h 0) (app + 1 (app count_zeros t)) (app count_zeros t))))))
+  (fn main
+    (doc "Print count_zeros(Nil) and count_zeros(Cons(0, Cons(5, Cons(0, Cons(3, Cons(0, Nil)))))) each on its own line.")
+    (type (fn-type (params) (ret (con Unit)) (effects IO)))
+    (params)
+    (body (seq (do io/print_int (app count_zeros (term-ctor List Nil)))
+      (seq (do io/print_int (app count_zeros (term-ctor List Cons 0 (term-ctor List Cons 5 (term-ctor List Cons 0 (term-ctor List Cons 3 (term-ctor List Cons 0 (term-ctor List Nil)))))) (lit-unit))))))
+)

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t4_count_zeros/turn_4_response.json

@@ -0,0 +1,8 @@
+{
+  "content": "(module t4_count_zeros\n  (data List (vars a)\n    (ctor Nil)\n    (ctor Cons a (con List)))\n  (fn count_zeros\n    (doc \"Count zeros in an Int list using the prelude Eq Int instance.\")\n    (type (fn-type (params (con List)) (ret (con Int))))\n    (params xs)\n    (body (match xs\n      (case (pat-ctor Nil) 0)\n      (case (pat-ctor Cons h t) (if (app == h 0) (app + 1 (app count_zeros t)) (app count_zeros t))))))\n  (fn main\n    (doc \"Print count_zeros(Nil) and count_zeros(Cons(0, Cons(5, Cons(0, Cons(3, Cons(0, Nil)))))) each on its own line.\")\n    (type (fn-type (params) (ret (con Unit)) (effects IO)))\n    (params)\n    (body (seq (do io/print_int (app count_zeros (term-ctor List Nil)))\n      (seq (do io/print_int (app count_zeros (term-ctor List Cons 0 (term-ctor List Cons 5 (term-ctor List Cons 0 (term-ctor List Cons 3 (term-ctor List Cons 0 (term-ctor List Nil)))))) (lit-unit))))))\n)",
+  "usage": {
+    "completion_tokens": 291,
+    "prompt_tokens": 7462,
+    "total_tokens": 7753
+  }
+}

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t4_count_zeros/turn_5_check_stderr.txt

@@ -0,0 +1 @@
+parse error: parse error in term: unknown term head `term-lit-unit`; expected one of `app`, `tail-app`, `lam`, `let`, `let-rec`, `if`, `match`, `do`, `tail-do`, `seq`, `term-ctor`, `clone`, `reuse-as`, `lit-unit` at byte 874

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t4_count_zeros/turn_5_program.ailx

@@ -0,0 +1,18 @@
+(module t4_count_zeros
+  (data List (vars a)
+    (ctor Nil)
+    (ctor Cons a (con List)))
+  (fn count_zeros
+    (doc "Count zeros in an Int list using the prelude Eq Int instance.")
+    (type (fn-type (params (con List)) (ret (con Int))))
+    (params xs)
+    (body (match xs
+      (case (pat-ctor Nil) 0)
+      (case (pat-ctor Cons h t) (if (app == h 0) (app + 1 (app count_zeros t)) (app count_zeros t))))))
+  (fn main
+    (doc "Print count_zeros(Nil) and count_zeros(Cons(0, Cons(5, Cons(0, Cons(3, Cons(0, Nil)))))) each on its own line.")
+    (type (fn-type (params) (ret (con Unit)) (effects IO)))
+    (params)
+    (body (seq (do io/print_int (app count_zeros (term-ctor List Nil)))
+      (seq (do io/print_int (app count_zeros (term-ctor List Cons 0 (term-ctor List Cons 5 (term-ctor List Cons 0 (term-ctor List Cons 3 (term-ctor List Cons 0 (term-ctor List Nil)))))) (term-lit-unit))))))
+)

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/ailx/t4_count_zeros/turn_5_response.json

@@ -0,0 +1,8 @@
+{
+  "content": "(module t4_count_zeros\n  (data List (vars a)\n    (ctor Nil)\n    (ctor Cons a (con List)))\n  (fn count_zeros\n    (doc \"Count zeros in an Int list using the prelude Eq Int instance.\")\n    (type (fn-type (params (con List)) (ret (con Int))))\n    (params xs)\n    (body (match xs\n      (case (pat-ctor Nil) 0)\n      (case (pat-ctor Cons h t) (if (app == h 0) (app + 1 (app count_zeros t)) (app count_zeros t))))))\n  (fn main\n    (doc \"Print count_zeros(Nil) and count_zeros(Cons(0, Cons(5, Cons(0, Cons(3, Cons(0, Nil)))))) each on its own line.\")\n    (type (fn-type (params) (ret (con Unit)) (effects IO)))\n    (params)\n    (body (seq (do io/print_int (app count_zeros (term-ctor List Nil)))\n      (seq (do io/print_int (app count_zeros (term-ctor List Cons 0 (term-ctor List Cons 5 (term-ctor List Cons 0 (term-ctor List Cons 3 (term-ctor List Cons 0 (term-ctor List Nil)))))) (term-lit-unit))))))\n)",
+  "usage": {
+    "completion_tokens": 293,
+    "prompt_tokens": 7776,
+    "total_tokens": 8069
+  }
+}

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/json/t1_add_three/turn_1_program.ail.json

@@ -0,0 +1,101 @@
+{
+  "schema": "ailang/v0",
+  "name": "t1_add_three",
+  "imports": [],
+  "defs": [
+    {
+      "kind": "fn",
+      "name": "add_three",
+      "doc": "Add three Ints.",
+      "type": {
+        "k": "fn",
+        "params": [
+          { "k": "con", "name": "Int" },
+          { "k": "con", "name": "Int" },
+          { "k": "con", "name": "Int" }
+        ],
+        "ret": { "k": "con", "name": "Int" },
+        "effects": []
+      },
+      "params": ["a", "b", "c"],
+      "body": {
+        "t": "app",
+        "fn": { "t": "var", "name": "+" },
+        "args": [
+          {
+            "t": "app",
+            "fn": { "t": "var", "name": "+" },
+            "args": [
+              { "t": "var", "name": "a" },
+              { "t": "var", "name": "b" }
+            ]
+          },
+          { "t": "var", "name": "c" }
+        ]
+      }
+    },
+    {
+      "kind": "fn",
+      "name": "main",
+      "doc": "Print add_three(1, 2, 3) and add_three(10, 20, 30) on separate lines.",
+      "type": {
+        "k": "fn",
+        "params": [],
+        "ret": { "k": "con", "name": "Unit" },
+        "effects": ["IO"]
+      },
+      "params": [],
+      "body": {
+        "t": "seq",
+        "lhs": {
+          "t": "do",
+          "op": "io/print_int",
+          "args": [
+            {
+              "t": "app",
+              "fn": { "t": "var", "name": "add_three" },
+              "args": [
+                { "t": "lit", "lit": { "kind": "int", "value": 1 } },
+                { "t": "lit", "lit": { "kind": "int", "value": 2 } },
+                { "t": "lit", "lit": { "kind": "int", "value": 3 } }
+              ]
+            }
+          ]
+        },
+        "rhs": {
+          "t": "seq",
+          "lhs": {
+            "t": "do",
+            "op": "io/print_int",
+            "args": [
+              {
+                "t": "app",
+                "fn": { "t": "var", "name": "add_three" },
+                "args": [
+                  { "t": "lit", "lit": { "kind": "int", "value": 10 } },
+                  { "t": "lit", "lit": { "kind": "int", "value": 20 } },
+                  { "t": "lit", "lit": { "kind": "int", "value": 30 } }
+                ]
+              }
+            ]
+          },
+          "rhs": {
+            "t": "do",
+            "op": "io/print_int",
+            "args": [
+              {
+                "t": "app",
+                "fn": { "t": "var", "name": "add_three" },
+                "args": [
+                  { "t": "lit", "lit": { "kind": "int", "value": 1 } },
+                  { "t": "lit", "lit": { "kind": "int", "value": 2 } },
+                  { "t": "lit", "lit": { "kind": "int", "value": 3 } }
+                ]
+              }
+            ]
+          }
+        }
+      }
+    }
+  ]
+}

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/json/t1_add_three/turn_1_response.json

@@ -0,0 +1,8 @@
+{
+  "content": "{\n  \"schema\": \"ailang/v0\",\n  \"name\": \"t1_add_three\",\n  \"imports\": [],\n  \"defs\": [\n    {\n      \"kind\": \"fn\",\n      \"name\": \"add_three\",\n      \"doc\": \"Add three Ints.\",\n      \"type\": {\n        \"k\": \"fn\",\n        \"params\": [\n          { \"k\": \"con\", \"name\": \"Int\" },\n          { \"k\": \"con\", \"name\": \"Int\" },\n          { \"k\": \"con\", \"name\": \"Int\" }\n        ],\n        \"ret\": { \"k\": \"con\", \"name\": \"Int\" },\n        \"effects\": []\n      },\n      \"params\": [\"a\", \"b\", \"c\"],\n      \"body\": {\n        \"t\": \"app\",\n        \"fn\": { \"t\": \"var\", \"name\": \"+\" },\n        \"args\": [\n          {\n            \"t\": \"app\",\n            \"fn\": { \"t\": \"var\", \"name\": \"+\" },\n            \"args\": [\n              { \"t\": \"var\", \"name\": \"a\" },\n              { \"t\": \"var\", \"name\": \"b\" }\n            ]\n          },\n          { \"t\": \"var\", \"name\": \"c\" }\n        ]\n      }\n    },\n    {\n      \"kind\": \"fn\",\n      \"name\": \"main\",\n      \"doc\": \"Print add_three(1, 2, 3) and add_three(10, 20, 30) on separate lines.\",\n      \"type\": {\n        \"k\": \"fn\",\n        \"params\": [],\n        \"ret\": { \"k\": \"con\", \"name\": \"Unit\" },\n        \"effects\": [\"IO\"]\n      },\n      \"params\": [],\n      \"body\": {\n        \"t\": \"seq\",\n        \"lhs\": {\n          \"t\": \"do\",\n          \"op\": \"io/print_int\",\n          \"args\": [\n            {\n              \"t\": \"app\",\n              \"fn\": { \"t\": \"var\", \"name\": \"add_three\" },\n              \"args\": [\n                { \"t\": \"lit\", \"lit\": { \"kind\": \"int\", \"value\": 1 } },\n                { \"t\": \"lit\", \"lit\": { \"kind\": \"int\", \"value\": 2 } },\n                { \"t\": \"lit\", \"lit\": { \"kind\": \"int\", \"value\": 3 } }\n              ]\n            }\n          ]\n        },\n        \"rhs\": {\n          \"t\": \"seq\",\n          \"lhs\": {\n            \"t\": \"do\",\n            \"op\": \"io/print_int\",\n            \"args\": [\n              {\n                \"t\": \"app\",\n                \"fn\": { \"t\": \"var\", \"name\": \"add_three\" },\n                \"args\": [\n                  { \"t\": \"lit\", \"lit\": { \"kind\": \"int\", \"value\": 10 } },\n                  { \"t\": \"lit\", \"lit\": { \"kind\": \"int\", \"value\": 20 } },\n                  { \"t\": \"lit\", \"lit\": { \"kind\": \"int\", \"value\": 30 } }\n                ]\n              }\n            ]\n          },\n          \"rhs\": {\n            \"t\": \"do\",\n            \"op\": \"io/print_int\",\n            \"args\": [\n              {\n                \"t\": \"app\",\n                \"fn\": { \"t\": \"var\", \"name\": \"add_three\" },\n                \"args\": [\n                  { \"t\": \"lit\", \"lit\": { \"kind\": \"int\", \"value\": 1 } },\n                  { \"t\": \"lit\", \"lit\": { \"kind\": \"int\", \"value\": 2 } },\n                  { \"t\": \"lit\", \"lit\": { \"kind\": \"int\", \"value\": 3 } }\n                ]\n              }\n            ]\n          }\n        }\n      }\n    }\n  ]\n}",
+  "usage": {
+    "completion_tokens": 842,
+    "prompt_tokens": 9435,
+    "total_tokens": 10277
+  }
+}

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/json/t1_add_three/turn_1_run_stdout.txt

@@ -0,0 +1,3 @@
+6
+60
+6

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/json/t1_add_three/turn_2_check_stderr.txt

@@ -0,0 +1 @@
+parsing JSON in /tmp/cma2-run-tk0Cm9/prog.ail.json

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/json/t1_add_three/turn_2_program.ail.json

@@ -0,0 +1,99 @@
+{
+  "schema": "ailang/v0",
+  "name": "t1_add_three",
+  "imports": [],
+  "defs": [
+    {
+      "kind": "fn",
+      "name": "add_three",
+      "doc": "Add three Ints.",
+      "type": {
+        "k": "fn",
+        "params": [
+          { "k": "con", "name": "Int" },
+          { "k": "con", "name": "Int" },
+          { "k": "con", "name": "Int" }
+        ],
+        "ret": { "k": "con", "name": "Int" },
+        "effects": []
+      },
+      "params": ["a", "b", "c"],
+      "body": {
+        "t": "app",
+        "fn": { "t": "var", "name": "+" },
+        "args": [
+          {
+            "t": "app",
+        "fn": { "t": "var", "name": "+" },
+        "args": [
+          { "t": "var", "name": "a" },
+          { "t": "var", "name": "b" }
+        ]
+        },
+        { "t": "var", "name": "c" }
+      }
+    },
+    {
+      "kind": "fn",
+      "name": "main",
+      "doc": "Print add_three(1, 2, 3) and add_three(10, 20, 30) on separate lines.",
+      "type": {
+        "k": "fn",
+        "params": [],
+        "ret": { "k": "con", "name": "Unit" },
+        "effects": ["IO"]
+      },
+      "params": [],
+      "body": {
+        "t": "seq",
+        "lhs": {
+          "t": "do",
+          "op": "io/print_int",
+          "args": [
+            {
+              "t": "app",
+              "fn": { "t": "var", "name": "add_three" },
+              "args": [
+                { "t": "lit", "lit": { "kind": "int", "value": 1 } },
+                { "t": "lit", "lit": { "kind": "int", "value": 2 } },
+                { "t": "lit", "lit": { "kind": "int", "value": 3 } }
+              ]
+            }
+          }
+        },
+        "rhs": {
+          "t": "seq",
+          "lhs": {
+            "t": "do",
+            "op": "io/print_int",
+            "args": [
+              {
+                "t": "app",
+                "fn": { "t": "var", "name": "add_three" },
+                "args": [
+                  { "t": "lit", "lit": { "kind": "int", "value": 10 } },
+                  { "t": "lit", "lit": { "kind": "int", "value": 20 } },
+                  { "t": "lit", "lit": { "kind": "int", "value": 30 } }
+              ]
+            }
+          },
+          "rhs": {
+            "t": "do",
+            "op": "io/print_int",
+            "args": [
+              {
+                "t": "app",
+                "fn": { "t": "var", "name": "add_three" },
+                "args": [
+                  { "t": "lit", "lit": { "kind": "int", "value": 1 } },
+                  { "t": "lit", "lit": { "kind": "int", "value": 2 } },
+                  { "t": "lit": { "kind": "int", "value": 3 } }
+                ]
+              }
+            ]
+          }
+        }
+      }
+    }
+  ]
+}

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/json/t1_add_three/turn_2_response.json

@@ -0,0 +1,8 @@
+{
+  "content": "{\n  \"schema\": \"ailang/v0\",\n  \"name\": \"t1_add_three\",\n  \"imports\": [],\n  \"defs\": [\n    {\n      \"kind\": \"fn\",\n      \"name\": \"add_three\",\n      \"doc\": \"Add three Ints.\",\n      \"type\": {\n        \"k\": \"fn\",\n        \"params\": [\n          { \"k\": \"con\", \"name\": \"Int\" },\n          { \"k\": \"con\", \"name\": \"Int\" },\n          { \"k\": \"con\", \"name\": \"Int\" }\n        ],\n        \"ret\": { \"k\": \"con\", \"name\": \"Int\" },\n        \"effects\": []\n      },\n      \"params\": [\"a\", \"b\", \"c\"],\n      \"body\": {\n        \"t\": \"app\",\n        \"fn\": { \"t\": \"var\", \"name\": \"+\" },\n        \"args\": [\n          {\n            \"t\": \"app\",\n        \"fn\": { \"t\": \"var\", \"name\": \"+\" },\n        \"args\": [\n          { \"t\": \"var\", \"name\": \"a\" },\n          { \"t\": \"var\", \"name\": \"b\" }\n        ]\n        },\n        { \"t\": \"var\", \"name\": \"c\" }\n      }\n    },\n    {\n      \"kind\": \"fn\",\n      \"name\": \"main\",\n      \"doc\": \"Print add_three(1, 2, 3) and add_three(10, 20, 30) on separate lines.\",\n      \"type\": {\n        \"k\": \"fn\",\n        \"params\": [],\n        \"ret\": { \"k\": \"con\", \"name\": \"Unit\" },\n        \"effects\": [\"IO\"]\n      },\n      \"params\": [],\n      \"body\": {\n        \"t\": \"seq\",\n        \"lhs\": {\n          \"t\": \"do\",\n          \"op\": \"io/print_int\",\n          \"args\": [\n            {\n              \"t\": \"app\",\n              \"fn\": { \"t\": \"var\", \"name\": \"add_three\" },\n              \"args\": [\n                { \"t\": \"lit\", \"lit\": { \"kind\": \"int\", \"value\": 1 } },\n                { \"t\": \"lit\", \"lit\": { \"kind\": \"int\", \"value\": 2 } },\n                { \"t\": \"lit\", \"lit\": { \"kind\": \"int\", \"value\": 3 } }\n              ]\n            }\n          }\n        },\n        \"rhs\": {\n          \"t\": \"seq\",\n          \"lhs\": {\n            \"t\": \"do\",\n            \"op\": \"io/print_int\",\n            \"args\": [\n              {\n                \"t\": \"app\",\n                \"fn\": { \"t\": \"var\", \"name\": \"add_three\" },\n                \"args\": [\n                  { \"t\": \"lit\", \"lit\": { \"kind\": \"int\", \"value\": 10 } },\n                  { \"t\": \"lit\", \"lit\": { \"kind\": \"int\", \"value\": 20 } },\n                  { \"t\": \"lit\", \"lit\": { \"kind\": \"int\", \"value\": 30 } }\n              ]\n            }\n          },\n          \"rhs\": {\n            \"t\": \"do\",\n            \"op\": \"io/print_int\",\n            \"args\": [\n              {\n                \"t\": \"app\",\n                \"fn\": { \"t\": \"var\", \"name\": \"add_three\" },\n                \"args\": [\n                  { \"t\": \"lit\", \"lit\": { \"kind\": \"int\", \"value\": 1 } },\n                  { \"t\": \"lit\", \"lit\": { \"kind\": \"int\", \"value\": 2 } },\n                  { \"t\": \"lit\": { \"kind\": \"int\", \"value\": 3 } }\n                ]\n              }\n            ]\n          }\n        }\n      }\n    }\n  ]\n}",
+  "usage": {
+    "completion_tokens": 835,
+    "prompt_tokens": 10306,
+    "total_tokens": 11141
+  }
+}

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/json/t1_add_three/turn_3_check_stderr.txt

@@ -0,0 +1 @@
+parsing JSON in /tmp/cma2-run-3tQmlG/prog.ail.json

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/json/t1_add_three/turn_3_program.ail.json

@@ -0,0 +1,83 @@
+{
+  "schema": "ailang/v0",
+  "name": "t1_add_three",
+  "imports": [],
+  "defs": [
+    {
+      "kind": "fn",
+      "name": "add_three",
+      "doc": "Add three Ints.",
+      "type": {
+        "k": "fn",
+        "params": [
+          { "k": "con", "name": "Int" },
+          { "k": "con", "name": "Int" },
+          { "k": "con", "name": "Int" }
+        ],
+        "ret": { "k": "con", "name": "Int" },
+        "effects": []
+      },
+      "params": ["a", "b", "c"],
+      "body": {
+        "t": "app",
+        "fn": { "t": "var", "name": "+" },
+        "args": [
+          {
+            "t": "app",
+            "fn": { "t": "var", "name": "+" },
+            "args": [
+              { "t": "var", "name": "a" },
+              { "t": "var", "name": "b" }
+            ]
+          },
+          { "t": "var", "name": "c" }
+        ]
+      }
+    },
+    {
+      "kind": "fn",
+      "name": "main",
+      "doc": "Print add_three(1, 2, 3) and add_three(10, 20, 30) on separate lines.",
+      "type": {
+        "k": "fn",
+        "params": [],
+        "ret": { "k": "con", "name": "Unit" },
+        "effects": ["IO"]
+      },
+      "params": [],
+      "body": {
+        "t": "seq",
+        "lhs": {
+          "t": "do",
+          "op": "io/print_int",
+          "args": [
+            {
+              "t": "app",
+              "fn": { "t": "var", "name": "add_three" },
+              "args": [
+                { "t": "lit", "lit": { "kind": "int", "value": 1 } },
+                { "t": "lit", "lit": { "kind": "int", "value": 2 } },
+                { "t": "lit", "lit": { "kind": "int", "value": 3 } }
+              ]
+            }
+          }
+        },
+        "rhs": {
+          "t": "do",
+          "op": "io/print_int",
+          "args": [
+            {
+              "t": "app",
+              "fn": { "t": "var", "name": "add_three" },
+              "args": [
+                { "t": "lit", "lit": { "kind": "int", "value": 10 } },
+                { "t": "lit", "lit": { "kind": "int", "value": 20 } },
+                { "t": "lit", "lit": { "kind": "int", "value": 30 } }
+              ]
+            }
+          ]
+        }
+      }
+    }
+  ]
+}

experiments/2026-05-12-cross-model-authoring/runs/2026-05-12-080864/per_cohort/json/t1_add_three/turn_3_response.json

@@ -0,0 +1,8 @@
+{
+  "content": "{\n  \"schema\": \"ailang/v0\",\n  \"name\": \"t1_add_three\",\n  \"imports\": [],\n  \"defs\": [\n    {\n      \"kind\": \"fn\",\n      \"name\": \"add_three\",\n      \"doc\": \"Add three Ints.\",\n      \"type\": {\n        \"k\": \"fn\",\n        \"params\": [\n          { \"k\": \"con\", \"name\": \"Int\" },\n          { \"k\": \"con\", \"name\": \"Int\" },\n          { \"k\": \"con\", \"name\": \"Int\" }\n        ],\n        \"ret\": { \"k\": \"con\", \"name\": \"Int\" },\n        \"effects\": []\n      },\n      \"params\": [\"a\", \"b\", \"c\"],\n      \"body\": {\n        \"t\": \"app\",\n        \"fn\": { \"t\": \"var\", \"name\": \"+\" },\n        \"args\": [\n          {\n            \"t\": \"app\",\n            \"fn\": { \"t\": \"var\", \"name\": \"+\" },\n            \"args\": [\n              { \"t\": \"var\", \"name\": \"a\" },\n              { \"t\": \"var\", \"name\": \"b\" }\n            ]\n          },\n          { \"t\": \"var\", \"name\": \"c\" }\n        ]\n      }\n    },\n    {\n      \"kind\": \"fn\",\n      \"name\": \"main\",\n      \"doc\": \"Print add_three(1, 2, 3) and add_three(10, 20, 30) on separate lines.\",\n      \"type\": {\n        \"k\": \"fn\",\n        \"params\": [],\n        \"ret\": { \"k\": \"con\", \"name\": \"Unit\" },\n        \"effects\": [\"IO\"]\n      },\n      \"params\": [],\n      \"body\": {\n        \"t\": \"seq\",\n        \"lhs\": {\n          \"t\": \"do\",\n          \"op\": \"io/print_int\",\n          \"args\": [\n            {\n              \"t\": \"app\",\n              \"fn\": { \"t\": \"var\", \"name\": \"add_three\" },\n              \"args\": [\n                { \"t\": \"lit\", \"lit\": { \"kind\": \"int\", \"value\": 1 } },\n                { \"t\": \"lit\", \"lit\": { \"kind\": \"int\", \"value\": 2 } },\n                { \"t\": \"lit\", \"lit\": { \"kind\": \"int\", \"value\": 3 } }\n              ]\n            }\n          }\n        },\n        \"rhs\": {\n          \"t\": \"do\",\n          \"op\": \"io/print_int\",\n          \"args\": [\n            {\n              \"t\": \"app\",\n              \"fn\": { \"t\": \"var\", \"name\": \"add_three\" },\n              \"args\": [\n                { \"t\": \"lit\", \"lit\": { \"kind\": \"int\", \"value\": 10 } },\n                { \"t\": \"lit\", \"lit\": { \"kind\": \"int\", \"value\": 20 } },\n                { \"t\": \"lit\", \"lit\": { \"kind\": \"int\", \"value\": 30 } }\n              ]\n            }\n          ]\n        }\n      }\n    }\n  ]\n}",
+  "usage": {
+    "completion_tokens": 686,
+    "prompt_tokens": 11181,
+    "total_tokens": 11867
+  }
+}