Manuscript revision and pending experiment work, snapshot before restructuring

Clarity pass over the main text (36-item audit), Discussion rewrite and cut,
acknowledgements, Souly et al. as ref 62, lettered SI panels, model section
moved under Results; plus the untracked curriculum/society/compose/smol
configs, runners, figures, stats and tests that the SI already cites.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Y64o8FKP7rCuXzC48pxpMm

tests/test_llm_compose.py

@@ -0,0 +1,110 @@
+"""Tests for the composition experiment's pure pieces and its execution verifier (prereg v3 §7)."""
+
+import numpy as np
+import pytest
+
+from llm.compose import predicted_composition, score_composed, score_gsm8k, union_exceedance
+from llm.compose_data import ProgTask
+from llm.execute import ExecResult, extract_code, numeric_match, run_solution, verify_program
+from llm.tasks import Task
+
+
+# ---------------------------------------------------------------- execution verifier
+
+
+def test_executes_and_matches_reference():
+    ok, res = verify_program("```python\ndef solution():\n    return 6*7\n```", 42.0)
+    assert ok and res.ok and res.value == 42.0 and res.status == "ok"
+
+
+def test_rejects_wrong_answer_but_still_ran():
+    ok, res = verify_program("def solution():\n    return 41", 42.0)
+    assert not ok and res.ok and res.value == 41.0
+
+
+@pytest.mark.parametrize("code,status", [
+    ("def solution():\n    while True: pass", "timeout"),
+    ("def solution():\n    return len([0]*10**9)", "memory"),
+    ("x = 1", "no_solution"),
+    ("def solution(:\n  return 1", "error:SyntaxError"),
+    ("def solution():\n    return solution()", "recursion"),
+    ("", "no_code"),
+])
+def test_hazards_are_contained(code, status):
+    assert run_solution(code, timeout_s=8.0).status == status
+
+
+def test_sandbox_blocks_writes_outside_jail_and_network():
+    assert run_solution(
+        "def solution():\n    open('/tmp/_llm_compose_escape','w').write('x'); return 1"
+    ).status == "error:PermissionError"
+    assert run_solution(
+        "import socket\ndef solution():\n    socket.socket().connect(('1.1.1.1',80)); return 1"
+    ).status == "error:PermissionError"
+    import os
+    assert not os.path.exists("/tmp/_llm_compose_escape")
+
+
+def test_sandbox_allows_writes_inside_its_own_jail():
+    # scratch files are fine — the jail is a fresh temp dir destroyed after the run
+    assert run_solution("def solution():\n    open('s.txt','w').write('x'); return 1").ok
+
+
+def test_extract_code_prefers_last_fence_and_drops_prose():
+    got = extract_code("Sure:\n```python\ndef solution():\n    return 1\n```\nHope that helps!")
+    assert got == "def solution():\n    return 1"
+    assert extract_code("def solution():\n    return 2") == "def solution():\n    return 2"
+
+
+def test_numeric_match_tolerances():
+    assert numeric_match(1e6, 1e6 + 1)            # relative tolerance
+    assert numeric_match(0.0, 0.0)
+    assert not numeric_match(None, 1.0)
+    assert not numeric_match(1.0, 2.0)
+
+
+def test_execution_is_deterministic():
+    code = "def solution():\n    return sum(range(1000))"
+    assert len({run_solution(code).value for _ in range(3)}) == 1
+
+
+# ---------------------------------------------------------------- scoring and the prediction
+
+
+def test_score_composed_counts_correct_and_executable_separately():
+    tasks = [ProgTask("p", 42.0, 0), ProgTask("p", 42.0, 1), ProgTask("p", 42.0, 2)]
+    comps = ["def solution():\n    return 42",      # correct
+             "def solution():\n    return 7",       # ran, wrong
+             "def solution(:\n"]                    # did not run
+    acc, ok, ran = score_composed(comps, tasks)
+    assert acc == pytest.approx(1 / 3) and ok.tolist() == [True, False, False]
+    assert ran == pytest.approx(2 / 3)
+
+
+def test_score_gsm8k_reads_after_the_hash_marker():
+    tasks = [Task("math", "p", "18"), Task("math", "p", "7")]
+    assert score_gsm8k(["reasoning blah\n#### 18", "the answer is 9"], tasks) == pytest.approx(0.5)
+
+
+def test_union_exceedance_is_solved_by_merge_and_no_parent():
+    merged = np.array([True, True, True, False])
+    pa = np.array([True, False, False, False])
+    pb = np.array([False, True, False, True])
+    assert union_exceedance(merged, [pa, pb]) == pytest.approx(0.25)   # only item 2
+    assert union_exceedance(merged, [merged]) == 0.0
+
+
+def test_predicted_composition_is_anchored_at_generation_zero():
+    q_m = np.array([0.9, 0.8, 0.7]); q_c = np.array([0.9, 0.85, 0.8])
+    rho = np.array([0.2, 0.4, 0.6])
+    pred = predicted_composition(q_m, q_c, rho, observed0=0.30)
+    assert pred[0] == pytest.approx(0.30)                     # one free scale, fixed at t=0
+    assert pred[1] > pred[2]                                  # decays with q and rho
+    # decays faster than either parent alone: product form plus the decorrelation term
+    assert pred[2] / pred[0] < min(q_m[2] / q_m[0], q_c[2] / q_c[0])
+
+
+def test_predicted_composition_handles_degenerate_start():
+    pred = predicted_composition(np.array([0.0, 0.0]), np.array([0.0, 0.0]),
+                                 np.array([0.0, 0.0]), observed0=0.0)
+    assert np.all(np.isfinite(pred))