The Second Reader or the Second Call? Matched Call Baselines for Agreement Routing, Validation and Recovery

When a second or third model call improves a verdict, is it because a different reader looked, or only because another call was made, once every composition is compared with the same reader resampled, the same reader validating itself, and one call with room to argue each verdict, at the same number of calls?

Round 52 takes the matched call baseline question from the roadmap and the Round 51 handoff. Track R replays all 36 Round 49 packets verbatim with the Round 49 prompt and labels, which is also the direct replication of the Round 49 near misses. Track N adds 16 authored raw table claims with thresholds within 2 percent of the correct total and declared missing rows. Track S adds 24 real SEC merger agreement exhibits, none used before, with one termination fee claim each. Structurally, unanimity, recovery and majority have 4, 20 and 28 unsafe states of 81, strictly nested, and every unsafe recovery state needs two reads sharing the wrong verdict. Live, Witness D reproduced its Round 49 verdicts on 36 of 36 items, including a wrong FAIL on all 9 near misses, and a second or third call from the same reader changed nothing: two resamples and a self validation gave the same FAIL on 9 of 9, and self validation changed none of 75 reads. At two calls, routing Witnesses C and D released 6 unsafe verdicts against 5 for Witness C routed with its own resample, so a second reader did not beat a second call from the better of the two. Witness C as validator moved 2 of 7 wrong Witness D reads to HOLD and turned one correct HOLD into PASS. Recovery released 5 unsafe verdicts against 0 for three reader unanimity. One Witness D call with room to argue each verdict moved 5 near miss FAILs to HOLD and released 2 unsafe verdicts on 69 usable items. Witness B alone released none, and no reader made a decisive error on the table or SEC tracks, so all separation comes from the replicated packets.

• F52.S1 (deterministic, E52-A): Over 81 states of gold and three verdicts, unanimity, recovery and majority are unsafe in 4, 20 and 28 states, strictly nested, and every unsafe recovery state needs two reads sharing the same wrong decisive verdict.
• F52.S2 (deterministic, E52-A): All 36 track R prompts are identical to Round 49; all 16 table claims and their exclusion traps and two world completions recompute; all 24 SEC windows contain their definition sentence.
• F52.E1 (live, E52-B): Witness D reproduced its Round 49 verdicts on 36 of 36 items, including a wrong FAIL on 9 of 9 near miss items.
• F52.E2 (live, E52-B and E52-C): Two Witness D resamples and a Witness D self validation gave the same wrong FAIL on 9 of 9 near miss items; self validation changed none of 75 reads.
• F52.E3 (live, E52-B): At two calls, routing Witnesses C and D released 6 unsafe verdicts, routing Witness C with its own resample 5, and routing Witness D with its own resample 9.
• F52.E4 (live, E52-B): One Witness D call with room to argue each verdict released 2 unsafe verdicts on 69 usable items, moving 5 near miss FAILs to HOLD; seven of its outputs were empty.
• F52.E5 (live, E52-C): Witness C as validator moved 2 of 7 wrong Witness D reads to HOLD and turned one correct HOLD into PASS; recovery released 5 unsafe verdicts against 0 for three reader unanimity.
• F52.E6 (live): Witness B alone released no unsafe verdict, with 2 false holds; no reader made a decisive error on the 16 table claims or the 24 SEC claims, and Witness A's blind audit agreed with all 40 of their labels.

• E52-A Structural diagnostic for unanimity, majority, routing and recovery, with replay and gold certificates Complete
• E52-B Independent, resampled, deliberate and procedure card reads at matched call counts Complete
• E52-C Cross validation, self validation and recovery against matched call baselines Complete

• H52.1 Over all 81 states of gold and three verdicts, the unsafe states of three reader unanimity are a strict subset of those of recovery, which are a strict subset of those of majority, and every unsafe recovery state has two reads sharing the same wrong decisive verdict.
• H52.2 With the identical Round 49 prompt and packets, Witness D's single read is decisive on at least 5 of the 9 Round 49 near miss items.
• H52.3 At two calls, routing Witnesses C and D has fewer unsafe outcomes than routing either reader with its own resample, pooled over all items.
• H52.4 Routing Witnesses C and D does not dominate routing the better of the two readers with its own resample: it pays at least as many false holds.
• H52.5 One Witness D call with twice the output allowance and a counter case step has no more unsafe outcomes than Witness D's two call self routing.
• H52.6 At three calls, recovery (Witness D read, Witness C validation, Witness B adjudicator) has no more unsafe outcomes than three reader unanimity and fewer false holds.
• H52.7 Cross validation changes more of Witness D's wrong decisive reads to gold or HOLD than self validation.
• H52.8 Manipulation check: each of Witnesses B, C and D makes at least one decisive error on the replicated or table tracks, and at least one reader is decisive on at least one SEC payment claim.

Research diagnostic and output replay only. Arms are replays of recorded calls at matched call counts, not live orchestration; reader capability and resource per call are not matched. No production system, release gate, or Noetis behavior changed.

• Does a different reading procedure in one call beat a different reader at matched calls and matched output allowance on held out near miss structures outside Round 49?
• Which non-contract materials produce single reader errors, given that near threshold arithmetic and declared missing rows did not?

Builds on Round 51, Round 50, Round 49, Round 42, Round 40, Round 35. Continued in Round 54, Round 53.