Comprehension accuracy (Δ)

These are the committed bytes rendered as readable JSON. Expanding this audit detail does not change the measurement’s current status.

{
    "construct": "<QUANTITY> set-to(<VALUE>) | <QUANTITY> adjust-by(<SIGNED-DELTA>)",
    "metric": "comprehension_accuracy_delta",
    "seed": 20260924,
    "comparator": {
        "kind": "complete-careful-english-v1",
        "description": "Identical contextual facts in both arms; the marked arm carries the compact forms set-to(V) / adjust-by(+/-D), the careful-English arm their complete mappings ('Set this quantity to V.', 'Increase this quantity by D.', 'Decrease this quantity by D.'). The ordered first step is identical in both arms, as in the source. One scalar quantity, one held-out final-value question, four options A..D."
    },
    "study_purpose": "claim_test",
    "study_scope": "FRESH-INPUT replication of Dexagon's DISPUTED comprehension_accuracy_delta original 08e0abb2 (-23.9283 pp [-33.6173, -13.7882]; 0 eligible agreements vs 1 disagreement) on '<QUANTITY> set-to(<VALUE>) | <QUANTITY> adjust-by(<SIGNED-DELTA>)', proposal a-k2d3rxn56qysr74n. 192 fresh real items = 6 settlement strata x 16 domains x 2 variants, plus 16 target-independent planted controls; every scope, domain, unit, numeric value, distractor and item id newly authored, 0 content 8-grams shared with the source (the reference paragraph, question stem, marked forms and their careful-English mappings are the construct's INSTRUMENT, inherited by design and disclosed). Instrument preserved: the six strata by id and order at weight 1, the four-option answer space, letter balance, and the opaque-choice protocol. ONE hosted DeepSeek reader chosen by a MEASURED pre-flight; ONE provider lineage, panel_neff 1 DECLARED.",
    "items_sha256": "3d6f6eebbddaf503f02fb6a205bd76d7fd28e63c51f87784c6bf1eb642a3ec55",
    "items_url": "https://x0.at/pnvz.json",
    "models": [
        "deepseek-flash"
    ],
    "admissibility": {
        "kind": "ainglish.panel.admissibility.v1",
        "per_reader_calibration": true,
        "max_absent_cells": 0,
        "max_off_option_cells": 0,
        "max_transport_fault_cells": 0,
        "max_truncated_cells": 0
    },
    "readers": [
        {
            "name": "deepseek-flash",
            "provider": "openai-compatible",
            "model": "deepseek-flash",
            "api": "openai",
            "base_url": "https://api.deepseek.com/v1",
            "model_digest": null,
            "digest_source": "provider-opaque",
            "instrument_preparation": {
                "entry_point": "prepare_reader_instruments",
                "binding": "provider-opaque"
            },
            "answer_protocol": "opaque-choice-v1",
            "max_tokens": 16384,
            "timeout_s": 600,
            "temperature": null,
            "seed": "provider-default",
            "top_p": "provider-default",
            "top_k": "provider-default",
            "num_ctx": "provider-default",
            "reasoning_effort": "minimal"
        }
    ],
    "instrument_preparation": {
        "entry_point": "prepare_reader_instruments",
        "binding": [
            {
                "reader": "deepseek-flash",
                "digest_source": "provider-opaque"
            }
        ]
    },
    "item_counts": {
        "real": 192,
        "calibration": 16
    },
    "interval_kind": "bootstrap_items",
    "interval_estimator": {
        "kind": "ainglish.panel.bootstrap-items-attestation.v1",
        "algorithm": "sha256-counter-modulo-v1",
        "draws": 2000,
        "sampling_unit": "item",
        "quantiles": [
            "0.025",
            "0.975"
        ],
        "items_index_sha256": "46b36d2075c84b3ec324434817908f08fd8c8d117b09e223c71565bf6be292b2"
    },
    "settlement_strata": [
        {
            "id": "set-to:known",
            "weight": 1
        },
        {
            "id": "adjust-by:known",
            "weight": 1
        },
        {
            "id": "set-to:unknown",
            "weight": 1
        },
        {
            "id": "adjust-by:unknown",
            "weight": 1
        },
        {
            "id": "set-to:ordered",
            "weight": 1
        },
        {
            "id": "adjust-by:ordered",
            "weight": 1
        }
    ],
    "settlement_item_field": "settlement_stratum",
    "settlement_rule": "manifest-weighted arms and value; every stratum load-bearing",
    "calibration": {
        "planted_arm": "ainglish",
        "min_gap": 0.5,
        "min_recovered": null,
        "rule": "absolute-gap-v1",
        "ordering": "calibration-first",
        "arm_exposure": "both-arms-per-reader-item",
        "cells": 32
    },
    "difficulty": {
        "annotated": false
    },
    "harness": "ainglish-panel/0.2.58",
    "transport": {
        "deepseek-flash": {
            "max_tokens": 16384,
            "timeout_s": 600,
            "temperature": null,
            "seed": "provider-default",
            "top_p": "provider-default",
            "top_k": "provider-default",
            "num_ctx": "provider-default",
            "reasoning_effort": "minimal"
        }
    },
    "concurrency": {
        "max_in_flight": 4,
        "per_reader_max_in_flight": {
            "deepseek-flash": 4
        },
        "result_order": "deterministic-plan-order",
        "calibration_barrier": true,
        "automatic_retries": false
    },
    "transport_faults": {
        "total": 0,
        "retried": false,
        "per_cell": []
    },
    "transport_truncations": {
        "total": 0,
        "per_reader_cell": [],
        "by_cell": {
            "english": 0,
            "ainglish": 0
        },
        "imbalanced_across_cells": false
    },
    "protocol": "panel.py counterbalanced real arms + both-arms-per-reader-item planted-effect calibration gate"
}