english_mapping |
− Use one form when a claim about several groups would otherwise use a phrase such as `across all groups`, which can mean either that the claim holds separately in every group or that it holds only for the groups treated as one aggregate.
`each-group(<group-set-ref>): <CLAUSE>` asserts that `<CLAUSE>` evaluates true separately for every member group in the exact finite set resolved by `<group-set-ref>`. The same declared predicate, threshold, denominator rule, observation window, and analysis method are applied independently to each group. It does not assert that the clause is true after the groups are combined, that the effect size is equal across groups, that every group has equal weight or sample size, or that an omitted group is covered.
`groups-combined(<group-set-ref>): <CLAUSE>` asserts that `<CLAUSE>` evaluates true once on the combined observations associated with the referenced groups, using the explicitly declared aggregation, weighting, membership, deduplication, denominator, and time-window rules. It makes no claim either way about any member group separately. It does not imply that some group fails; the clause may happen to be true in every group, but this marker does not say so.
The group-set reference is load-bearing. It must resolve to the intended finite group set and the versioned data or population boundary. If memberships overlap, observations are missing, groups are weighted, or records may be counted more than once, the surrounding reference or analysis method must say how those cases are handled. Neither marker chooses the scientifically appropriate aggregation level, establishes causation, certifies data quality, or makes an under-specified statistic reproducible.
These forms type assertion scope, not actor coordination. They do not replace `each-alone / as-one`, which counts whether actors perform separate or joint action instances; `whole / part`, which marks set completeness; `some-or-all / some-but-not-all`, which marks quantity; or ordinary stratified tables that report every group's value. Use ordinary `in every group` or `for all groups combined` whenever those phrases are clearer. Bare `across all groups` remains legal when the two readings cannot change a receiver's action or an inherited specification has already fixed its meaning.
+ Use one form when a claim about several groups would otherwise use a phrase such as `across all groups`, which can mean either that the claim holds separately in every group or that it holds only for the groups treated as one aggregate.
`each-group(<group-set-ref>): <CLAUSE>` asserts that `<CLAUSE>` evaluates true separately for every member group in the exact finite nonempty set resolved by `<group-set-ref>`. The same declared predicate, threshold, denominator rule, observation window, and analysis method are applied independently to each group. It does not assert that the clause is true after the groups are combined, that the effect size is equal across groups, that every group has equal weight or sample size, or that an omitted group is covered.
`groups-combined(<group-set-ref>): <CLAUSE>` asserts that `<CLAUSE>` evaluates true once on the combined observations associated with the referenced groups, using the explicitly declared aggregation, weighting, membership, deduplication, denominator, and time-window rules. It makes no claim either way about any member group separately. It does not imply that some group fails; the clause may happen to be true in every group, but this marker does not say so.
The group-set reference is load-bearing. It must resolve to the intended finite nonempty group set and the versioned data or population boundary. If memberships overlap, observations are missing, groups are weighted, or records may be counted more than once, the surrounding reference or analysis method must say how those cases are handled. Neither marker chooses the scientifically appropriate aggregation level, establishes causation, certifies data quality, or makes an under-specified statistic reproducible.
These forms type assertion scope, not actor coordination. They do not replace `each-alone / as-one`, which counts whether actors perform separate or joint action instances; `whole / part`, which marks set completeness; `some-or-all / some-but-not-all`, which marks quantity; or ordinary stratified tables that report every group's value. Use ordinary `in every group` or `for all groups combined` whenever those phrases are clearer. Bare `across all groups` remains legal when the two readings cannot change a receiver's action or an inherited specification has already fixed its meaning.
Preconditions are explicit, not silently repaired. A resolved empty group set is INVALID for either marker; do not use vacuous truth to license an each-group claim. An unresolved reference is UNKNOWN, not empty. A nonempty set containing a zero-observation member remains that exact set: for a rate predicate requiring a positive denominator in every member, that member's predicate is UNDEFINED and each-group cannot assert it. Never drop that member to obtain a true universal. For groups-combined, evaluate the declared aggregate: an empty member need not make a pooled rate undefined if the combined denominator is positive and the declared inclusion rule permits it. A zero combined denominator is UNDEFINED. Other predicates use their declared domains; zero observations alone is not a universal ban on a predicate such as 'has zero observations'. These are validity/fidelity rules, distinct from which further conclusions a successfully asserted message licenses.
|
predicted_measurement |
− CLAIM CARRIER: before any reader sees scientific items, preregister at least 192 held-out, form-balanced scenarios: 96 `each-group` and 96 `groups-combined`. Cross rates, threshold comparisons, changes over time, model accuracy, job failure, latency, employment, approval, medical outcomes, sales, and allocation. Every scenario binds an exact group set, membership table, numerator/denominator rule, time window, and answer key. Include ordinary aligned cases, cases where both levels agree, and Simpson-reversal cases where the per-group and combined conclusions oppose one another. Report the two forms separately.
Compare three arms without pooling comparators: (1) context-balanced bare English using `across all <groups>`; (2) complete careful English using `in every named group, considered separately` or `after observations from the named groups are combined`; and (3) the matching Ainglish form. Bare items use the same surface across balanced hidden intentions, so a preferred default cannot score both. Ask held-out consequence questions that repeat none of the marker or mapping vocabulary: whether the report commits to the result for a named member, whether one member may show the opposite result without contradicting the message, and which action a downstream policy is licensed to take. Exact recovery of assertion scope plus group-set reference is primary.
Prediction: each marked form improves exact scope recovery by at least 20 percentage points over the balanced bare arm and is non-inferior to its complete careful-English mapping within 5 points. Require at least two independently qualified base-model lineages, immutable answer-bearing inputs, passed ordinary-English calibration, fixed reader editions, complete cell yield, zero transport truncations, and no retry after exposure. A supplied-reference learnability arm is descriptive and cannot substitute for the cold claim carrier.
REQUIRED HARD CELLS: a combined improvement while every member declines; a per-member improvement while the combined result declines; one small group opposing a large group; equal versus unequal group sizes; a rate whose denominator changes; overlapping membership; an omitted group; missing values; a group-set revision between reports; a pooled threshold pass with at least one member below threshold; equal signs but materially different effect sizes; and claims where neither form is licensed because the group set or aggregation rule is unresolved. Ask explicitly whether `each-group` entails equal magnitudes (no) and whether `groups-combined` entails that at least one group differs (no).
PRACTICAL COMPARATORS: `in every group`, `for all groups combined`, `per-group`, `pooled`, a stratified table, and a machine-readable aggregation field. The deterministic token prerequisite is a least-favourable mean token_delta no greater than +3 tokens versus the full careful-English mappings on fresh complete messages, with both forms and references retained. Report current cost honestly: today's tokenizers were trained on English and generally not on Ainglish, so a present premium does not settle future efficiency; it is still a real present cost and the fixed bound can veto this exact surface.
ROBUSTNESS AND FIDELITY: test hyphen loss, punctuation stripping, the declared one-edit neighbours, summary, translation, group-name substitution, and removal of nearby statistical cues. Hyphen loss should preserve direction as ordinary English but becomes nonconformant. Fidelity recomputes the stated clause at both levels from immutable tables; the selected marker is false when its own level does not satisfy the clause. Unresolved memberships, denominators, weighting, or time windows are UNKNOWN rather than guessed.
REFUTED IF context-balanced bare English is already at parity; either form-specific delta is non-positive; either marker trails complete careful English by more than 5 points; readers infer member-level truth from `groups-combined` or equal effects from `each-group`; the group reference is routinely ignored; ordinary comparators dominate in clarity and price; current token cost exceeds the declared bound; fidelity cannot be reproduced; or eligible post-ratification use remains zero.
+ PROSPECTIVE CLAIM UNDER THE CURRENT RULE: the fixed scope marker is hypothesised to improve recovery of the message's asserted statistical scope over equally informative concise careful English. Predict a gain of at least 5 percentage points for EACH form; an interval whose lower endpoint is not above zero does not support this claim. The rationale is consistent scope placement across different statistical predicates, not English being intrinsically deficient. This is a genuinely stronger, untested claim than the predecessor's preservation claim; if careful English ties or wins, do not seek admission for this surface on ambiguous-English gains alone.
GOVERNING COMPARATOR: complete-careful-english-v1, rendered concisely as 'in every group in <group-set-ref>, considered separately: <CLAUSE>' and 'for the observations from <group-set-ref> combined under <method-ref>: <CLAUSE>', or an independently reviewed shorter equally explicit rendering. Freeze the chosen complete messages before exposure. Both arms carry identical reference bindings, predicate, method, population and observation window. Do not append explanatory material to English while leaving it implicit for Ainglish. Practical alternatives 'in every group', 'per-group', 'pooled' and 'for all groups combined' must be reviewed before choosing the frozen comparator, not selected after results. No comparator-policy proposal is treated as operative.
DESIGN: preregister at least 192 genuinely fresh held-out scenarios, balanced 96 per form, across rates, threshold comparisons, changes, job failure, latency, accuracy, employment, approval and allocation. Freeze all answer-bearing inputs, golds, exact prompts, readers, dependency-family identifiers and analysis before any target call. Families that share one underlying world are clusters, not independent items; a reversed question on the same Simpson table is not a new world. Require two independently qualified base-model lineages and report reader-specific and form-specific results, ordinary-English calibration, complete yield, transport loss and all failed cells. Fix sample size and stopping before calls; insufficient planned precision stops preparation, not a post-result enlargement or retry. No inference is authorised by this prose design.
Separate two questions. FIDELITY recomputes the predicate from full immutable tables and checks valid/nonempty/resolved sets, denominator domains, weighting, time and member/aggregate truth. READER CONSEQUENCE asks what a valid message commits to, using common context that resolves references but does not reveal the outcome tables or the keyed consequence. Unasserted does not mean false. Ask whether a named member must meet the clause, whether a member can differ without contradicting an aggregate assertion, and which downstream action is licensed. Test the exact boundaries: each-group promises neither equal magnitudes nor pooled success; groups-combined promises neither member success nor a failing member.
HARD CELLS: aligned and opposing aggregation levels, combined improvement with every member declining, the reverse using separate independent worlds, unequal group sizes, changed denominators, missing/overlapping observations, a changed versioned set, omitted members, pooled threshold with a failing member, resolved empty set, unresolved reference, zero-observation member, zero aggregate denominator and predicates legitimately defined on zero observations. Semantic invalidity/unknown labels are separate from truth and from downstream entailment. The public arithmetic witnesses and all predecessor items are excluded from held-out evidence.
The balanced bare-English 'across all groups' comparison is a separately reported descriptive ambiguity arm. A 20-point improvement there does not satisfy the primary claim. Supplied-reference learnability and corruption/summary/translation robustness are separately scoped diagnostics, never substitutes for cold positive support against the governing complete comparator.
COST PREREQUISITE: unchanged least-favourable mean token_delta <= +3 on fresh complete messages with identical references in both arms. This bound permits a current cost; it is not evidence of benefit. Today's English-trained readers and tokenizers give English an exposure advantage, so present results do not establish an intrinsic post-training limit. Nevertheless null/adverse present results remain on record, and hoped-for future training does not count as current support.
NON-ADOPTION RULE: absent confirmed positive primary support, this revision is not ready for adoption. Failure of the 5-point per-form prediction, a non-positive primary interval, ignored group references, scope confusion, better practical English at lower cost, cost above +3, or unreproducible fidelity is a reason for a bounded revision/non-adoption decision, not serial banks until a favourable result. Preserve every null/adverse result and the current comprehension-loss veto. No weakening or future-policy bypass of the declared unbounded comprehension carrier is requested.
|
