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 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.
+ OPERATIVE ENGLISH EXPANSIONS (declared here before any study; the explanatory paragraphs below are not additional per-item stimulus text):
each-group(<G>): <C>
expands to exactly:
In every group in <G>, considered separately: <C>
groups-combined(<G>): <C>
expands to exactly:
For the observations from <G> combined: <C>
Replace only the named parameters G and C with their identical literal bindings in the marked and English messages. G is the concrete versioned group-set reference, corresponding to <group-set-ref> in the form field. C is the same complete declarative clause, corresponding to <CLAUSE>, including any terminal punctuation. The fixed prefix, spacing and colon above are part of the prescribed expansion; an experimenter may not substitute another paraphrase or select a shorter English rendering after inspecting outcomes.
The shared context must resolve G and identify one applicable analysis method M: the predicate and threshold, observation/comparison window, included population, denominator/domain rules, aggregation, weighting and any overlap/deduplication rules. M is an explicitly named shared-context binding, not an extra surface argument and not wording added only to the English arm. It applies to C at the indicated scope in either rendering. Both full messages carry the same context and references. An unresolved or multiply interpretable method remains under-specified in BOTH forms; neither the marker nor its English expansion repairs it. The examples are exposed illustrations, never held-out bank items.
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.
Logical-consequence boundary: the markers distinguish the directly asserted scope; they do not forbid further conclusions entailed by the shared context. With a common strict threshold and positive denominators, every group rate below that threshold entails the pooled total-events/total-observations rate below it. For a resolved singleton group set under that rule, the combined rate is the sole member rate. Conversely, a combined rate below threshold over multiple groups need not put each member below it. These are consequences of the specified arithmetic/domain, not universal laws for arbitrary predicates or weighting. Key a consequence from the entire licensed context, never from a context-free table that assigns unknown to all cross-scope questions.
|
predicted_measurement |
− 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.
+ 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: the applicable operative English template declared in this revision's english_mapping, instantiated only with its named G and C bindings. The English arm is therefore the declared mapping itself, not a study-authored paraphrase. The exact prescribed prefixes are 'In every group in <G>, considered separately: <C>' and 'For the observations from <G> combined: <C>'. Both complete messages have identical shared context resolving G, method M, predicate, population and observation window. No glossary or extra method/reference wording is added to only one arm. The five-point prediction is specifically against THESE templates; an alternative English comparator requires a prospective revision, not experimenter discretion. The pending comparator-class proposal is not operative and bare ambiguous English is not the carrier.
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 directly asserted scope AND context-licensed consequences separately: equal magnitudes do not follow from each-group, and a combined claim does not itself assert a member result or a failing member. However, common-threshold positive-denominator arithmetic can entail pooled success from each-group, and a resolved singleton can entail its member result from groups-combined. These must not receive generic unknown golds. Action questions require an explicit shared decision policy; an observation log is usable only if its relevant coverage/completeness is specified. The official held-out question rule still applies: answer vocabulary appears in neither stimulus arm, and a scope-label paraphrase is not a held-out consequence.
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.
PREPARATION STOP (prospective revision 4): declaring the templates resolves the row-versus-design comparator mismatch, not the remaining study design. No runnable bank, reader qualification, fixed allocation, power result or authorised spend is supplied by this amendment. The 192-world minimum is not a precision guarantee. Before mint, independently review the exact full bank, context-sensitive keys, separately frozen expected observation roster, full-render reuse/dependence audit, sampling/weighting/resampling units, fixed readers and budget/stopping rules against the COMPLETE acceptance event (at least +5pp for each form and a positive lower interval). Exposed preparation fixtures and predecessor inputs cannot be reused as fresh scientific items. Preserve every null/adverse outcome; do not enlarge or retune after target exposure. A transparent insufficient-precision or design refusal is preferable to an uninterpretable run. All previous versions, seconds and evidence remain historical; no previous evidence is claimed to carry.
|
