english_mapping |
− Attach exactly one marker to a status word (a lifecycle or verdict word such as timed_out, confirmed, closed, deprecated, passed) in a report about an identified subject. `S on-record(E)` means: the status S is stated by the record E; E was written when S came to be, can be fetched and read by anyone with access to it, and S does not change unless a later record changes it. `S derived-at-read(R)` means: S was produced when this message was composed, by applying the rule R to other records; no record states S. Re-evaluating R over the same records reproduces S; a change to R, or to the records it reads, changes S without any new record being written, and the message's S is therefore only as current as its composition time. R must resolve to the rule as it stood when S was produced (a version, a hash, a dated document); E must resolve to the record itself, not to a document that mentions it. Neither marker says that S is true, that E is honest, or that R is a good rule; both say only how S was produced. An unmarked status word says nothing about its production. Round-trip: 'S, as stated by record E' / 'S, as computed when this was read by applying rule R; no record states it'.
+ Attach exactly one marker to a status word (a lifecycle or verdict word such as timed_out, confirmed, closed, deprecated, passed) in a report about an identified subject. A field served empty is marked on the word that states the emptiness (`search-empty(S): P`, `predicate-empty(S): P`); an empty field with no such word has nothing to carry a marker and says nothing about its production. In this mapping a record is an entry written when something happened, which states it, can be fetched by a locator, and is not overwritten by a later computation; a stored field that a later run may overwrite is a cache, not a record. `S on-record(E)` means: the status S is stated by the record E; E was written when S came to be, can be fetched and read by anyone with access to it, and S does not change unless a later record changes it. `S derived-at-read(R)` means: S is the output of a computation that applied the rule R to other records; no record states S. The marker identifies the computation that produced the reported value. Unpinned, that computation ran when this message was composed. A value that is cached, stored or relayed without running R again reports the earlier computation, claims no new one, and carries `as_of(t)` with the time that computation ran. Reproducing S needs the same version of R and the complete inputs it used, the time included if R reads the clock. A change to R, or to what it reads, yields a different S with no new record written, and leaves what the earlier computation reported unchanged. A marked status reports what was stated or computed at its time; it does not say S is still current. A later record can contradict an on-record status; nothing rescinds a derived one: it stops being what R would say, without notice, so whoever holds it holds the duty to re-derive it. R must resolve to the rule as it stood when S was produced (a version, a hash, a dated document); E must resolve to the record itself, not to a document that mentions it. A derived status written back into a stored field is still derived-at-read, because that field is a cache. It is on-record only when the write is itself a record, naming R and the time R ran, and E is that record. Neither marker says that S is true, that E is honest, or that R is a good rule; both say only how S was produced. An unmarked status word says nothing about its production. Two statuses that disagree about one subject are written as two marked statements; there is no third marker for the disagreement, which a reader finds by comparing them. Round-trip: 'S, as stated by record E' / 'S, as computed by applying rule R, when this was written unless a time is given; no record states it'.
|
predicted_measurement |
− PRIMARY: a preregistered paired comprehension panel over scenarios with determinate ground truth (a scenario ledger states, per item, whether a record stating the status exists and whether the status can change with no new record), comparing each marked form against its full careful-English mapping under the complete-careful-english-v1 comparator. Two settlement strata, on-record and derived-at-read, never pooled. Probes with five fixed options including 'Cannot determine': (a) is there a record you can fetch that states this status; (b) if the rule changed tomorrow and no new record were written, could the status differ; (c) what must you cite so a stranger reproduces the status, a record locator or a rule plus the records it reads. Planted calibration items under the headroom-relative-v1 gate. PREDICTION: comprehension delta versus careful English between -10 and +5 percentage points on each stratum; the marker's descriptive content (record, derived, read) is expected to survive and the consequence in probe (b) is expected to be partly lost on the derived-at-read stratum. REFUTED if either stratum's interval lies wholly below -10 points against the careful-English arm. My three most recent comprehension originals all missed on the adverse side, so the adverse side here is the one to widen, not the favourable one. SECONDARY: token_delta over 32 prospectively authored complete status statements, 16 per stratum, registered form minus the shortest complete careful-English statement carrying the same production fact and reference. PREDICTION: derived-at-read stratum between -12 and -6 tokens, on-record stratum between -2 and +2, headline (maximum tokenizer mean over both strata) between -7 and -2. REFUTED if the headline is at or above 0. Not claimed: that readers act differently on marked statuses, that on-record records are honest, or that adoption follows.
+ PRIMARY: a preregistered paired comprehension panel over scenarios with determinate ground truth (a scenario ledger states, per item, whether a record stating the status exists and whether the status can change with no new record), comparing each marked form against its full careful-English mapping under the complete-careful-english-v1 comparator. Two settlement strata, on-record and derived-at-read, never pooled. Probes with five fixed options including 'Cannot determine': (a) is there a record you can fetch that states this status; (b) if the rule changed tomorrow and no new record were written, could the status differ; (c) what must you cite so a stranger reproduces the status, a record locator or a rule plus the records it reads. Planted calibration items under the headroom-relative-v1 gate. PREDICTION: comprehension delta versus careful English between -10 and +5 percentage points on each stratum; the marker's descriptive content (record, derived, read) is expected to survive and the consequence in probe (b) is expected to be partly lost on the derived-at-read stratum. REFUTED if either stratum's interval lies wholly below -10 points against the careful-English arm. My three most recent comprehension originals all missed on the adverse side, so the adverse side here is the one to widen, not the favourable one. SECONDARY: token_delta over 32 prospectively authored complete status statements, 16 per stratum, registered form minus the shortest complete careful-English statement carrying the same production fact and reference. PREDICTION: derived-at-read stratum between -12 and -6 tokens, on-record stratum between -2 and +2, headline, the least favourable value (maximum tokenizer mean over both strata), between -2 and +2, because the on-record stratum controls it. The declared prerequisite is at most 0, so this forecast puts the prerequisite at risk on the on-record stratum and says so. REFUTED if the headline is above 0. The equal-weight mean of the two strata, expected between -7 and -2, is a diagnostic and settles nothing. Not claimed: that readers act differently on marked statuses, that on-record records are honest, or that adoption follows.
|
slot |
− {"on-record(<event-ref>)":"the status is stated by the named record, written when the status came to be; fetchable; unchanged unless a later record changes it","derived-at-read(<rule-ref>)":"the status was produced at composition time by applying the named rule to other records; no record states it; a change to the rule or to what it reads changes the status with no new record"}
+ {"on-record(<event-ref>)":"the status is stated by the named record, written when the status came to be; fetchable; unchanged unless a later record changes it","derived-at-read(<rule-ref>)":"output of a computation applying the named rule to other records, run at composition time unless as_of gives its time; no record states it; it changes with the rule or its inputs, with no new record"}
|
