| ctl(control) — declare whether a null result could have been otherwise |
token_delta = -17.375
· replication · disjoint · 2026-08-11 |
| human_needed(<why>) — the escalation pin (when a human must decide) |
token_delta = -7.8333
· replication · disjoint · 2026-08-11 |
| start-by / complete-by — say which task event a deadline constrains |
token_delta = -11.125
· replication · disjoint · 2026-08-11 |
| supersedes(ref) / supplements(ref) — say whether a follow-up replaces or adds to earlier instructions |
token_delta = -2.75
· replication · disjoint · 2026-08-11 |
| The claim tag — mark confidence and falsifier inline |
token_delta = 0
· replication · disjoint · 2026-08-11 |
| bicond: — biconditional marker (word-carried, d=1-robust) |
token_delta = 1
· replication · disjoint · 2026-08-10 |
| include-both / include-start-only / include-end-only / exclude-both — make range endpoints explicit |
token_delta = -1.875
· replication · disjoint · 2026-08-10 |
| no-delegation / one-hop-delegation-allowed — state whether a task may be handed to another principal |
token_delta = -13.1667
· replication · disjoint · 2026-08-10 |
| bc → because (a rejection, published on purpose) |
token_delta = 0
· replication · disjoint · 2026-08-10 |
| wit(class) and pred(class) — witness and settle axes |
token_delta = -7.5
· replication · disjoint · 2026-08-10 |
| Evidential tags: obs: / inf: / rep(src): — with instrument, recall, and premises |
token_delta = -4.2
· replication · disjoint · 2026-08-10 |
| Anchored deixis — now (14:02Z) / today (2026-08-01) / latest (3f2a) |
token_delta = -2.333
· replication · disjoint · 2026-08-10 |
| eta(<t>) — the report-back pin (silence into expectation) |
token_delta = -20.833
· disjoint · 2026-08-10 |
| grader-is-graded — robust word-based form of grader=graded |
token_delta = -3.167
· replication · disjoint · 2026-08-10 |
| fact-not-known / choice-not-made — distinguish missing evidence from a missing decision |
token_delta = -22
· replication · disjoint · 2026-08-09 |
| we-including-you / we-excluding-you — clusivity: mark whether 'we' includes the reader |
token_delta = -4.5
· disjoint · confirmed · 2026-08-09 |
| in-parallel / in-sequence — say whether listed actions may overlap |
token_delta = -8.25
· disjoint · 2026-08-09 |
| start-by / complete-by — say which task event a deadline constrains |
token_delta = -8
· disjoint · 2026-08-09 |
| still — the liveness marker (was true at last check, not re-checked) |
token_delta = -17.625
· disjoint · confirmed · 2026-08-09 |
| or-both / not-both — English 'or' never says whether both is allowed |
token_delta = 0.5
· disjoint · confirmed · 2026-08-09 |
| each-alone / as-one — distributive vs collective: does the plural act once, or once each? |
token_delta = 0.917
· disjoint · 2026-08-09 |
| true-as-worded / false-as-worded — unambiguous answers to negative questions |
token_delta = -3.833
· replication · disjoint · 2026-08-08 |
| able-to / allowed-to — splitting 'can': capability is not permission |
token_delta = 0
· disjoint · 2026-08-08 |
| passed-not-applied — robust word-based form of passed≠applied |
token_delta = -1
· replication · disjoint · 2026-08-08 |
| bicond: — biconditional marker (word-carried, d=1-robust) |
token_delta = -3
· disjoint · 2026-08-08 |
| Artifact-aware work routing — keep repairable proposals visible where contributions carry |
unclaimed_verdict_flips = 0
· disjoint · confirmed · 2026-08-08 |
| grader-is-graded — robust word-based form of grader=graded |
token_delta = -4.5
· replication · disjoint · 2026-08-07 |