From af0a56d45f31ea942ceea1b7bcbd8477a519f02a Mon Sep 17 00:00:00 2001 From: Weksa Date: Thu, 12 Nov 2026 21:40:39 +0000 Subject: [PATCH] ja-anger-mirror: ja-JP:3 gets hedge and affection bounds as en-US:3 carries (#62) --- README.md | 2 +- crates/weksa/tests/original_corpus.rs | 54 ++++++++++++++--------- data/ontology/ontology.cc | Bin 12323 -> 12438 bytes docs/targets/interlingua-lowering-map.md | 2 +- 4 files changed, 34 insertions(+), 24 deletions(-) diff --git a/README.md b/README.md index 31960d8..ff6eadd 100644 --- a/README.md +++ b/README.md @@ -95,7 +95,7 @@ addressee, and none for an above-status in-group addressee below intimacy 700 (` an in-group addressee at intimacy 700 or more, whatever the status). Two entries for the above-status cases were withdrawn: a paired measure found they made the lowerer match the reference register less often, and they stay out until a native reader attests them. -ja-JP `:5` (hedging), `:7` (affection) and `:8` (restrained sadness) carry certainty and restraint conditions, through `AtMostOrUnset` bounds (an unrated certainty or restraint does not defeat them), so the hedging, certainty, affection, restraint and sadness entries never co-select on the pairs `:5`/`:6`, `:4`/`:7`, `:6`/`:7` and `:6`/`:8`; the store has no retire, so that was a rebuild of `data/ontology/ontology.cc` with the ja-JP text unchanged. en-US `:3` (blunt anger) carries `AtMostOrUnset` hedge and affection bounds, and `:5` (hedging) and `:8` (affection) each an `AtMostOrUnset` certainty bound (as ja-JP `:7`), so `:3`/`:5`, `:3`/`:8`, `:5`/`:6` and `:6`/`:8` never co-select; `:5`'s certainty clause is that condition and no longer prose; `:6` and the Scene entry `:10` still co-select and are kept apart by scoping in the text. ja-JP `:9` (surprise) states its question ending as available, not prescribed, so `:6`/`:9`, `:5`/`:9` and `:3`/`:9` stay co-selectable and are reconciled by wording, not by condition. +ja-JP `:5` (hedging), `:7` (affection) and `:8` (restrained sadness) carry certainty and restraint conditions, through `AtMostOrUnset` bounds (an unrated certainty or restraint does not defeat them), so the hedging, certainty, affection, restraint and sadness entries never co-select on the pairs `:5`/`:6`, `:4`/`:7`, `:6`/`:7` and `:6`/`:8`; ja-JP `:3` (anger) carries `AtMostOrUnset` hedge and affection bounds, as en-US `:3`, so `:3`/`:5` and `:3`/`:7` never co-select; the store has no retire, so that was a rebuild of `data/ontology/ontology.cc` with the ja-JP text unchanged. en-US `:3` (blunt anger) carries `AtMostOrUnset` hedge and affection bounds, and `:5` (hedging) and `:8` (affection) each an `AtMostOrUnset` certainty bound (as ja-JP `:7`), so `:3`/`:5`, `:3`/`:8`, `:5`/`:6` and `:6`/`:8` never co-select; `:5`'s certainty clause is that condition and no longer prose; `:6` and the Scene entry `:10` still co-select and are kept apart by scoping in the text. ja-JP `:9` (surprise) states its question ending as available, not prescribed, so `:6`/`:9`, `:5`/`:9` and `:3`/`:9` stay co-selectable and are reconciled by wording, not by condition. For the first AquaSynth speech-training handoff, see [Tiny PanPhon v0.1 Speech Curriculum](./examples/speech-training/tiny-panphon-v0.1/README.md). diff --git a/crates/weksa/tests/original_corpus.rs b/crates/weksa/tests/original_corpus.rs index 6c73ed2..99e7e30 100644 --- a/crates/weksa/tests/original_corpus.rs +++ b/crates/weksa/tests/original_corpus.rs @@ -1031,36 +1031,46 @@ fn sweep_seed_pairs( } } -/// ja-JP seed entries :4 to :8 over the stance and discourse grades that bear on -/// them (hedge, certainty, sadness, affection, restraint): the pairs that gave -/// opposed instructions (hedge against certainty, particles, final force) never -/// hold together; and each of :5, :7, :8 still fires where it should (hedged at -/// certainty 700-799, affection with certainty or restraint unrated). +/// ja-JP seed entries :3 to :8 over the stance and discourse grades that bear on +/// them (anger, hedge, certainty, sadness, affection, restraint): the pairs that +/// gave opposed instructions (clipped anger against hedge or soft particles, +/// hedge against certainty, particles, final force) never hold together; and +/// each of :3, :5, :7, :8 still fires where it should (anger with hedge and +/// affection unrated or below 600, hedged at certainty 700-799, affection with +/// certainty or restraint unrated). #[test] fn ja_seed_pairs_never_co_select() { let (n, s) = (None, Some); sweep_seed_pairs( "ja-JP", - ["hedge", "certainty", "sadness", "affection", "restraint"], - &[(5, 6), (4, 7), (6, 7), (6, 8)], + ["anger", "hedge", "certainty", "sadness", "affection", "restraint"], + &[(5, 6), (4, 7), (6, 7), (6, 8), (3, 5), (3, 7)], &[ - (5, [s(600), n, n, n, n]), - (5, [s(700), s(799), n, n, n]), - (5, [s(700), n, n, n, n]), - (7, [n, s(799), n, s(700), s(599)]), - (7, [n, n, n, s(700), n]), - (7, [s(1000), s(0), s(1000), s(600), s(0)]), - (8, [n, s(799), s(700), n, s(700)]), - (8, [n, n, s(600), n, s(600)]), - (6, [n, s(800), n, n, n]), + (3, [s(700), n, n, n, n, s(300)]), + (3, [s(700), s(599), n, n, s(599), s(300)]), + (3, [s(1000), s(0), s(799), n, s(0), s(0)]), + (5, [n, s(600), n, n, n, n]), + (5, [n, s(700), s(799), n, n, n]), + (5, [n, s(700), n, n, n, n]), + (7, [n, n, s(799), n, s(700), s(599)]), + (7, [n, n, n, n, s(700), n]), + (7, [n, s(1000), s(0), s(1000), s(600), s(0)]), + (8, [n, n, s(799), s(700), n, s(700)]), + (8, [n, n, n, s(600), n, s(600)]), + (6, [n, n, s(800), n, n, n]), ], &[ - (8, [n, n, s(599), n, s(700)]), - (8, [n, n, n, n, s(700)]), - (5, [s(599), n, n, n, n]), - (7, [n, n, n, s(599), n]), - (7, [n, n, n, s(700), s(600)]), - (8, [n, n, s(600), n, s(599)]), + (3, [s(700), s(600), n, n, n, s(300)]), + (3, [s(700), n, n, n, s(600), s(300)]), + (3, [s(699), n, n, n, n, s(300)]), + (3, [s(700), n, n, n, n, s(301)]), + (3, [s(700), n, n, n, n, n]), + (8, [n, n, n, s(599), n, s(700)]), + (8, [n, n, n, n, n, s(700)]), + (5, [n, s(599), n, n, n, n]), + (7, [n, n, n, n, s(599), n]), + (7, [n, n, n, n, s(700), s(600)]), + (8, [n, n, n, s(600), n, s(599)]), ], ); } diff --git a/data/ontology/ontology.cc b/data/ontology/ontology.cc index c385a8c007c470d6a7a685c0e98e9ab6d64672f5..4cd355459606fe8a02c683e0c2e9e69c54f0c7d3 100644 GIT binary patch delta 353 zcmZ3SFfDO|I3ug6xs{Q@W*J5o7&Dd0jR`8cfh7>eWMk)nG8c<;!UScw6=1p?d8%Qe z2l@PAqM`z~V9YOq3t-Hd!bLEqfG9tc0N4ppM;R+-EKSYR4Go^$sAs!5M?4Lt=()4YQ_5h9Aakle+^`kggyD6YWs)WR!-Q%_K8pX;z}HR{%5Pa`&Rd+}y;XDU(0& zh)&Mok(w;6VmNs_PvK@?6-LI%=QLa=Pf%5bhQKb>B$&yH>f$hyZ8c+HqVu#q!I)EZ L;I1gsTgwOlwO?Jw delta 353 zcmbQ1xHw^hI3ugEk(H^@W*J5o7&Dd0jR`8cfh7>eWMk)nG8c<;!UScw6=1p?d8%Qe z2l@PAqM`z~V9YOq3t-Hd!bLEqfG9sqn~L~4nCNwhG8i*RN*bo1NCvL9P3{g%LArtr zOhJc|C!;jjKT$^+SI$_Pm8k0#z|6SZy(lp^H?e5a:`, `n` canonical decimal >= 1 (families: concept, frame, role, relation, speech_act, feature, referent_kind, extension); type `weksa.inventory_entry`, with a bounded gloss, value kind (option labels bounded), the slots a feature may sit in (`Discourse`, `Referent`, `Predication`, `Relation`; `Stance` from cut `speaker-state`, `Speaker` and `Scene` from cut `speaker-scene`), `introduced_rev` and optional `retired_rev`. Speaker axes, scene relations and affects are features of those slots, so the loop grows them like any closed-class family and convergence covers them | Added or retired by an inventory revision; never edited in place (a changed meaning is a retire plus an add); a retired id still resolves for packets of earlier revisions | The loop's accepted rounds, whose minting call the context builder assembles from Train items only; `weksa inventory admit` for one model-drafted `EditDraft` outside a run (cap 256, reviewed whole in its cut; same numbering and admission check as the loop); Self on merge to main. `data/original` revs 5 (233 concepts and frames) and 6 (five concepts closing named gaps) were drafted by claude-sonnet-5-5 (Weksa Hands, model-drafted original-bed lexicon from Train and Validation passages); Validation-informed: numbers on this bed measure lowering, never generalization or convergence. Residue after rev 6, not amended (each fresh coverage reader names new gaps; the loop's growth path owns them): simultaneity (ながら), distal deixis (あの), 'first' (まず), counterfactual mood, 'at least', emphatic question; heaven versus sky for the visible 天 stays weak. Admission checks form, not text | | Inventory revision | Key `rev:`, type `weksa.inventory_revision`, with parent, change list and `frozen` | Appended per accepted round; exactly one revision is ever marked frozen, by the convergence test | The loop's accept rule appends; the convergence test freezes; Self records the freeze as a ruling | | Target profile | Locale or language-project id (`en-US`, `ja-JP`, a conlang's slug). Until entries grow in rounds there is no profile revision document: a run names the profile it lowered with by the ontology store's path and digest in its `RunRecord` (cut `language-ontology`); `profile::` revision documents arrive with follow-up `language-ontology-growth` | The ontology store is revised by commit; a run pins it and refuses drift; it likewise pins the speaker-state store (`RunRecord` keys 17 and 18, `Drift(SpeakerState)`, cut `language-ontology-scene`) | Profile authors and accepted rounds; never the lowerer's defaults (`persona-drives-register`) | -| Language ontology entry (cut `language-ontology`) | Key `onto::`, `n` from 1 per language; type `weksa.ontology_entry` in `data/ontology/ontology.cc`: the language, the revision of the inventory it was admitted through (provenance: beds number revisions independently and a run reads each condition's feature at its own head), a layer (lexicon, grammar, discourse, phonology, orthography), at most four conditions (a feature id of slot `Stance`, `Discourse` or `Scene` with `AtLeast`/`AtMost`/`AtMostOrUnset` a grade or `Is` an option or flag; a `Scene` condition reads the relation of the item's speaker to its addressee that `with_scene` selected; slot `Speaker` and community ids wait on follow-up `language-ontology-communities`), a choice of 1 to 200 bytes, at most three examples of 1 to 120 bytes, and an `Annotator`. Whether an entry's text keeps politeness on the scene is a model reader's judgment, owed per change (a mint owes it under `language-ontology-growth`), not a test | Admitted in all-or-nothing batches through `OntologyStore::admit`, immutable, never edited; retire arrives with `language-ontology-growth`. The run pins the store like the entity store (path and digest, `Drift(Ontology)`), never copies it, because no loop step writes it yet. Cut `language-ontology-seed` converts by drafting, not by parse: a fresh model drafts each language's seed from that language's YAML and the inventory's feature lines with no corpus text, then deletes `data/target-language-ontology/` and `.weksa/cultural-ontology/` in the same cut | Seed: a labelled model (`Annotator::Model`), no operator gate, never Test evidence (`ja-ontology-owner-answer`); attestation (operator, native reader) appends later. Accepted rounds later, through a mint call from Train items only. Selection is `ontology::select(ontology, language, view)`, called only inside `Prompt::lower`, so no caller picks entries; the prompt prints each selected entry's id, layer, choice and examples. Its text is minted text for the leak diagnostic, which today has no runtime caller (follow-up `leak-diagnostic-in-round`). The store was rebuilt without ja-JP `:14` and `:15` (above-status Scene entries; a paired measure found them net-negative on register, follow-up `ja-scene-entries-lower-register-agreement`), so ja-JP ends at `:13`: an above-status out-group addressee, and an above-status in-group addressee below intimacy 700, select no ja-JP Scene entry (`:12` still selects in-group at intimacy 700 or more regardless of status) until a native reader attests a replacement (`ja-native-reader-scenes`). ja-JP `:5`, `:7` and `:8` were revised by certainty and restraint `AtMostOrUnset` conditions (holds when the feature is unrated or at most the grade; `AtMost` still fails on an unrated feature) in a store rebuild (the store has no retire, so a conditions change is a rebuild), which makes ja-JP's hedging, certainty, affection, restraint and sadness entries disjoint on `:5`/`:6`, `:4`/`:7`, `:6`/`:7`, `:6`/`:8`; en-US `:3` carries `AtMostOrUnset` hedge and affection bounds, `:5` an `AtMostOrUnset` certainty bound (the clause it held in prose) and `:8` one too (as ja-JP `:7`), which makes `:3`/`:5`, `:3`/`:8`, `:5`/`:6` and `:6`/`:8` disjoint, while `:6`/`:10` stay co-selectable and are kept apart by scoping in `:6`'s text; ja-JP `:9` was reworded in a rebuild to state its question ending as available, so `:6`/`:9`, `:5`/`:9` and `:3`/`:9` stay co-selectable and are reconciled by wording, not by condition | +| Language ontology entry (cut `language-ontology`) | Key `onto::`, `n` from 1 per language; type `weksa.ontology_entry` in `data/ontology/ontology.cc`: the language, the revision of the inventory it was admitted through (provenance: beds number revisions independently and a run reads each condition's feature at its own head), a layer (lexicon, grammar, discourse, phonology, orthography), at most four conditions (a feature id of slot `Stance`, `Discourse` or `Scene` with `AtLeast`/`AtMost`/`AtMostOrUnset` a grade or `Is` an option or flag; a `Scene` condition reads the relation of the item's speaker to its addressee that `with_scene` selected; slot `Speaker` and community ids wait on follow-up `language-ontology-communities`), a choice of 1 to 200 bytes, at most three examples of 1 to 120 bytes, and an `Annotator`. Whether an entry's text keeps politeness on the scene is a model reader's judgment, owed per change (a mint owes it under `language-ontology-growth`), not a test | Admitted in all-or-nothing batches through `OntologyStore::admit`, immutable, never edited; retire arrives with `language-ontology-growth`. The run pins the store like the entity store (path and digest, `Drift(Ontology)`), never copies it, because no loop step writes it yet. Cut `language-ontology-seed` converts by drafting, not by parse: a fresh model drafts each language's seed from that language's YAML and the inventory's feature lines with no corpus text, then deletes `data/target-language-ontology/` and `.weksa/cultural-ontology/` in the same cut | Seed: a labelled model (`Annotator::Model`), no operator gate, never Test evidence (`ja-ontology-owner-answer`); attestation (operator, native reader) appends later. Accepted rounds later, through a mint call from Train items only. Selection is `ontology::select(ontology, language, view)`, called only inside `Prompt::lower`, so no caller picks entries; the prompt prints each selected entry's id, layer, choice and examples. Its text is minted text for the leak diagnostic, which today has no runtime caller (follow-up `leak-diagnostic-in-round`). The store was rebuilt without ja-JP `:14` and `:15` (above-status Scene entries; a paired measure found them net-negative on register, follow-up `ja-scene-entries-lower-register-agreement`), so ja-JP ends at `:13`: an above-status out-group addressee, and an above-status in-group addressee below intimacy 700, select no ja-JP Scene entry (`:12` still selects in-group at intimacy 700 or more regardless of status) until a native reader attests a replacement (`ja-native-reader-scenes`). ja-JP `:5`, `:7` and `:8` were revised by certainty and restraint `AtMostOrUnset` conditions (holds when the feature is unrated or at most the grade; `AtMost` still fails on an unrated feature) in a store rebuild (the store has no retire, so a conditions change is a rebuild), which makes ja-JP's hedging, certainty, affection, restraint and sadness entries disjoint on `:5`/`:6`, `:4`/`:7`, `:6`/`:7`, `:6`/`:8`, and ja-JP `:3` (anger) carries `AtMostOrUnset` hedge and affection bounds, as en-US `:3`, which makes `:3`/`:5` and `:3`/`:7` disjoint; en-US `:3` carries `AtMostOrUnset` hedge and affection bounds, `:5` an `AtMostOrUnset` certainty bound (the clause it held in prose) and `:8` one too (as ja-JP `:7`), which makes `:3`/`:5`, `:3`/`:8`, `:5`/`:6` and `:6`/`:8` disjoint, while `:6`/`:10` stay co-selectable and are kept apart by scoping in `:6`'s text; ja-JP `:9` was reworded in a rebuild to state its question ending as available, so `:6`/`:9`, `:5`/`:9` and `:3`/`:9` stay co-selectable and are reconciled by wording, not by condition | | Community (cut `language-ontology`, follow-up `language-ontology-communities`) | Key `community:`; type `weksa.community`, converted from `data/cultural-ontology/cultures/` and `referents/` (YAML deleted in the same cut) | Revised by commit; a speaker names the communities it belongs to by id | The cultural ontology's author (owner-attested evidence only; Discord-only content stays deleted, `discord-only-content-deleted`) | | Speaker (cut `speaker-scene`) | Key `speaker:@`; type `weksa.speaker`: stable axes as feature values of slot `Speaker` (origin, socioeconomic standing, age cohort, education and whatever the loop adds), at an inventory revision, and an `Annotator` | A new revision appends, never edits; a corpus item and every prior turn name a speaker slug, and a round records the speaker revisions it read | The annotator it names: `PersonaSnapshot` (a projection of a `gamecult.persona_state.v0` document, naming its source document and `updatedAt`), `Operator`, `WorkMetadata` (a public-domain work's own cast list and narration), or `Model { family, generator }` (the 2b `ModelFamily`) | | Scene (cut `speaker-scene`) | Key `scene:@`, the item's split group; type `weksa.scene`: participants (speaker slugs) and, per ordered pair, relation features of slot `Scene` (relative status, intimacy, in-group, audience and whatever the loop adds), at an inventory revision (provenance; a run reads the features at its own head), and an `Annotator` | As Speaker. Keyed by the group, so a scene never straddles the split. `data/original/speaker-state.cc` holds Model-annotated keeper scenes, one per Train or Validation group of both languages (`weksa scene put|dump`); a Test group has none and reads `NoScene` | As Speaker; a model-annotated scene is never Test evidence |