diff --git a/README.md b/README.md index 3b02136..24b3b8c 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 Two entries for the above-status cases were withdrawn: a paired measure found they made the lowerer match the reference register less often, and they stay out until a native reader attests them.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. +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) an `AtMostOrUnset` certainty bound, so `:3`/`:5`, `:3`/`:8` and `:5`/`:6` 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. 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 715233c..de6c0bb 100644 --- a/crates/weksa/tests/original_corpus.rs +++ b/crates/weksa/tests/original_corpus.rs @@ -961,14 +961,18 @@ fn committed_scenes_cover_original_groups() { } } -/// ja-JP seed entries :4 to :8 over the stance and discourse grades that bear on -/// them (hedge, certainty, sadness, affection, restraint, each also ABSENT): -/// 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), so a tightened bound does not pass as a disjoint one. -#[test] -fn ja_seed_pairs_never_co_select() { +/// The sweep both seed-pair tests share: over a grid of grades per feature (each +/// also ABSENT) and the production `Condition::holds`, no listed pair of one +/// language's entries co-holds; and each witness entry fires where it should and +/// stays silent where it should, so a tightened or dropped bound does not pass +/// as a disjoint one. `glosses` names the swept features, in point order. +fn sweep_seed_pairs( + language: &str, + glosses: [&str; N], + pairs: &[(u32, u32)], + fires: &[(u32, [Option; N])], + silent: &[(u32, [Option; N])], +) { use weksa::inventory::Slot; use weksa::ontology::{Condition, Test}; use weksa::OntologyStore; @@ -978,18 +982,18 @@ fn ja_seed_pairs_never_co_select() { std::fs::copy(data.join("ontology/ontology.cc"), &onto).unwrap(); let inv = InventoryStore::open(&data.join("original/inventory.cc")).unwrap().inventory().unwrap(); let id = |gloss: &str| inv.entries().find(|e| e.gloss == gloss).unwrap().id; - let feats = [id("hedge"), id("certainty"), id("sadness"), id("affection"), id("restraint")]; + let feats = glosses.map(id); let entries = OntologyStore::open(&onto).unwrap().all().unwrap(); - let ja = |n: u32| { + let entry = |n: u32| { entries .iter() - .find(|e| e.language == "ja-JP" && e.n == n) - .unwrap_or_else(|| panic!("onto:ja-JP:{n} is absent")) + .find(|e| e.language == language && e.n == n) + .unwrap_or_else(|| panic!("onto:{language}:{n} is absent")) }; - type Point = [Option; 5]; + type Point = [Option; N]; // The production evaluator over the slot's feature values: absent features // are left out of the list, as a view leaves them out. - let holds = |e: &weksa::OntologyEntry, point: &Point| { + let holds = |e: &weksa::OntologyEntry, point: &Point| { use weksa::packet::{FeatValue, FeatureValue, Grade}; e.when.iter().all(|c: &Condition| { assert!(matches!(c.slot, Slot::Stance | Slot::Discourse), "{}", e.key()); @@ -1010,45 +1014,96 @@ fn ja_seed_pairs_never_co_select() { }) }; let grid = [None, Some(0u16), Some(300), Some(500), Some(599), Some(600), Some(700), Some(799), Some(800), Some(1000)]; - let pairs = [(5, 6), (4, 7), (6, 7), (6, 8)]; - for p in 0..grid.len().pow(5) { - let point: Point = std::array::from_fn(|i| grid[p / grid.len().pow(i as u32) % grid.len()]); - for (a, b) in pairs { + for p in 0..grid.len().pow(N as u32) { + let point: Point = std::array::from_fn(|i| grid[p / grid.len().pow(i as u32) % grid.len()]); + for &(a, b) in pairs { assert!( - !(holds(ja(a), &point) && holds(ja(b), &point)), - "onto:ja-JP:{a} and :{b} co-select at (hedge, certainty, sadness, affection, restraint) = {point:?}" + !(holds(entry(a), &point) && holds(entry(b), &point)), + "onto:{language}:{a} and :{b} co-select at {glosses:?} = {point:?}" ); } } - // Reach: each entry fires at its witnesses and not just outside its core. - let (n, s) = (None, Some); - let fires: [(u32, Point); 9] = [ - (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]), - ]; for (e, point) in fires { - assert!(holds(ja(e), &point), "onto:ja-JP:{e} does not fire at {point:?}"); + assert!(holds(entry(*e), point), "onto:{language}:{e} does not fire at {point:?}"); } - let silent: [(u32, Point); 6] = [ - (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)]), - ]; for (e, point) in silent { - assert!(!holds(ja(e), &point), "onto:ja-JP:{e} fires at {point:?}"); + assert!(!holds(entry(*e), point), "onto:{language}:{e} fires at {point:?}"); } } +/// 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). +#[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)], + &[ + (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]), + ], + &[ + (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)]), + ], + ); +} + +/// en-US seed entries :3, :5, :6, :8 over anger, restraint, hedge, certainty and +/// affection: blunt anger never holds with a hedge or affection entry, and a +/// hedge never holds with a flatly certain line, so the pairs that gave opposed +/// instructions (no cushioning against softening, hedge against no hedge) are +/// disjoint by condition; each of :3, :5, :6, :8 fires and stays silent at its +/// witnesses, so a dropped or tightened bound does not pass as a disjoint one. +/// :6 against the Scene entry :10 is kept apart by scoping in the text only. +#[test] +fn en_us_seed_pairs_never_co_select() { + let (n, s) = (None, Some); + sweep_seed_pairs( + "en-US", + ["anger", "restraint", "hedge", "certainty", "affection"], + &[(3, 5), (3, 8), (5, 6)], + &[ + (3, [s(600), s(300), n, n, n]), + (3, [s(600), s(300), s(599), n, s(599)]), + (3, [s(1000), s(0), s(0), s(799), s(0)]), + (5, [n, n, s(600), n, n]), + (5, [n, n, s(700), s(799), n]), + (5, [s(1000), s(1000), s(600), n, n]), + (6, [n, n, n, s(800), n]), + (8, [n, n, n, n, s(600)]), + (8, [s(1000), s(0), n, n, s(600)]), + ], + &[ + (3, [s(600), s(300), s(600), n, n]), + (3, [s(600), s(300), n, n, s(600)]), + (3, [s(599), s(300), n, n, n]), + (3, [s(600), s(301), n, n, n]), + (3, [s(600), n, n, n, n]), + (5, [n, n, s(599), n, n]), + (5, [n, n, s(700), s(800), n]), + (6, [n, n, n, s(799), n]), + (8, [n, n, n, n, s(599)]), + ], + ); +} + /// The committed ontology's Scene-conditioned entries, over every scene relation /// (relative_status x in_group x intimacy in steps of 50): two entries of one /// language and layer are never selected by the same relation, so the ontology diff --git a/data/ontology/ontology.cc b/data/ontology/ontology.cc index a6d2edd..5876983 100644 Binary files a/data/ontology/ontology.cc and b/data/ontology/ontology.cc differ diff --git a/docs/targets/interlingua-lowering-map.md b/docs/targets/interlingua-lowering-map.md index b436b3b..bf4ff74 100644 --- a/docs/targets/interlingua-lowering-map.md +++ b/docs/targets/interlingua-lowering-map.md @@ -34,7 +34,7 @@ means no store holds it and nothing writes it. | Inventory entry | Key `:`, `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` | +| 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 and `:5` an `AtMostOrUnset` certainty bound (the clause it held in prose), which makes `:3`/`:5`, `:3`/`:8` and `:5`/`:6` disjoint, while `:6`/`:10` stay co-selectable and are kept apart by scoping in `:6`'s text | | 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 |