crates/weksa/examples/show_working.rs

@@ -258,7 +258,7 @@ fn lower_error(e: &LowerError) -> Value {
         LowerError::DanglingStress { entity, at } => ("DanglingStress", format!("the ruled pronunciation of {entity} has a stress mark at {at} with no vowel after it")),
         LowerError::ConsentMissing { predication } => ("ConsentMissing", format!("{predication} is a request the packet does not carry the addressee's consent to")),
         LowerError::AskerNotAddressee { predication } => ("AskerNotAddressee", format!("the agent of {predication} is not the addressee")),
-        LowerError::EntityRead { entity, why } => ("EntityRead", format!("reading {entity}: {why}")),
+        LowerError::EntityRead { entity, .. } => ("EntityRead", format!("the entity store failed reading {entity}")),
     };
     json!({ "variant": variant, "reason": reason })
 }
@@ -279,11 +279,11 @@ fn run(w: &World, dir: &Path, packet: &Packet) -> Result<(String, Value), Value>
         Err(StoreError::Invalid(rs)) => {
             return Err(json!({
                 "kind": "admission_refused",
-                "refusals": rs.iter().map(|r| json!({ "rule": r.rule(), "detail": format!("{r:?}") })).collect::<Vec<_>>(),
+                "refusals": rs.iter().map(|r| json!({ "rule": r.rule(), "detail": r.to_string() })).collect::<Vec<_>>(),
             }));
         }
         Err(e) => {
-            return Err(json!({ "kind": "admission_refused", "refusals": [{ "rule": "store", "detail": format!("{e:?}") }] }));
+            return Err(json!({ "kind": "admission_refused", "refusals": [{ "rule": "store", "detail": e.to_string() }] }));
         }
     };
     let text = lower(&view, &w.inv, &w.entities).map_err(|e| {

crates/weksa/src/corpus.rs

@@ -32,7 +32,7 @@ pub enum Source {
     /// A public-domain work, with everything a reader needs to check the claim:
     /// the edition's licence and the jurisdiction the public-domain status is
     /// asserted in, who translated it (the translation is the text's copyright,
-    /// not the original's) and when the edition appeared. A work missing any
+    /// not the original's) and when the work or translation first appeared. A work missing any
     /// is refused at admission.
     PublicDomain {
         work: String,
@@ -41,6 +41,10 @@ pub enum Source {
         licence: String,
         jurisdiction: String,
         translator: String,
+        /// The year the work, or for a translation this translation, first
+        /// appeared. It is not the year of the `edition_url` file's source
+        /// print: Project Gutenberg's text may be a later or modernised
+        /// edition, and the claim rests on the date of first appearance.
         edition_year: u16,
     },
     /// Labelled model output; never in the test split. The rule that it is

schemas/cultnet/weksa.corpus_item.schema.json

@@ -170,7 +170,7 @@
           ]
         },
         {
-          "description": "A public-domain work, with everything a reader needs to check the claim:\nthe edition's licence and the jurisdiction the public-domain status is\nasserted in, who translated it (the translation is the text's copyright,\nnot the original's) and when the edition appeared. A work missing any\nis refused at admission.",
+          "description": "A public-domain work, with everything a reader needs to check the claim:\nthe edition's licence and the jurisdiction the public-domain status is\nasserted in, who translated it (the translation is the text's copyright,\nnot the original's) and when the work or translation first appeared. A work missing any\nis refused at admission.",
           "type": "object",
           "properties": {
             "PublicDomain": {
@@ -183,6 +183,7 @@
                   "type": "string"
                 },
                 "edition_year": {
+                  "description": "The year the work, or for a translation this translation, first\nappeared. It is not the year of the `edition_url` file's source\nprint: Project Gutenberg's text may be a later or modernised\nedition, and the claim rests on the date of first appearance.",
                   "type": "integer",
                   "format": "uint16",
                   "maximum": 65535,

tools/show-working/build.py

@@ -59,7 +59,9 @@ for m in re.finditer(r'^(item:\S+) \[(.*?)\]\n  "(.*)"$', run([str(weksa_bin), "
 if set(corpus) != cited:
     sys.exit(f"corpus dump lacks cited items {sorted(cited - set(corpus))}; unexpected {sorted(set(corpus) - cited)}")
 # The dump's meta ends with the split (`... group=g Validation`, `... excluded`).
-held_out = {k: v["meta"].split()[-1] for k, v in corpus.items() if v["meta"].split()[-1] in ("Validation", "Test")}
+# Only Train and split-less items publish; any other name, including a split
+# added later, is held out until it is allowed here.
+held_out = {k: v["meta"].split()[-1] for k, v in corpus.items() if v["meta"].split()[-1] not in ("Train", "excluded")}
 if held_out:
     sys.exit(f"refusing to publish held-out items (nothing written): {held_out}")
 model = "qwen3-embedding:0.6b"