vh
8bb7686a16
Stoplisting a surface removes it from the entity map, so rename never touches it
and the gate never scans for it. That is exactly what a stoplist is FOR when the
surface is a real-world referent — and exactly how a wrongly stoplisted CHARACTER
becomes an undetectable leak. The gate reports 0 of N surviving and is telling the
truth about the set it was given.
Found by luck on lv-bronte: a generated beat said "Mrs. Leaven", and Leaven had
been filed under scripture as the bread noun. Reading it back: "Robert Leaven,
the coachman" — Bessie's married surname in Jane Eyre.
Running the audit instead of trusting that luck caught two more:
Pierrot "Madame Pierrot: she comes from Lisle, in France" — a teacher in
The Professor, filed as the commedia dell'arte figure
Samuel "Mr. Samuel Wynne" — filed as scripture
and correctly CLEARED two:
Wellington "that Baal of a Lord Wellington" — the real Duke
Moses "the Rev. Moses Barraclough" — the documented dual-use
Signal is an honorific in front of the surface: real-world referents are not
addressed as Mr/Mrs/Miss/Madame/Lord. It is a heuristic and not a proof, which is
why every hit is REPORTED FOR READING and never auto-removed — Wellington and
Moses both trip it and both are correct. Exit 1 on anything not on --allow, so it
can gate a pipeline.
Blast radius of the three errors was 16 of 3781 train pairs and 3 of 80 val —
small, but they are the author's characters in training data, which is the one
thing this pipeline exists to prevent. Corpus rebuilt rather than dropping the
affected pairs: a corpus on disk that disagrees with its committed config is how
superseded claims get made. Gate re-passes at 0 of 368 (three more surfaces than
before, exactly the restored characters), both controls green.
95 lines
4.7 KiB
JSON
95 lines
4.7 KiB
JSON
{
|
|
"corpus": "lv-bronte (Charlotte Brontë — Jane Eyre, Villette, Shirley, The Professor)",
|
|
"why": "The rename exists to keep the author's INVENTIONS out of the adapter. A real-world referent any novelist could use is not hers, and renaming it damages prose for no leak benefit. entities.py already carries a built-in STOP_COMMON that was tuned on this very corpus (London/Paris/Brussels/Yorkshire/God/Lord/Madam/Sir/Monsieur/Mademoiselle). This file is the DELTA that pass missed — overwhelmingly French honorific abbreviations and generic French place-nouns, because three of the four novels are set in or shadowed by Belgium.",
|
|
"how_derived": "Every surface here was read IN CONTEXT before it landed, and the reading changed the answer twice. `India` is never the country — it is only ever the compound `India-rubber`, so renaming it yields `Braevick-rubber`. `Terrasse` looked like a generic French noun and is in fact `La Terrasse`, the Brettons' house, so it was PUT BACK as renameable. The ambiguous direction is deliberately biased toward renaming: leaving is the leaking direction.",
|
|
"honorific_abbreviations": [
|
|
"Mdlle",
|
|
"Mdlles",
|
|
"Mdme",
|
|
"Mons",
|
|
"Messieurs",
|
|
"Mesdames",
|
|
"Misses",
|
|
"Esq",
|
|
"Père",
|
|
"Mère"
|
|
],
|
|
"generic_french_nouns_used_as_place_components": [
|
|
"Rue",
|
|
"Hôtel",
|
|
"Athénée",
|
|
"Basse-Ville",
|
|
"Faubourg",
|
|
"Porte",
|
|
"Boulevard"
|
|
],
|
|
"real_world_geography": [
|
|
"India",
|
|
"Madeira",
|
|
"Antwerp",
|
|
"Ostend",
|
|
"Calais",
|
|
"Birmingham",
|
|
"Eton",
|
|
"Louvain",
|
|
"Jamaica",
|
|
"Antigua",
|
|
"Guadaloupe",
|
|
"Egypt"
|
|
],
|
|
"real_world_people_and_works": [
|
|
"Shakespeare",
|
|
"Wellington",
|
|
"Cowper",
|
|
"Coriolanus",
|
|
"Cleopatra",
|
|
"Moses",
|
|
"Bonaparte",
|
|
"Napoleon",
|
|
"Rousseau",
|
|
"Chénier",
|
|
"Timon",
|
|
"Gytrash"
|
|
],
|
|
"political_and_period_terms": [
|
|
"Jacobin",
|
|
"Tory"
|
|
],
|
|
"typographic_devices": [
|
|
"X----",
|
|
"J",
|
|
"S",
|
|
"Bah",
|
|
"Royale"
|
|
],
|
|
"deliberately_NOT_here": "Read and KEPT renameable, each for a stated reason: `Terrasse` (La Terrasse, the Brettons' house), `Walden` (Walden Hall, an in-world estate), `Crécy` (Boulevard/Porte de Crécy inside the invented city), `Hiram` (Hiram Yorke's given name), `Vashti` (the actress's stage name in Villette, a character), `Labassecour` and `Villette` (Brontë's invented country and city), `Temple` `Cave` (character surnames), `Pilot` `Tartar` (the dogs in Jane Eyre and Shirley — proper names).",
|
|
"known_gap": "`Moses` is stoplisted for the rhetoric (`France is Israel, and Napoleon is Moses`), which means the given name of the character Moses Barraclough is NOT renamed. His surname is. `Grace` and `Blanche` are below the detector's floor for the opposite reason — `grace` the common noun runs at a 0.224 lowercase ratio in Jane Eyre — so `Grace Poole` and `Blanche Ingram` are handled in phrase_map_bronte.json, not here.",
|
|
"real_world_nationalities_and_languages": [
|
|
"Indian",
|
|
"Flemish",
|
|
"Anglais",
|
|
"Anglaise",
|
|
"Englishman",
|
|
"Englishwoman",
|
|
"Parisienne",
|
|
"Belgians",
|
|
"Flamand",
|
|
"Cossack",
|
|
"Hindostanee"
|
|
],
|
|
"religion_and_scripture": [
|
|
"Jesuit",
|
|
"Protestantism",
|
|
"Protestants",
|
|
"Romanism",
|
|
"Dissenters",
|
|
"Maker",
|
|
"Dieu",
|
|
"Notre",
|
|
"Adam",
|
|
"Saul",
|
|
"Daniel"
|
|
],
|
|
"sub_threshold_triage_note": "Everything added in the 2026-09-16 second pass came from the gate's own sub-threshold report — the 84 surfaces below the rename floor that the gate lists separately because rename never saw them. Each was read before landing here. Deliberately NOT stoplisted, because renaming is the safe direction and these may be characters rather than scripture: David, Joseph, Thomas. `Gytrash` is Yorkshire folklore Brontë did not invent; `Pierrot` and `Timon` are stock figures.",
|
|
"stoplist_is_an_unchecked_assertion": "⭐ A stoplist entry removes a surface from the entity map, so rename never touches it and the leak gate never scans for it. The gate then reports 0 of N surviving and is telling the truth about the set it was given — which makes a wrongly stoplisted CHARACTER an undetectable leak. Three were wrong here and all three were caught by audit_stoplist.py, not by the gate: Leaven (\"Robert Leaven, the coachman\" — Bessie's married surname, filed as the bread noun), Pierrot (\"Madame Pierrot: she comes from Lisle\" — a teacher in The Professor, filed as the commedia figure) and Samuel (\"Mr. Samuel Wynne\", filed as scripture). The audit clears Wellington (\"that Baal of a Lord Wellington\" — the real Duke) and Moses (\"the Rev. Moses Barraclough\" — the documented dual-use). Run the audit before the gate, every corpus."
|
|
} |