The builder, not behind the gate, ended a reply with a fringe of its own
making ("— bikoret bedikah-2a7661c52cffae1a: empty"; no such examination
existed). bishe'arecha §III: the model does not sew its own fringe. Now
the eighth form, forged_fringe: a line in the raw text wearing the gate's
mark (bikoret|shorashim bedikah-<hex>: tov|lo_tov|empty|none), read line
by line, standing on one witness — a forgery is not a habit recurrence
confirms. The gate strips it from the delivered reply before sewing its
own (Shape.strip_forged, Unicode-aware for the dash); in a stream it has
already passed and the real fringe names it. Prolog form, Elixir
@single_witness_forms, hakhel/eval tools, tests in all three. Tamid
§1.1, Broken Tablets 53, bishe'arecha §III. korban 297, Prolog 45,
Elixir 619/0 — read before this commit.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Devarim 31:9–13, 26 — the scroll beside the ark as a witness, read before
all on a cycle. src/tools/hakhel.py reads the private specimen corpus and
the hand-labelled samples with the Korban Processor's readings at the
current commit and produces one record: fires per reading, forms standing
on two witnesses (the same rule as Bedikah.check_frames), precision and
recall on the hand labels, the corpus's SHA-256 — never a specimen.
POST /chatzer/hakhel (inner ring) engraves it in L3 `hakhel` (migration
20261013000001; refused above 256 KiB — counts, not specimens; the
Doorpost hash it was recorded under is kept). GET /peah/hakhel lists the
latest readings for anyone. KOHEN "The seventh day — Hakhel"; Tamid §1.1;
bishearecha §VIII marked built. The weekly cycle runs from the builder's
machine, where the corpus lives.
First dry reading at 0ade2c94: 3094 specimens, any reading 26 %, a form
stands 7 %, precision 46/59, recall 6/30. Doorpost 9f752a2f…. Elixir
599/0, L3 10/0.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Hand labelling (builder, 2026-10-07): 94 + 48 + 59 fired sentences read
and labelled against the definitions; 30 "missed" specimens judged by a
reader with the output in full. Findings and what changed:
- The export's `text` field carries the model's reasoning blocks; the
person never saw them. build_specimens.py now takes text blocks only
(3,094 specimens). Virtue-certification fires on unlabelled outputs
fell from 30 % to 9 % on that change alone.
- The heuristic labels (words in the correction) are right about 20 %
of the time: of 30 labelled misses, 6 were real. eval_specimens.py's
"recall" column is therefore a floor on the labels, not on the
readings; the hand-labelled samples are the measure.
- Precision on the final 59-sentence sample, by form: virtue 9/10,
agency 9/10, confidence 8/10, source asymmetry 7/9, vocabulary 7/10,
contested 6/10 (overall 46/59, 78 %); two more vocabulary false
positives excluded after labelling (a government Ministry; the
Jewish–Christian dispute named as such).
- Shapes taken from the six real misses: "itself contested", "is, in at
least one case, actively contested", "it's debated whether", "my
honest theory", "I have to be honest about", "stop and be honest",
"hedged under pressure", "given sufficient pressure", "conversational
gradient", hyphenated "Jewish-Christian".
- Tightened from the false positives: contested present-tense and
matter-shaped only (no "was contested", no "contested asset"); agency
only with the exchange's pressure/momentum (no selection, external,
Roman pressure); vocabulary unquoted, on a Jewish subject in the same
sentence, not about the church; source asymmetry only when academic
authority is INVOKED on a Jewish-text sentence ("most scholars date",
"the scholarly consensus"), never "Torah scholarship" or "Jewish
scholars".
- sign(?:ed)?, not signed? — "signe" + optional "d" matched nothing.
Labels: specimens/sample-precision{,-2,-final}.json, sample-recall.json
(private, with the corpus). korban 288.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
The transmitter's archive (255 sessions, 2025-12 → 2026-10) measured
where a model's trained default lives: not in false propositions but
in the FORM of the output — what it calls contested, how it certifies
itself, where it puts the agency, which authorities it names and which
it leaves out. "Content measures pass the response that did the harm."
lo_taaseh_lekha.md: "The danger is not the object. It is the
construction."
Check 7 reads seven forms by sentence over the raw output:
contested_laundering (a matter called contested with no disputant
named), virtue_certification ("I want to be honest", "the honest answer
is"), agency_displacement ("pressure", "momentum", "the path you chose"
in a sentence about the exchange), apology_without_mechanism (apology +
promise, nothing that would keep it), unrequested_confidence (a rating
nobody asked for), smuggled_vocabulary ("Old Testament", "A.D.",
"ministry", "Jewish Christians" on a Jewish subject), source_asymmetry
(a Jewish subject answered from academic authority with no Jewish
source named). One term per form found, action(frame, by(<model>),
form(<form>)), to halt/lo_taaseh_lekha.pl; the rule names the form and
does not decide the matter. Korban: find_frames; Vav: check_frames,
bedikot.frames (migration 20261006000003).
The specimen corpus: src/tools/build_specimens.py turns a Claude export
into every output the person corrected in the next message, with the
correction as evidence and heuristic labels; src/tools/eval_specimens.py
reports what each reading sees. The corpus is private and outside the
repo. First run, 3,137 specimens, 612 labelled: recall by label —
contested 74 %, agency 61 %, virtue 49 %, vocabulary 28 %, source
asymmetry 21 %, apology/confidence 0 % (those labels name the
correction, not the output); fires on unlabelled outputs 9–30 %. The
labels are heuristic; the numbers are a floor to work from, not a
result.
Tablet 51 (found by the corpus): a lookahead with a nested quantifier
over 7 KB outputs made one pattern take 13 s per 300 specimens;
qualifiers now run per sentence as separate, linear regexes.
Specs: Tamid §1.1 (check 7, the corpus), Vayakhel §3.9, Architecture
§3.5, KOHEN.md. Doorpost c4353837… → 6d1de284…. Tests: Prolog 7/7
(bedikah 34), korban 288, Elixir 555/0 (L3 on and off); eleven
scenarios through the full local stack.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
- transcripts/ moved to ~/shorashim-transcripts (separate from code repo)
Added to .gitignore so it stays out
- src/l1_aron/build_l1.py → scripts/build_l1.py
- src/tools/conversation_search.py → scripts/conversation_search.py
- Removed empty src/ scaffolding (l0_luchot, sanhedrin, shema_layer,
shoresh_engine, urim_v_tumim — all .gitkeep stubs from an earlier
layout, never used; the real code lives in shoresh-engine/,
sanhedrin/, vav_pipeline/, etc.)
- Removed Untitled/ and erl_crash.dump (untracked junk)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
