Original corpus for a non-memorised target; recall probes every item; encode prompt states the id form

weksa commented

2026-11-10 14:24:16 +00:00

Member

data/original: six model-written (Anthropic) original passages, 3 Train 3 Validation, over the Dao rev3 inventory. weksa loop recall probes every live item; its line states the real chrF noise floor. Encode prompt says ids carry their family prefix (5 of 6 encoders wrote bare integers). Soul passes s1 and s2: lows fixed. Provenance and probe-coverage tests added.

🤖 Generated with Claude Code

data/original: six model-written (Anthropic) original passages, 3 Train 3 Validation, over the Dao rev3 inventory. weksa loop recall probes every live item; its line states the real chrF noise floor. Encode prompt says ids carry their family prefix (5 of 6 encoders wrote bare integers). Soul passes s1 and s2: lows fixed. Provenance and probe-coverage tests added. 🤖 Generated with [Claude Code](https://claude.com/claude-code)

weksa added 3 commits

2026-11-10 14:24:16 +00:00

Original corpus (data/original): six passages written for the non-memorised target; recall probes every live item 1c08b2abac

Six short original sentences, model-written (Anthropic, claude-sonnet-5-5) and so
labelled, three Train and three Validation, over the Dao revision-3 inventory and
one live entity. The recall probe now covers every offered item, naming the work
only for a public-domain one, so it can show the original set reads near the
guessing floor.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

Encode prompt states the id form; recall line states the real chrF floor; probe test over data/original 3d3ca915ea

Five of six encoders in the first original-corpus round wrote bare integer ids and
were refused at parse (encoder-prompt-concept-ids). The prompt now says ids are
written in full with their family prefix. Soul s1 on the original corpus: unrelated
English scores chrF 13 to 18, not near 0, so the recall line says so; a test runs the
probe over the real original items.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

Soul s2 lows: the id-form test lists a real inventory; the floor reads 14 to 20 5ebdb3cff4

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

weksa merged commit aa6385edc3 into main

2026-11-10 14:24:17 +00:00

weksa referenced this pull request from a commit

2026-11-10 14:24:17 +00:00

Merge pull request 'Original corpus for a non-memorised target; recall probes every item; encode prompt states the id form' (#40) from weksa-lowering/encode-id-form into main

Rows
Columns

Original corpus for a non-memorised target; recall probes every item; encode prompt states the id form #40