0 Fork 0

Files

T

ZacharyZhang-NY b8f83f422a Put the stop-word bound's evidence in the repo, not in a scratch script

COMMON_TERM_FRACTION = 0.05 is a magic number unless something prints the curve it
came from. bench/term_sweep.py asks the frozen suite as its holders would, once per
candidate bound, and writes recall and latency into the same row of
bench/reports/TERMS.md.

rare_terms now resolves its bound when the call runs instead of when the function was
defined, which is the only way a harness can move it. The default value is unchanged,
so the reports stamped at the parent commit still describe this code.

2026-10-08 14:36:59 -04:00

src/ely_eye

Put the stop-word bound's evidence in the repo, not in a scratch script

2026-10-08 14:36:59 -04:00

tests

Keep the vectors beside the atoms instead of rebuilding them per query

2026-10-08 14:05:27 -04:00

pyproject.toml

Keep the vectors beside the atoms instead of rebuilding them per query

2026-10-08 14:05:27 -04:00

README.md

Ely-Eye — local multimodal context operating system on Qwen3.5-9B