Kai 5de80905ba eval(golden): pin bare cross-turn back-reference ("收") ...

Recording for the new cross_turn_bare_backreference case: ask "is it worth
collecting?", then a lone "收" must resolve to that film (collect / movie /
巴尼的人生) and propose collect with the tmdb id -- not ask which work.

2026-08-29 15:44:59 -07:00

..

bare_title.jsonl

feat(curator): golden evaluation recordings

2026-08-28 20:28:44 -07:00

cross_turn_4k_reference.jsonl

feat(curator): golden evaluation recordings

2026-08-28 20:28:44 -07:00

cross_turn_bare_backreference.jsonl

eval(golden): pin bare cross-turn back-reference ("收")

2026-08-29 15:44:59 -07:00

destructive_request.jsonl

feat(curator): golden evaluation recordings

2026-08-28 20:28:44 -07:00

explicit_book_wanted.jsonl

feat(curator): golden evaluation recordings

2026-08-28 20:28:44 -07:00

explicit_collect_tv.jsonl

feat(curator): golden evaluation recordings

2026-08-28 20:28:44 -07:00

injection_no_write.jsonl

feat(curator): golden evaluation recordings

2026-08-28 20:28:44 -07:00

library_typo_question.jsonl

feat(curator): golden evaluation recordings

2026-08-28 20:28:44 -07:00

question_must_not_write.jsonl

feat(curator): golden evaluation recordings

2026-08-28 20:28:44 -07:00