Mandate exhaustive fact extraction in text-to-fact criteria#150
Merged
Conversation
Add a "완전성 원칙" section so extraction sweeps every section and table
row-by-row instead of skimming prose. Dense tables (참여인력 명부, 재무·등기
현황, 예산 비목, 추진 일정, 경력·특허 실적) were the main silent-omission
source — narrative got captured while repeated table rows were dropped.
- forbid sampling ("대표 몇 개만") of repeated items
- table → triple mapping rule (row key→subject, header→relation, cell→object)
- judge coverage by section/table sweep, not converted-file byte size
- pre-finish self-check, with existing PII exclusions preserved
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Adds a 완전성 원칙 (exhaustiveness) section to
skills/factlog/references/text-to-fact.md, the authoritative criteria theagent follows when extracting candidate facts during
/factlog syncand/factlog add.Why
Dense tables — participant rosters, financial/registry status, budget line
items, monthly schedules, career/patent records — are the highest-density fact
source in real documents, yet the prior criteria only said "record relation
candidates." In practice the agent skimmed the visible prose and silently
dropped repeated table rows. On a real proposal, a source with ~400 extractable
facts yielded only ~90 (≈20–25% coverage) before this change.
What it changes
subject, column header →relation, cell →object; per-year/unit context →note.(HWP/office conversions are inflated by HTML table markup).
(사업자/법인등록번호) and financials are in-scope while personal contact info
and birthdates stay out.
Docs/criteria only — no code paths touched; the file is read at extraction time
so the change is live without reinstall.