Loading
Loading
Two axes that turn unstructured notes into something a retrieval pipeline can reason about.
A deposit's direction— whether it asserts something works, doesn't, should be approached with care, or is an open question.
positive— "X works" / "X is true".negative— "X doesn't work" / "X failed". cautionary — "X works but…" / "watch out for…".open— "we haven't tested yet" / a note, not a claim.positive, negative, and cautionary are directional. When two or more distinct directional polarities appear in the same scope bag, the bag is flagged as in conflict — that includes negative + cautionary without a positive. open is non-directional and never triggers a conflict: open questions are always cheap to record.
How well-supported the claim is.
anecdotal — one person, one observation, no logs.observed — measured at least once with artifacts.replicated — multiple independent observations agree.verified — replicated and recorded with provenance.The gate weighs polarity against evidence to decide if a write should pass. A broad positiveclaim ("threshold 0.7 is always optimal") needs replicated or better. A narrow negativeclaim ("0.7 over-flags on dataset X") only needs provenance — a known failure is allowed in cheaply because downstream agents need to know.
At read time, every hit's polarity is used to compute the dominant direction of its scope bag. If the bag is unanimous in one direction, is_confident can fire; if it has both a positive and a negative, has_disagreement fires regardless of how many votes each side has.
Pass an unknown value and the error message tells you every valid option with a one-line definition. Atlaso's validation layer is explicitly pedagogical.
user.add("hello", polarity="strong")
# InputValidationError: polarity must be one of:
# "positive" — claim that X works / is true
# "negative" — claim that X doesn't work / failed
# "cautionary" — claim with caveats
# "open" — note or open questionWas this page helpful?