Evidence Provenance
A second artifact is not a second proof. Count loops, not files.
Owns one invariant: evidence produced by the same reasoning loop as the
artifact it validates is one evidentiary loop, unless something outside that
loop can falsify it. It does not reject creator-authored tests, require a human
reviewer, require several models, or force an expensive or unavailable gate.
Triggers
is this independent evidence, did the reviewer confirm this, closed loop,
count the confirmations, which checks actually ran
The invariant
agent reads requirement R
+--> writes implementation I
+--> writes new test T from the same reading
I + T = useful evidence about I
I + T != two independent confirmations of R
Creator tests stay valid. They answer "does I do what I was written to do". They
cannot answer "was R read correctly", because both artifacts inherit one reading.
Process
List the claim and the artifact. Name the artifact, its revision, and the
premises it was built from (the reading of R, the generator, the fixture
source).
Record each piece of evidence with its lineage. The fields and their
values are in references/lineage-model.md. Two rules decide most cases:
- Shared premise or inheritance joins the subject's loop. A reviewer who is
handed the implementer's conclusion, or an expected output made by the
implementation's generator, is in that loop whatever agent produced it.
- Lineage you cannot state is lineage you cannot count. An item with no
recorded premises is never independent.
Classify. Write the record as JSON and run:
python3 "${COPILOT_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-.claude}}/skills/evidence-provenance/scripts/classify_lineage.py" <record.json>
An item whose bound_to names a different artifact or revision is always
rejected (binding-mismatch), not downgraded. Add --promotion when the
evidence gates a deployment: every item then also needs a bound_to with
artifact, revision, validator, command, and result, or it is rejected as
binding-missing.
Read the verdict.
| Verdict |
Meaning |
CORROBORATED |
At least one independent loop verified the claim. independent_loops is the count to cite. |
SINGLE_LOOP |
Verified, but only inside the subject's loop. Cite it as one loop, however many files. |
FALSIFIED_BY_INDEPENDENT_OBSERVATION |
An independent item with normative or executable-runtime authority failed. It wins over any same-loop pass. |
FAILED |
An item failed without independent authority. Investigate before citing anything else. |
NO_VERIFIED_EVIDENCE |
Nothing verified, or every item was rejected for a binding problem (binding-mismatch or binding-missing). |
Cite the count the classifier gives. Set claimed_independent to the
number you intend to write. A claim above independent_loops exits 1 as
inflated-confidence.
Independence and authority are separate. An independent heuristic is a weak
loop; a same-loop run of the real runtime is strong evidence about I and still
one loop. The output carries both, so a consumer never has to collapse them.
Strengthening evidence
| Evidence |
Why it counts |
| Pre-existing test that was red and is now green |
Written before the change from a different premise, and the change did not edit it. |
| Observation of the real runtime, service, or tool |
Its premise is the system itself, not a reading of it. |
| Reviewer who rebuilt the result from primary evidence |
Own premises, no inheritance from the implementer. |
| New test that fails when the defect is restored |
Marked discriminating. It proves the test can fail. It is still one loop for the premise. |
Walk or do not name
When a relevant check is cheap and available, run it before you cite it. Do not
strengthen a conclusion with a check you chose not to run.
| State |
Use it when |
VERIFIED |
You ran the check and observed it pass. |
NOT RUN |
You did not run it. It may not support a conclusion. |
UNAVAILABLE |
The tools or environment could not run it. Say why. |
FAILED |
You ran it and it failed. |
Any other wording for a named check ("should run X", "pending", no state) exits
1 as named-without-state. A NOT RUN or FAILED item used as support exits 1
as unverified-support. A cheap, available check left NOT RUN but not cited
returns the warning cheap-gate-not-run. Expensive, destructive, or
credentialed checks are never mandatory; the duty is to report their state.
Composition
This skill owns the lineage and state semantics and nothing else.
| Concern |
Owner |
| Strong, falsifiable tests and mutation controls |
the testing rule |
| Equivalence without copied contracts |
the canonical-source evidence contract |
| Wording of progress and completion reports |
the voice rule, "Clear The Gate Or Drop The Claim" |
| Which validator governs a change |
validation-authority, analysis-provenance |
| Review verdicts and independent reviewer behavior |
review (technical-review) |
Consumers name this skill by its id and link here. They do not copy this
skill's tables.
Scripts
| Script |
Purpose |
Exit codes |
classify_lineage.py |
Loops, independence, authority, verdict, violations |
0 classified, 1 violation or failed claim, 2 bad input |
Exit 0 means classified, not passed. NO_VERIFIED_EVIDENCE exits 0, even
under --promotion with every item rejected. A promotion gate must also require
a CORROBORATED or SINGLE_LOOP verdict and an empty rejected list.
The script is stdlib-only. It trusts the lineage fields it is given, so a
fabricated premise list defeats it. Check the fields against the diff and the
transcript, not against the agent's own summary.
Verification
1---2name: evidence-provenance3description: Decide whether evidence is independent or the same loop twice, and whether a named check was run. Classifies lineage (premise, origin, time, mutability, environment), keeps authority a separate axis, and reports VERIFIED, NOT RUN, UNAVAILABLE, or FAILED. Use when you say `is this independent evidence`, `did the reviewer confirm this`, `closed loop`, or `count the confirmations`. Do NOT use to report progress (use the voice rule) or to pick the governing validator (use validation-authority).4metadata:5 source: https://skillmd.com/skills/rjmurillo/evidence-provenance6---78# Evidence Provenance910> A second artifact is not a second proof. Count loops, not files.1112Owns one invariant: evidence produced by the same reasoning loop as the13artifact it validates is one evidentiary loop, unless something outside that14loop can falsify it. It does not reject creator-authored tests, require a human15reviewer, require several models, or force an expensive or unavailable gate.1617## Triggers1819`is this independent evidence`, `did the reviewer confirm this`, `closed loop`,20`count the confirmations`, `which checks actually ran`2122## The invariant2324```text25agent reads requirement R26 +--> writes implementation I27 +--> writes new test T from the same reading2829I + T = useful evidence about I30I + T != two independent confirmations of R31```3233Creator tests stay valid. They answer "does I do what I was written to do". They34cannot answer "was R read correctly", because both artifacts inherit one reading.3536## Process37381. **List the claim and the artifact.** Name the artifact, its revision, and the39 premises it was built from (the reading of R, the generator, the fixture40 source).412. **Record each piece of evidence with its lineage.** The fields and their42 values are in `references/lineage-model.md`. Two rules decide most cases:43 - Shared premise or inheritance joins the subject's loop. A reviewer who is44 handed the implementer's conclusion, or an expected output made by the45 implementation's generator, is in that loop whatever agent produced it.46 - Lineage you cannot state is lineage you cannot count. An item with no47 recorded premises is never independent.483. **Classify.** Write the record as JSON and run:4950 ```bash51 python3 "${COPILOT_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-.claude}}/skills/evidence-provenance/scripts/classify_lineage.py" <record.json>52 ```5354 An item whose `bound_to` names a different artifact or revision is always55 rejected (`binding-mismatch`), not downgraded. Add `--promotion` when the56 evidence gates a deployment: every item then also needs a `bound_to` with57 artifact, revision, validator, command, and result, or it is rejected as58 `binding-missing`.594. **Read the verdict.**6061 | Verdict | Meaning |62 |---------|---------|63 | `CORROBORATED` | At least one independent loop verified the claim. `independent_loops` is the count to cite. |64 | `SINGLE_LOOP` | Verified, but only inside the subject's loop. Cite it as one loop, however many files. |65 | `FALSIFIED_BY_INDEPENDENT_OBSERVATION` | An independent item with normative or executable-runtime authority failed. It wins over any same-loop pass. |66 | `FAILED` | An item failed without independent authority. Investigate before citing anything else. |67 | `NO_VERIFIED_EVIDENCE` | Nothing verified, or every item was rejected for a binding problem (`binding-mismatch` or `binding-missing`). |68695. **Cite the count the classifier gives.** Set `claimed_independent` to the70 number you intend to write. A claim above `independent_loops` exits 1 as71 `inflated-confidence`.7273Independence and authority are separate. An independent heuristic is a weak74loop; a same-loop run of the real runtime is strong evidence about I and still75one loop. The output carries both, so a consumer never has to collapse them.7677## Strengthening evidence7879| Evidence | Why it counts |80|----------|---------------|81| Pre-existing test that was red and is now green | Written before the change from a different premise, and the change did not edit it. |82| Observation of the real runtime, service, or tool | Its premise is the system itself, not a reading of it. |83| Reviewer who rebuilt the result from primary evidence | Own premises, no inheritance from the implementer. |84| New test that fails when the defect is restored | Marked `discriminating`. It proves the test can fail. It is still one loop for the premise. |8586## Walk or do not name8788When a relevant check is cheap and available, run it before you cite it. Do not89strengthen a conclusion with a check you chose not to run.9091| State | Use it when |92|-------|-------------|93| `VERIFIED` | You ran the check and observed it pass. |94| `NOT RUN` | You did not run it. It may not support a conclusion. |95| `UNAVAILABLE` | The tools or environment could not run it. Say why. |96| `FAILED` | You ran it and it failed. |9798Any other wording for a named check ("should run X", "pending", no state) exits991 as `named-without-state`. A `NOT RUN` or `FAILED` item used as support exits 1100as `unverified-support`. A cheap, available check left `NOT RUN` but not cited101returns the warning `cheap-gate-not-run`. Expensive, destructive, or102credentialed checks are never mandatory; the duty is to report their state.103104## Composition105106This skill owns the lineage and state semantics and nothing else.107108| Concern | Owner |109|---------|-------|110| Strong, falsifiable tests and mutation controls | the testing rule |111| Equivalence without copied contracts | the canonical-source evidence contract |112| Wording of progress and completion reports | the voice rule, "Clear The Gate Or Drop The Claim" |113| Which validator governs a change | `validation-authority`, `analysis-provenance` |114| Review verdicts and independent reviewer behavior | `review` (technical-review) |115116Consumers name this skill by its id and link here. They do not copy this117skill's tables.118119## Scripts120121| Script | Purpose | Exit codes |122|--------|---------|------------|123| `classify_lineage.py` | Loops, independence, authority, verdict, violations | `0` classified, `1` violation or failed claim, `2` bad input |124125Exit `0` means classified, not passed. `NO_VERIFIED_EVIDENCE` exits `0`, even126under `--promotion` with every item rejected. A promotion gate must also require127a `CORROBORATED` or `SINGLE_LOOP` verdict and an empty `rejected` list.128129The script is stdlib-only. It trusts the lineage fields it is given, so a130fabricated premise list defeats it. Check the fields against the diff and the131transcript, not against the agent's own summary.132133## Verification134135- [ ] Every cited confirmation has a lineage record, including each reviewer.136- [ ] The number of confirmations cited is at most `independent_loops`.137- [ ] Every named check carries `VERIFIED`, `NOT RUN`, `UNAVAILABLE`, or `FAILED`.138- [ ] A promotion record was classified with `--promotion` at the final head.