{"release":{"schemaVersion":"maha-epistemic-release/1.0","releaseId":"epirelease_92b3bb496d074e44a7ba0f906fdf90f0","releaseKind":"initial","status":"active","recordId":"urn:maha:record:mechanistic-interpretability-causal-scrubbing","domainSlug":"mechanistic-interpretability","targetSha256":"sha256:8fd7d34fe31225012157eb78d84da4c9ffe9d0cad94226f7c27ba6ef83774949","canonicalPath":"/knowledge/mechanistic-interpretability/methods/mechanistic-interpretability-causal-scrubbing","canonicalVersion":"1.0.0","supersedesReleaseId":null,"approvals":[{"scope":"boundary-adequacy","reviewId":"epireview_fd271253e06a4886888b4e94bb45c9a6","reviewSha256":"sha256:8ded443b001f02d38d48aac7756e293822a1d98f20c72e4a01b1fad293e5db07","reviewedAt":"2026-08-27T04:26:21.613Z","reviewerKind":"internal-editorial","reviewMethod":"Record-specific exact-revision review against the inspected source location, bounded claim, non-claims, rights basis, and source identity. No external reviewer participated."},{"scope":"domain-fidelity","reviewId":"epireview_20e19187b3e54080bbd77d4a46afc2c3","reviewSha256":"sha256:48a62f05c4c49de72c0874dd5aa085db44ff4c35f3b0037300cbdaa09b2288a0","reviewedAt":"2026-08-27T04:26:21.468Z","reviewerKind":"internal-editorial","reviewMethod":"Record-specific exact-revision review against the inspected source location, bounded claim, non-claims, rights basis, and source identity. No external reviewer participated."},{"scope":"rights-and-locator","reviewId":"epireview_8feca578c6184e66a500126c00b0dd83","reviewSha256":"sha256:268b7593fc8a4a30d39841b8a010d8674efcb4dd744c63e1bec2ad1afdd05224","reviewedAt":"2026-08-27T04:26:21.817Z","reviewerKind":"internal-editorial","reviewMethod":"Record-specific exact-revision review against the inspected source location, bounded claim, non-claims, rights basis, and source identity. No external reviewer participated."},{"scope":"source-fidelity","reviewId":"epireview_0751539b999c4973a91c257e79d937b7","reviewSha256":"sha256:63b1cbc9fc7b51cb7db28efecd33bb640d87d7a6c9414792a8786fc0f69daf55","reviewedAt":"2026-08-27T04:26:21.332Z","reviewerKind":"internal-editorial","reviewMethod":"Record-specific exact-revision review against the inspected source location, bounded claim, non-claims, rights basis, and source identity. No external reviewer participated."}],"assuranceTier":"internally-reviewed-canonical","releaseAuthority":{"authoritySha256":"sha256:8f3c4f4120db69c1ff36788b6ce7adc88585bcec238f2f2f21cc2f105d10b18b","attribution":"withheld-by-consent"},"publicChangeSummary":"Initial canonical publication under the disclosed Batch 2 internal-review tier.","recordSha256":"sha256:4097a1b90c0c4e9908313d83025f6f229ef66fb4610c058164540d8363ef5cbe","gateDecision":{"reasons":[],"recordId":"urn:maha:record:mechanistic-interpretability-causal-scrubbing","publicEligible":true,"evaluatedAgainst":"maha-epistemic/1.0"},"releasedAt":"2026-08-27T04:26:30.659Z","releaseSha256":"sha256:3268a4a5d0a923d81391cb48c88ec88e8afe1242e4a9ab182062498adca04d45","withdrawal":null},"provenance":{"schemaVersion":"maha-epistemic/1.0","evidencePolicyVersion":"mps/0.1","recordId":"urn:maha:record:mechanistic-interpretability-causal-scrubbing","canonicalPath":"/knowledge/mechanistic-interpretability/methods/mechanistic-interpretability-causal-scrubbing","contentHash":"sha256:4097a1b90c0c4e9908313d83025f6f229ef66fb4610c058164540d8363ef5cbe","generatedAt":"2026-08-27T04:26:30.659Z","publicationDecision":{"recordId":"urn:maha:record:mechanistic-interpretability-causal-scrubbing","publicEligible":true,"evaluatedAgainst":"maha-epistemic/1.0","reasons":[]},"claims":[{"id":"urn:maha:claim:mechanistic-interpretability-causal-scrubbing","scope":"Limited to Method definition, correspondence, resampling interventions, examples, and limitations. in “Causal Scrubbing: a method for rigorously testing interpretability hypotheses”; this candidate records the concept boundary and does not pool results from uncited systems or studies.","boundary":"Causal scrubbing does not by itself establish system-level performance, safety, manufacturability, scalability, economic advantage, clinical benefit, or deployment readiness.","claimKind":"theoretical-model","sourceIds":["source-mechanistic-interpretability-causal-scrubbing"],"statement":"The cited source supports treating causal scrubbing as a distinct method within the stated mechanistic interpretability scope.","replication":{"asOfDate":"2026-08-24","assessment":"Independent replication and cross-platform transfer have not been compiled for this candidate; the evidence maturity refers only to the bounded source contract.","independentReplicationCount":null},"uncertainty":{"kind":"qualitative","statement":"No cross-source quantitative interval is asserted. Definitions, operating conditions, samples, instruments, and outcome measures must be checked against the exact cited locator during review."},"evidenceMaturity":"single-study"}],"sources":[{"id":"source-mechanistic-interpretability-causal-scrubbing","url":"https://www.alignmentforum.org/posts/JvZhhzycHu2Yd57RN/causal-scrubbing-a-method-for-rigorously-testing","title":"Causal Scrubbing: a method for rigorously testing interpretability hypotheses","rights":{"note":"The candidate uses original boundary language and a short paraphrase linked to the cited source. No source passage, figure, or table is reproduced.","basis":"citation-with-paraphrase","quotationUsed":false},"authors":["Lawrence Chan","Adrià Garriga-Alonso","Nicholas Goldowsky-Dill","et al."],"boundary":"Passing a declared test does not prove the hypothesis is unique, complete, or semantically correct.","publisher":"Alignment Research Center","establishes":"The work proposes resampling-based tests for whether a hypothesized computational graph preserves behavior under declared interventions.","identifiers":[{"value":"https://www.alignmentforum.org/posts/JvZhhzycHu2Yd57RN/causal-scrubbing-a-method-for-rigorously-testing","scheme":"url"}],"publishedAt":"2022-12-06","exactLocator":"Method definition, correspondence, resampling interventions, examples, and limitations."}],"reviewEvents":[{"reviewId":"epireview_0751539b999c4973a91c257e79d937b7","scope":"source-fidelity","targetSha256":"sha256:8fd7d34fe31225012157eb78d84da4c9ffe9d0cad94226f7c27ba6ef83774949","reviewedAt":"2026-08-27T04:26:21.332Z","verdict":"approve","supersedesReviewId":null},{"reviewId":"epireview_20e19187b3e54080bbd77d4a46afc2c3","scope":"domain-fidelity","targetSha256":"sha256:8fd7d34fe31225012157eb78d84da4c9ffe9d0cad94226f7c27ba6ef83774949","reviewedAt":"2026-08-27T04:26:21.468Z","verdict":"approve","supersedesReviewId":null},{"reviewId":"epireview_fd271253e06a4886888b4e94bb45c9a6","scope":"boundary-adequacy","targetSha256":"sha256:8fd7d34fe31225012157eb78d84da4c9ffe9d0cad94226f7c27ba6ef83774949","reviewedAt":"2026-08-27T04:26:21.613Z","verdict":"approve","supersedesReviewId":null},{"reviewId":"epireview_8feca578c6184e66a500126c00b0dd83","scope":"rights-and-locator","targetSha256":"sha256:8fd7d34fe31225012157eb78d84da4c9ffe9d0cad94226f7c27ba6ef83774949","reviewedAt":"2026-08-27T04:26:21.817Z","verdict":"approve","supersedesReviewId":null}]},"privacyBoundary":"Operational actor fingerprints, bearer credentials, private reviewer profiles, affiliations, conflicts, and non-consented authority identity fields are excluded."}