{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VAUXFR5AJ4AWQSC4EMCCNBEYCB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ef4a7363820103f440af1355cd254641b27ad3173aa788f7e86a5de388ca6771","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-26T12:57:54Z","title_canon_sha256":"132e7235f577d4c72cab1903cd6a6ec5a7bb9e2a87810cf253194897069fbad2"},"schema_version":"1.0","source":{"id":"2407.18712","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.18712","created_at":"2026-07-05T09:15:35Z"},{"alias_kind":"arxiv_version","alias_value":"2407.18712v2","created_at":"2026-07-05T09:15:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18712","created_at":"2026-07-05T09:15:35Z"},{"alias_kind":"pith_short_12","alias_value":"VAUXFR5AJ4AW","created_at":"2026-07-05T09:15:35Z"},{"alias_kind":"pith_short_16","alias_value":"VAUXFR5AJ4AWQSC4","created_at":"2026-07-05T09:15:35Z"},{"alias_kind":"pith_short_8","alias_value":"VAUXFR5A","created_at":"2026-07-05T09:15:35Z"}],"graph_snapshots":[{"event_id":"sha256:3e5d5a465981aa465019340dbb1f7536cb6daa7858a5d0901896be1227fa1ee8","target":"graph","created_at":"2026-07-05T09:15:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2407.18712/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The deployment of language models brings challenges in generating reliable information, especially when these models are fine-tuned using human preferences. To extract encoded knowledge without (potentially) biased human labels, unsupervised probing techniques like Contrast-Consistent Search (CCS) have been developed (Burns et al., 2022). However, salient but unrelated features in a given dataset can mislead these probes (Farquhar et al., 2023). Addressing this, we propose a cluster normalization method to minimize the impact of such features by clustering and normalizing activations of contra","authors_text":"Gr\\'egoire Dhimo\\\"ila, Kaarel H\\\"anni, Owen (Ho Wan) Yeung, Sharan Maiya, Walter Laurito","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-26T12:57:54Z","title":"Cluster-norm for Unsupervised Probing of Knowledge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18712","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c2ca62b2fe2f9e9fc7cee422dcba1549dd909e280391d6e09a3dc3d6d998f544","target":"record","created_at":"2026-07-05T09:15:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ef4a7363820103f440af1355cd254641b27ad3173aa788f7e86a5de388ca6771","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-26T12:57:54Z","title_canon_sha256":"132e7235f577d4c72cab1903cd6a6ec5a7bb9e2a87810cf253194897069fbad2"},"schema_version":"1.0","source":{"id":"2407.18712","kind":"arxiv","version":2}},"canonical_sha256":"a82972c7a04f0168485c23042684981074de80a3575fbc6c1f0434d28ad3f12c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a82972c7a04f0168485c23042684981074de80a3575fbc6c1f0434d28ad3f12c","first_computed_at":"2026-07-05T09:15:35.312304Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:15:35.312304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ddgj86xWGiK6k4t7kQZUZBcLJAbQ6H4WUdzEn8sqJwMd0yeI0OGTCpWCSeVxnvTGRYmyxXoox0eusnIg0N6/Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T09:15:35.312836Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.18712","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2ca62b2fe2f9e9fc7cee422dcba1549dd909e280391d6e09a3dc3d6d998f544","sha256:3e5d5a465981aa465019340dbb1f7536cb6daa7858a5d0901896be1227fa1ee8"],"state_sha256":"becd974ec438f0892f7450043b145b747148d9e0d5fe16d7fe247c79f133bdff"}