{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:X4LXBMEXMK5IMIHMD4DZRPUUZL","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":"62aeb66618cae50da374caa0ebfb87ebd1fd7202402e27f8a7b255cb47d47d3f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-29T23:21:48Z","title_canon_sha256":"98436ca50737373f203f4df95a31d52e6fc727123f1a66f8b4e4e4b1e378e312"},"schema_version":"1.0","source":{"id":"2606.00424","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.00424","created_at":"2026-06-02T01:03:54Z"},{"alias_kind":"arxiv_version","alias_value":"2606.00424v1","created_at":"2026-06-02T01:03:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00424","created_at":"2026-06-02T01:03:54Z"},{"alias_kind":"pith_short_12","alias_value":"X4LXBMEXMK5I","created_at":"2026-06-02T01:03:54Z"},{"alias_kind":"pith_short_16","alias_value":"X4LXBMEXMK5IMIHM","created_at":"2026-06-02T01:03:54Z"},{"alias_kind":"pith_short_8","alias_value":"X4LXBMEX","created_at":"2026-06-02T01:03:54Z"}],"graph_snapshots":[{"event_id":"sha256:95e0ca010c67daf7de030c88f3412ee24aa226365949da7b25f031eadb64a3da","target":"graph","created_at":"2026-06-02T01:03:54Z","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/2606.00424/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As large language models become stronger, weak supervisors may fail to provide reliable labels, preferences, or final judgments for complex outputs, limiting both weak-to-strong generalization and scalable oversight. We study a more tractable form of weak supervision: using a weak model as a critic rather than as a labeler or judge. Instead of solving the task or selecting the correct answer, the weak critic only needs to provide a non-misleading revision direction that helps the strong model better use its own knowledge. We call this setting *weak-critic strong oversight*. We first show that ","authors_text":"Can Jin, Dimitris N. Metaxas, Eddy Zhang, Jiakang Li, Rui Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-29T23:21:48Z","title":"Weak Critics Make Strong Learners: On-Policy Critique Distillation for Scalable Oversight"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00424","kind":"arxiv","version":1},"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":"sha256:7ac2973f65ef1e358078b1bb4cfa19680da0adbc28b19f0f760654b225b7fc9d","target":"record","created_at":"2026-06-02T01:03:54Z","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":"62aeb66618cae50da374caa0ebfb87ebd1fd7202402e27f8a7b255cb47d47d3f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-29T23:21:48Z","title_canon_sha256":"98436ca50737373f203f4df95a31d52e6fc727123f1a66f8b4e4e4b1e378e312"},"schema_version":"1.0","source":{"id":"2606.00424","kind":"arxiv","version":1}},"canonical_sha256":"bf1770b09762ba8620ec1f0798be94cacd3455e261125568585dc793664dcaa7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf1770b09762ba8620ec1f0798be94cacd3455e261125568585dc793664dcaa7","first_computed_at":"2026-06-02T01:03:54.238980Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:54.238980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bYLpNcQy++wisW4aa4ya15W1b4uV744q3iAT3HBUNRS5zpNRo5nQWmuAA9R6JAmy4S31rYAj1w0IwfqTqStICg==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:54.239386Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.00424","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ac2973f65ef1e358078b1bb4cfa19680da0adbc28b19f0f760654b225b7fc9d","sha256:95e0ca010c67daf7de030c88f3412ee24aa226365949da7b25f031eadb64a3da"],"state_sha256":"148d441f474ec79636d1a21cac8bb611756ca68130468cbbb9e74796f4fe522b"}