{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BP76C335XI4PH3WPZIAIKHC6FR","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":"a3d464ead577611f817b00164caee52dfb06214d3958bfa17d0baa31a6bbe016","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-14T23:07:33Z","title_canon_sha256":"4f29988dba1f8b2e21f7f1e637e3590a3b117e65c0b37159323c00aa7f28b086"},"schema_version":"1.0","source":{"id":"2312.09390","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.09390","created_at":"2026-07-05T07:24:24Z"},{"alias_kind":"arxiv_version","alias_value":"2312.09390v1","created_at":"2026-07-05T07:24:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.09390","created_at":"2026-07-05T07:24:24Z"},{"alias_kind":"pith_short_12","alias_value":"BP76C335XI4P","created_at":"2026-07-05T07:24:24Z"},{"alias_kind":"pith_short_16","alias_value":"BP76C335XI4PH3WP","created_at":"2026-07-05T07:24:24Z"},{"alias_kind":"pith_short_8","alias_value":"BP76C335","created_at":"2026-07-05T07:24:24Z"}],"graph_snapshots":[{"event_id":"sha256:1a00e2cad11379ab6e6aefe2240de45f1d575ef864f976fc4af603b69c1f1fa0","target":"graph","created_at":"2026-07-05T07:24:24Z","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/2312.09390/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Widely used alignment techniques, such as reinforcement learning from human feedback (RLHF), rely on the ability of humans to supervise model behavior - for example, to evaluate whether a model faithfully followed instructions or generated safe outputs. However, future superhuman models will behave in complex ways too difficult for humans to reliably evaluate; humans will only be able to weakly supervise superhuman models. We study an analogy to this problem: can weak model supervision elicit the full capabilities of a much stronger model? We test this using a range of pretrained language mode","authors_text":"Adrien Ecoffet, Bowen Baker, Collin Burns, Ilya Sutskever, Jan Hendrik Kirchner, Jan Leike, Jeff Wu, Leo Gao, Leopold Aschenbrenner, Manas Joglekar, Pavel Izmailov, Yining Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-14T23:07:33Z","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.09390","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:fb9d825870d9be318702fc10fa1f5f58d703423c58f864bf90c603245810b8ee","target":"record","created_at":"2026-07-05T07:24:24Z","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":"a3d464ead577611f817b00164caee52dfb06214d3958bfa17d0baa31a6bbe016","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-14T23:07:33Z","title_canon_sha256":"4f29988dba1f8b2e21f7f1e637e3590a3b117e65c0b37159323c00aa7f28b086"},"schema_version":"1.0","source":{"id":"2312.09390","kind":"arxiv","version":1}},"canonical_sha256":"0bffe16f7dba38f3eecfca00851c5e2c4e46745330313c365e79c3e0fe6ff20a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0bffe16f7dba38f3eecfca00851c5e2c4e46745330313c365e79c3e0fe6ff20a","first_computed_at":"2026-07-05T07:24:24.257258Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:24:24.257258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XOTES0aOcoiMFCHDwSvAFAzKtupTQ1g1PJQZGf+zeFNpEVDBd5hiy/rA44TVqHb1yBsDDMfK7ctxuQmsSMiPDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:24:24.257760Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.09390","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb9d825870d9be318702fc10fa1f5f58d703423c58f864bf90c603245810b8ee","sha256:1a00e2cad11379ab6e6aefe2240de45f1d575ef864f976fc4af603b69c1f1fa0"],"state_sha256":"97fe801f26cb6c6a8641d71993a3a7184d240687b19c53dfcd7b88816f7f0531"}