{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CKWX33GBOIO45WIXQOIWAX2ZAA","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":"d3f01a1848a198a061249030b33b5786fa46661ed5d3eedc96eb9de561464233","cross_cats_sorted":["cs.CL","cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-02T20:24:17Z","title_canon_sha256":"f6f00eb84115be9200f8dacd9d1852b04f56151dbcc4c16bb3c334b583283e05"},"schema_version":"1.0","source":{"id":"2412.01951","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.01951","created_at":"2026-07-05T09:44:17Z"},{"alias_kind":"arxiv_version","alias_value":"2412.01951v2","created_at":"2026-07-05T09:44:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01951","created_at":"2026-07-05T09:44:17Z"},{"alias_kind":"pith_short_12","alias_value":"CKWX33GBOIO4","created_at":"2026-07-05T09:44:17Z"},{"alias_kind":"pith_short_16","alias_value":"CKWX33GBOIO45WIX","created_at":"2026-07-05T09:44:17Z"},{"alias_kind":"pith_short_8","alias_value":"CKWX33GB","created_at":"2026-07-05T09:44:17Z"}],"graph_snapshots":[{"event_id":"sha256:e3a5050b327fc9d5f1a3ae7741f43ade1a5cde5900544bec94fe7b1e87bcaf27","target":"graph","created_at":"2026-07-05T09:44:17Z","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/2412.01951/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work in language modeling has raised the possibility of self-improvement, where a language models evaluates and refines its own generations to achieve higher performance without external feedback. It is impossible for this self-improvement to create information that is not already in the model, so why should we expect that this will lead to improved capabilities? We offer a new perspective on the capabilities of self-improvement through a lens we refer to as sharpening. Motivated by the observation that language models are often better at verifying response quality than they are at gene","authors_text":"Adam Block, Akshay Krishnamurthy, Audrey Huang, Cyril Zhang, Dhruv Rohatgi, Dylan J. Foster, Jordan T. Ash, Max Simchowitz","cross_cats":["cs.CL","cs.LG","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-02T20:24:17Z","title":"Self-Improvement in Language Models: The Sharpening Mechanism"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01951","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:b63774f4b60fc4e82f0a205f7aac325fabf86f415fe3a41ae3128687afcefa7e","target":"record","created_at":"2026-07-05T09:44:17Z","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":"d3f01a1848a198a061249030b33b5786fa46661ed5d3eedc96eb9de561464233","cross_cats_sorted":["cs.CL","cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-02T20:24:17Z","title_canon_sha256":"f6f00eb84115be9200f8dacd9d1852b04f56151dbcc4c16bb3c334b583283e05"},"schema_version":"1.0","source":{"id":"2412.01951","kind":"arxiv","version":2}},"canonical_sha256":"12ad7decc1721dced9178391605f59002787b79ae4c0af05b1514e483ca52e01","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"12ad7decc1721dced9178391605f59002787b79ae4c0af05b1514e483ca52e01","first_computed_at":"2026-07-05T09:44:17.840853Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:44:17.840853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D/7Q5oQ8hd9OvTCeXI/NKBlf2s2mW2+XhVT34Xzm4W+05i4XT3paPoUlJNttgw4bGobXr+zCcXpNqED1FTpGCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:44:17.841325Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.01951","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b63774f4b60fc4e82f0a205f7aac325fabf86f415fe3a41ae3128687afcefa7e","sha256:e3a5050b327fc9d5f1a3ae7741f43ade1a5cde5900544bec94fe7b1e87bcaf27"],"state_sha256":"99f3ddee809208095196988fed4e160cec8969fcf9cc33afd7bbf75cb29419ca"}