{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:DXWSLSXWO666DU2ZO7PKWKHRY2","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":"962779239eda5acdb8bffb82534aea5d7d0fc96ef455bb1ea65afa9d23ed1fe6","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-20T16:46:41Z","title_canon_sha256":"d5ff3a45f367e73bfa224e5e0a10df619be94b1ef58fb7746d3c70cc26471210"},"schema_version":"1.0","source":{"id":"2210.11399","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.11399","created_at":"2026-07-05T05:16:36Z"},{"alias_kind":"arxiv_version","alias_value":"2210.11399v2","created_at":"2026-07-05T05:16:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.11399","created_at":"2026-07-05T05:16:36Z"},{"alias_kind":"pith_short_12","alias_value":"DXWSLSXWO666","created_at":"2026-07-05T05:16:36Z"},{"alias_kind":"pith_short_16","alias_value":"DXWSLSXWO666DU2Z","created_at":"2026-07-05T05:16:36Z"},{"alias_kind":"pith_short_8","alias_value":"DXWSLSXW","created_at":"2026-07-05T05:16:36Z"}],"graph_snapshots":[{"event_id":"sha256:e79e598d6be8d5c0b2520e90dc576f82a299ac1713ee935bdd7d08beb011b722","target":"graph","created_at":"2026-07-05T05:16:36Z","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/2210.11399/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scaling language models improves performance but comes with significant computational costs. This paper proposes UL2R, a method that substantially improves existing language models and their scaling curves with a relatively tiny amount of extra compute. The key idea is to continue training a state-of-the-art large language model (e.g., PaLM) on a few more steps with UL2's mixture-of-denoiser objective. We show that, with almost negligible extra computational costs and no new sources of data, we are able to substantially improve the scaling properties of large language models on downstream metr","authors_text":"Aakanksha Chowdhery, David R. So, Denny Zhou, Donald Metzler, Huaixiu Steven Zheng, Hyung Won Chung, Jason Wei, Jinfeng Rao, Mostafa Dehghani, Neil Houlsby, Quoc V. Le, Siamak Shakeri, Slav Petrov, Vinh Q. Tran, Xavier Garcia, Yi Tay","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-20T16:46:41Z","title":"Transcending Scaling Laws with 0.1% Extra Compute"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.11399","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":"sha256:9010ce4c120e178662b515cd8f25f258d4ccf71e29dbd9ebe700f3c6a05af371","target":"record","created_at":"2026-07-05T05:16:36Z","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":"962779239eda5acdb8bffb82534aea5d7d0fc96ef455bb1ea65afa9d23ed1fe6","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-20T16:46:41Z","title_canon_sha256":"d5ff3a45f367e73bfa224e5e0a10df619be94b1ef58fb7746d3c70cc26471210"},"schema_version":"1.0","source":{"id":"2210.11399","kind":"arxiv","version":2}},"canonical_sha256":"1ded25caf677bde1d35977deab28f1c68b48771a0b090bd910af5d45f8851bbd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ded25caf677bde1d35977deab28f1c68b48771a0b090bd910af5d45f8851bbd","first_computed_at":"2026-07-05T05:16:36.954906Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:16:36.954906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aDzDz6qjMIbLm0UlKw+zt6JX0g3NNJiAgbWJO25kTLYhWAO7MLs3DBo1XGR9XKahYJdx4rfn4MwjeUALTRvsAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:16:36.955406Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.11399","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9010ce4c120e178662b515cd8f25f258d4ccf71e29dbd9ebe700f3c6a05af371","sha256:e79e598d6be8d5c0b2520e90dc576f82a299ac1713ee935bdd7d08beb011b722"],"state_sha256":"6d5c69451f38a036394580c6026972df291378f8b6aca8d236dc3d95bdeec15a"}