{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:X55NRAQWKZICPN7FTFCW4AKPRQ","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":"93a133889a92f47646ab0e1d08f1045e03f91da64b6fb4708d1419209b3809e8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-13T18:58:19Z","title_canon_sha256":"1ea822aed4319341b85fc4c057b5182f6531c8966a07e8610cd0522d7fa51b38"},"schema_version":"1.0","source":{"id":"2112.06905","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.06905","created_at":"2026-07-05T04:45:14Z"},{"alias_kind":"arxiv_version","alias_value":"2112.06905v2","created_at":"2026-07-05T04:45:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.06905","created_at":"2026-07-05T04:45:14Z"},{"alias_kind":"pith_short_12","alias_value":"X55NRAQWKZIC","created_at":"2026-07-05T04:45:14Z"},{"alias_kind":"pith_short_16","alias_value":"X55NRAQWKZICPN7F","created_at":"2026-07-05T04:45:14Z"},{"alias_kind":"pith_short_8","alias_value":"X55NRAQW","created_at":"2026-07-05T04:45:14Z"}],"graph_snapshots":[{"event_id":"sha256:478dbe2834280cd28357654d65cd52e8b2c04ecab53bad468540002fca13c539","target":"graph","created_at":"2026-07-05T04:45:14Z","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/2112.06905/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scaling language models with more data, compute and parameters has driven significant progress in natural language processing. For example, thanks to scaling, GPT-3 was able to achieve strong results on in-context learning tasks. However, training these large dense models requires significant amounts of computing resources. In this paper, we propose and develop a family of language models named GLaM (Generalist Language Model), which uses a sparsely activated mixture-of-experts architecture to scale the model capacity while also incurring substantially less training cost compared to dense vari","authors_text":"Adams Wei Yu, Andrew M. Dai, Barret Zoph, Claire Cui, Dmitry Lepikhin, Kathleen Meier-Hellstern, Kellie Webster, Kevin Robinson, Kun Zhang, Liam Fedus, Lucas Dixon, Maarten Bosma, Marie Pellat, Maxim Krikun, Nan Du, Orhan Firat, Quoc V Le, Simon Tong, Tao Wang, Toju Duke, Yanping Huang, Yanqi Zhou, Yonghui Wu, Yuanzhong Xu, Yu Emma Wang, Zhifeng Chen, Zongwei Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-13T18:58:19Z","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.06905","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":"sha256:0ca78400de7d920093dc07828ec8ee441ca67ce04a9516fa5b634a1964679d4e","target":"record","created_at":"2026-07-05T04:45:14Z","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":"93a133889a92f47646ab0e1d08f1045e03f91da64b6fb4708d1419209b3809e8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-13T18:58:19Z","title_canon_sha256":"1ea822aed4319341b85fc4c057b5182f6531c8966a07e8610cd0522d7fa51b38"},"schema_version":"1.0","source":{"id":"2112.06905","kind":"arxiv","version":2}},"canonical_sha256":"bf7ad88216565027b7e599456e014f8c2f7fa63d8996bb6d73bf5ce1ec756ade","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf7ad88216565027b7e599456e014f8c2f7fa63d8996bb6d73bf5ce1ec756ade","first_computed_at":"2026-07-05T04:45:14.339106Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:45:14.339106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GtEPL3UUUdbEygWX7fuEU0h2xDpQMIzAFP1jjHMZF8B4jzuUmyppGFGyJ1wNmfXzLA0+nM7SYxeyhjv7MvE5DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:45:14.339528Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.06905","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ca78400de7d920093dc07828ec8ee441ca67ce04a9516fa5b634a1964679d4e","sha256:478dbe2834280cd28357654d65cd52e8b2c04ecab53bad468540002fca13c539"],"state_sha256":"3c08a0acd8fbd8df2460aaff518a4820fd101520845c2fb521586477965c0274"}