{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:X55NRAQWKZICPN7FTFCW4AKPRQ","short_pith_number":"pith:X55NRAQW","canonical_record":{"source":{"id":"2112.06905","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-13T18:58:19Z","cross_cats_sorted":[],"title_canon_sha256":"1ea822aed4319341b85fc4c057b5182f6531c8966a07e8610cd0522d7fa51b38","abstract_canon_sha256":"93a133889a92f47646ab0e1d08f1045e03f91da64b6fb4708d1419209b3809e8"},"schema_version":"1.0"},"canonical_sha256":"bf7ad88216565027b7e599456e014f8c2f7fa63d8996bb6d73bf5ce1ec756ade","source":{"kind":"arxiv","id":"2112.06905","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:X55NRAQWKZICPN7FTFCW4AKPRQ","target":"record","payload":{"canonical_record":{"source":{"id":"2112.06905","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-13T18:58:19Z","cross_cats_sorted":[],"title_canon_sha256":"1ea822aed4319341b85fc4c057b5182f6531c8966a07e8610cd0522d7fa51b38","abstract_canon_sha256":"93a133889a92f47646ab0e1d08f1045e03f91da64b6fb4708d1419209b3809e8"},"schema_version":"1.0"},"canonical_sha256":"bf7ad88216565027b7e599456e014f8c2f7fa63d8996bb6d73bf5ce1ec756ade","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:45:14.339528Z","signature_b64":"GtEPL3UUUdbEygWX7fuEU0h2xDpQMIzAFP1jjHMZF8B4jzuUmyppGFGyJ1wNmfXzLA0+nM7SYxeyhjv7MvE5DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf7ad88216565027b7e599456e014f8c2f7fa63d8996bb6d73bf5ce1ec756ade","last_reissued_at":"2026-07-05T04:45:14.339106Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:45:14.339106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.06905","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:45:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9KBL6b/jjJmM088RiL+wAPgjlEc1G8+l4YBTpbVFVk3sSNkAUyIOlWxF+x23Zjnv/XQo8oL2TNiTz94+YwDaBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T23:11:26.754390Z"},"content_sha256":"0ca78400de7d920093dc07828ec8ee441ca67ce04a9516fa5b634a1964679d4e","schema_version":"1.0","event_id":"sha256:0ca78400de7d920093dc07828ec8ee441ca67ce04a9516fa5b634a1964679d4e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:X55NRAQWKZICPN7FTFCW4AKPRQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","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","submitted_at":"2021-12-13T18:58:19Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.06905","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2112.06905/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:45:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7SOzUuG6hvThp0gMsbnE2zv6sJ/WJUhjDTH3RcnIxKPY7kFS1bA5KAEb4cy8UxOqS4qU2ledhbl6uaJYTY8/Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T23:11:26.755023Z"},"content_sha256":"478dbe2834280cd28357654d65cd52e8b2c04ecab53bad468540002fca13c539","schema_version":"1.0","event_id":"sha256:478dbe2834280cd28357654d65cd52e8b2c04ecab53bad468540002fca13c539"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X55NRAQWKZICPN7FTFCW4AKPRQ/bundle.json","state_url":"https://pith.science/pith/X55NRAQWKZICPN7FTFCW4AKPRQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X55NRAQWKZICPN7FTFCW4AKPRQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-03T23:11:26Z","links":{"resolver":"https://pith.science/pith/X55NRAQWKZICPN7FTFCW4AKPRQ","bundle":"https://pith.science/pith/X55NRAQWKZICPN7FTFCW4AKPRQ/bundle.json","state":"https://pith.science/pith/X55NRAQWKZICPN7FTFCW4AKPRQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X55NRAQWKZICPN7FTFCW4AKPRQ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lj2+WiSH84ofM3UuO7KSe/URG5xDGVAGhRQmknT2ECITWimT/ZjzBnYzbAVZFQCyKW0cqsfd5x6WLdwM6Yg6Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T23:11:26.758718Z","bundle_sha256":"32fbf58ef0059c70adf26cfa2ec50d77defcf37b8f99aea5f04e11647cbdd58b"}}