{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:2TKXSWYJKCCBWHVZTQ4ZAJJ5DJ","short_pith_number":"pith:2TKXSWYJ","canonical_record":{"source":{"id":"2303.14177","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-24T17:38:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0ed46d8c2fb5d9c09a6d4ba869664ef23e1ab4982f94c871e082149db2ffc343","abstract_canon_sha256":"18528c59678561ee1ef21b53dbedcae707f1b500302976a207c6b6480ffafb63"},"schema_version":"1.0"},"canonical_sha256":"d4d5795b0950841b1eb99c3990253d1a5f9212a8fda6fe0847ff9d0444b59848","source":{"kind":"arxiv","id":"2303.14177","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.14177","created_at":"2026-07-05T05:54:24Z"},{"alias_kind":"arxiv_version","alias_value":"2303.14177v1","created_at":"2026-07-05T05:54:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.14177","created_at":"2026-07-05T05:54:24Z"},{"alias_kind":"pith_short_12","alias_value":"2TKXSWYJKCCB","created_at":"2026-07-05T05:54:24Z"},{"alias_kind":"pith_short_16","alias_value":"2TKXSWYJKCCBWHVZ","created_at":"2026-07-05T05:54:24Z"},{"alias_kind":"pith_short_8","alias_value":"2TKXSWYJ","created_at":"2026-07-05T05:54:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:2TKXSWYJKCCBWHVZTQ4ZAJJ5DJ","target":"record","payload":{"canonical_record":{"source":{"id":"2303.14177","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-24T17:38:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0ed46d8c2fb5d9c09a6d4ba869664ef23e1ab4982f94c871e082149db2ffc343","abstract_canon_sha256":"18528c59678561ee1ef21b53dbedcae707f1b500302976a207c6b6480ffafb63"},"schema_version":"1.0"},"canonical_sha256":"d4d5795b0950841b1eb99c3990253d1a5f9212a8fda6fe0847ff9d0444b59848","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:24.554361Z","signature_b64":"kHKDSfzORzGwSXVhqNEXF+ybd3fwGj2pTD8EsnV8zX3otnarovkaYglJVLCaWjIjSJiMDVUivWhsOUKhapmtDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4d5795b0950841b1eb99c3990253d1a5f9212a8fda6fe0847ff9d0444b59848","last_reissued_at":"2026-07-05T05:54:24.553932Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:24.553932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.14177","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:54:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wMaD1jhNEZt2B9+2Z3DUFTUpH1w6Px9jye4ofUfff+uBUX+JrhxkELsX8z2fG6h5mV6Wg2FVyhDMWwsnee3jAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:18:31.940488Z"},"content_sha256":"dfed0238dd49a13dc89d0cba06778e1fbc348aa454c2f0efc710fffd05b90a22","schema_version":"1.0","event_id":"sha256:dfed0238dd49a13dc89d0cba06778e1fbc348aa454c2f0efc710fffd05b90a22"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:2TKXSWYJKCCBWHVZTQ4ZAJJ5DJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling Expert Language Models with Unsupervised Domain Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Luke Zettlemoyer, Margaret Li, Mike Lewis, Noah A. Smith, Suchin Gururangan, Tim Althoff, Weijia Shi","submitted_at":"2023-03-24T17:38:58Z","abstract_excerpt":"Large language models are typically trained densely: all parameters are updated with respect to all inputs. This requires synchronization of billions of parameters across thousands of GPUs. We introduce a simple but effective method to asynchronously train large, sparse language models on arbitrary text corpora. Our method clusters a corpus into sets of related documents, trains a separate expert language model on each cluster, and combines them in a sparse ensemble for inference. This approach generalizes embarrassingly parallel training by automatically discovering the domains for each exper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.14177","kind":"arxiv","version":1},"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/2303.14177/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":"2026-07-05T05:54:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aOeoNhJ2kF5rJbsYW/sQKX4alNllScQSwAyMBJm3JgzHZ4uusycQvjG3lTim1Lv+7PODspZ8wTmlJGs5Jq5YCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:18:31.941010Z"},"content_sha256":"13d1ae51670c76ef1bcd01b2f6711c0881fcaf3dbb8ce8d28f7f20fe92df25d0","schema_version":"1.0","event_id":"sha256:13d1ae51670c76ef1bcd01b2f6711c0881fcaf3dbb8ce8d28f7f20fe92df25d0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2TKXSWYJKCCBWHVZTQ4ZAJJ5DJ/bundle.json","state_url":"https://pith.science/pith/2TKXSWYJKCCBWHVZTQ4ZAJJ5DJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2TKXSWYJKCCBWHVZTQ4ZAJJ5DJ/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":"2026-08-08T19:18:31Z","links":{"resolver":"https://pith.science/pith/2TKXSWYJKCCBWHVZTQ4ZAJJ5DJ","bundle":"https://pith.science/pith/2TKXSWYJKCCBWHVZTQ4ZAJJ5DJ/bundle.json","state":"https://pith.science/pith/2TKXSWYJKCCBWHVZTQ4ZAJJ5DJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2TKXSWYJKCCBWHVZTQ4ZAJJ5DJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2TKXSWYJKCCBWHVZTQ4ZAJJ5DJ","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":"18528c59678561ee1ef21b53dbedcae707f1b500302976a207c6b6480ffafb63","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-24T17:38:58Z","title_canon_sha256":"0ed46d8c2fb5d9c09a6d4ba869664ef23e1ab4982f94c871e082149db2ffc343"},"schema_version":"1.0","source":{"id":"2303.14177","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.14177","created_at":"2026-07-05T05:54:24Z"},{"alias_kind":"arxiv_version","alias_value":"2303.14177v1","created_at":"2026-07-05T05:54:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.14177","created_at":"2026-07-05T05:54:24Z"},{"alias_kind":"pith_short_12","alias_value":"2TKXSWYJKCCB","created_at":"2026-07-05T05:54:24Z"},{"alias_kind":"pith_short_16","alias_value":"2TKXSWYJKCCBWHVZ","created_at":"2026-07-05T05:54:24Z"},{"alias_kind":"pith_short_8","alias_value":"2TKXSWYJ","created_at":"2026-07-05T05:54:24Z"}],"graph_snapshots":[{"event_id":"sha256:13d1ae51670c76ef1bcd01b2f6711c0881fcaf3dbb8ce8d28f7f20fe92df25d0","target":"graph","created_at":"2026-07-05T05:54:24Z","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/2303.14177/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models are typically trained densely: all parameters are updated with respect to all inputs. This requires synchronization of billions of parameters across thousands of GPUs. We introduce a simple but effective method to asynchronously train large, sparse language models on arbitrary text corpora. Our method clusters a corpus into sets of related documents, trains a separate expert language model on each cluster, and combines them in a sparse ensemble for inference. This approach generalizes embarrassingly parallel training by automatically discovering the domains for each exper","authors_text":"Luke Zettlemoyer, Margaret Li, Mike Lewis, Noah A. Smith, Suchin Gururangan, Tim Althoff, Weijia Shi","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-24T17:38:58Z","title":"Scaling Expert Language Models with Unsupervised Domain Discovery"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.14177","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:dfed0238dd49a13dc89d0cba06778e1fbc348aa454c2f0efc710fffd05b90a22","target":"record","created_at":"2026-07-05T05:54:24Z","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":"18528c59678561ee1ef21b53dbedcae707f1b500302976a207c6b6480ffafb63","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-24T17:38:58Z","title_canon_sha256":"0ed46d8c2fb5d9c09a6d4ba869664ef23e1ab4982f94c871e082149db2ffc343"},"schema_version":"1.0","source":{"id":"2303.14177","kind":"arxiv","version":1}},"canonical_sha256":"d4d5795b0950841b1eb99c3990253d1a5f9212a8fda6fe0847ff9d0444b59848","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d4d5795b0950841b1eb99c3990253d1a5f9212a8fda6fe0847ff9d0444b59848","first_computed_at":"2026-07-05T05:54:24.553932Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:54:24.553932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kHKDSfzORzGwSXVhqNEXF+ybd3fwGj2pTD8EsnV8zX3otnarovkaYglJVLCaWjIjSJiMDVUivWhsOUKhapmtDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:54:24.554361Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.14177","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dfed0238dd49a13dc89d0cba06778e1fbc348aa454c2f0efc710fffd05b90a22","sha256:13d1ae51670c76ef1bcd01b2f6711c0881fcaf3dbb8ce8d28f7f20fe92df25d0"],"state_sha256":"424f90ce48976e94ee89d1f658ca63cfa8ca383a74786368d8017b477ef6ccab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F+KWw1jdXSuF+bRKVmMhswAX7vTCwH1lsmxLse18ra48PXxeyVyVG4HowX9fuPgnV+ekFTsv7koxEtvlC6nSDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:18:31.986278Z","bundle_sha256":"e601dbd27ee9faf98ab981b861719e090d913876fd1eb1a19db7aba494225595"}}