{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:B4OLSWL72GSKFSHGAWWCEZ6UNL","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":"2e57b3e19564c76687644fc85993de3a3e815d43c3b42a1b33264b87aa61d17c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T18:19:56Z","title_canon_sha256":"8fdfbab319c762085f93750e34158d04f747dd43614f652dcffca89b177e671e"},"schema_version":"1.0","source":{"id":"2311.10768","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.10768","created_at":"2026-07-05T07:13:57Z"},{"alias_kind":"arxiv_version","alias_value":"2311.10768v1","created_at":"2026-07-05T07:13:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.10768","created_at":"2026-07-05T07:13:57Z"},{"alias_kind":"pith_short_12","alias_value":"B4OLSWL72GSK","created_at":"2026-07-05T07:13:57Z"},{"alias_kind":"pith_short_16","alias_value":"B4OLSWL72GSKFSHG","created_at":"2026-07-05T07:13:57Z"},{"alias_kind":"pith_short_8","alias_value":"B4OLSWL7","created_at":"2026-07-05T07:13:57Z"}],"graph_snapshots":[{"event_id":"sha256:ab64546d38e385450ae3c3cda65a5fb5cd616b651c880846d170987ce9dacc2b","target":"graph","created_at":"2026-07-05T07:13:57Z","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/2311.10768/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scaling up the number of parameters of language models has proven to be an effective approach to improve performance. For dense models, increasing model size proportionally increases the model's computation footprint. In this work, we seek to aggressively decouple learning capacity and FLOPs through Mixture-of-Experts (MoE) style models with large knowledge-rich vocabulary based routing functions and experts. Our proposed approach, dubbed Mixture of Word Experts (MoWE), can be seen as a memory augmented model, where a large set of word-specific experts play the role of a sparse memory. We demo","authors_text":"Chung-Ching Chang, Cicero Nogueira dos Santos, David Uthus, Isaac Noble, James Lee-Thorp","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T18:19:56Z","title":"Memory Augmented Language Models through Mixture of Word Experts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.10768","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":"sha256:115e406adadec891afb9f4c21b2975aa58151f05c54200342ba183d368834cd3","target":"record","created_at":"2026-07-05T07:13:57Z","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":"2e57b3e19564c76687644fc85993de3a3e815d43c3b42a1b33264b87aa61d17c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T18:19:56Z","title_canon_sha256":"8fdfbab319c762085f93750e34158d04f747dd43614f652dcffca89b177e671e"},"schema_version":"1.0","source":{"id":"2311.10768","kind":"arxiv","version":1}},"canonical_sha256":"0f1cb9597fd1a4a2c8e605ac2267d46ada1e23c74b2b5fd8e0ed496ba93dbb0d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f1cb9597fd1a4a2c8e605ac2267d46ada1e23c74b2b5fd8e0ed496ba93dbb0d","first_computed_at":"2026-07-05T07:13:57.191693Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:13:57.191693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"56wzGT/0kfYLvdeTjb7lDu8V58ROBsrpI8HInin/lq4CNdrdfhM3AfCeI1Di2E0bmQLVDiNRvA5u837xI6PUBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:13:57.192167Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.10768","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:115e406adadec891afb9f4c21b2975aa58151f05c54200342ba183d368834cd3","sha256:ab64546d38e385450ae3c3cda65a5fb5cd616b651c880846d170987ce9dacc2b"],"state_sha256":"f7b003948e1f8ada8522e14afac8d199d36b62417361545e2e8868730a3b733e"}