{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YJS7OYRUBMHL6YKANM4ZI2IPNK","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":"6d3a600682a7727f038c55bb61f1475039297786cfcd04b47476356313dc8a6c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T12:28:37Z","title_canon_sha256":"90244bc870fc1accb497ab7f612a3bf0339b307314d21f6059a7c2c23e83b4fc"},"schema_version":"1.0","source":{"id":"2305.13999","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13999","created_at":"2026-07-05T07:04:16Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13999v3","created_at":"2026-07-05T07:04:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13999","created_at":"2026-07-05T07:04:16Z"},{"alias_kind":"pith_short_12","alias_value":"YJS7OYRUBMHL","created_at":"2026-07-05T07:04:16Z"},{"alias_kind":"pith_short_16","alias_value":"YJS7OYRUBMHL6YKA","created_at":"2026-07-05T07:04:16Z"},{"alias_kind":"pith_short_8","alias_value":"YJS7OYRU","created_at":"2026-07-05T07:04:16Z"}],"graph_snapshots":[{"event_id":"sha256:07cbf420388741e8a4dfe3b710370b4cf72724e65282bdb9fdcf1b3cc45e9baf","target":"graph","created_at":"2026-07-05T07:04:16Z","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/2305.13999/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large and sparse feed-forward layers (S-FFN) such as Mixture-of-Experts (MoE) have proven effective in scaling up Transformers model size for \\textit{pretraining} large language models. By only activating part of the FFN parameters conditioning on input, S-FFN improves generalization performance while keeping training and inference costs (in FLOPs) fixed. In this work, we analyzed two major design choices of S-FFN: the memory block (a.k.a. expert) size and the memory block selection method under a general conceptual framework of sparse neural memory. Using this unified framework, we compare se","authors_text":"Tim Dettmers, Veselin Stoyanov, Xian Li, Xi Victoria Lin, Zeyu Leo Liu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T12:28:37Z","title":"Towards A Unified View of Sparse Feed-Forward Network in Pretraining Large Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13999","kind":"arxiv","version":3},"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:d8ea1d04a73500c87073dea33537c7f6ccb49e4ee8c11cd9e8ed6e9145995860","target":"record","created_at":"2026-07-05T07:04:16Z","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":"6d3a600682a7727f038c55bb61f1475039297786cfcd04b47476356313dc8a6c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T12:28:37Z","title_canon_sha256":"90244bc870fc1accb497ab7f612a3bf0339b307314d21f6059a7c2c23e83b4fc"},"schema_version":"1.0","source":{"id":"2305.13999","kind":"arxiv","version":3}},"canonical_sha256":"c265f762340b0ebf61406b3994690f6a8f905e51a7310f829ae238fa3052accf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c265f762340b0ebf61406b3994690f6a8f905e51a7310f829ae238fa3052accf","first_computed_at":"2026-07-05T07:04:16.107380Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:04:16.107380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AJlMrYJyFTr6dUh5mfc/NDHFPRrv+7Jj7K6OOCGzFTE592g/zqtfeOuEb/DN3DqRESV+wgU9weoDlgr7laPQDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:04:16.107823Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.13999","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d8ea1d04a73500c87073dea33537c7f6ccb49e4ee8c11cd9e8ed6e9145995860","sha256:07cbf420388741e8a4dfe3b710370b4cf72724e65282bdb9fdcf1b3cc45e9baf"],"state_sha256":"afd3faad92ff26c4110f9d7bdb0b249e1407021f5eff2535bb9275b43dccc853"}