{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:INIGVSIUJVSX35FTGP57N7GPOX","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":"d46d8f138c21aae9f9a03b901af052e3d4e327c8d238a489a7a37efbbc425d1f","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-05T06:43:08Z","title_canon_sha256":"8bf424a2b4b3faf1a2a254bebc72eb0d7628ae3eb3437f1b24afe9706f5e4027"},"schema_version":"1.0","source":{"id":"2109.02008","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.02008","created_at":"2026-07-05T03:48:19Z"},{"alias_kind":"arxiv_version","alias_value":"2109.02008v3","created_at":"2026-07-05T03:48:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.02008","created_at":"2026-07-05T03:48:19Z"},{"alias_kind":"pith_short_12","alias_value":"INIGVSIUJVSX","created_at":"2026-07-05T03:48:19Z"},{"alias_kind":"pith_short_16","alias_value":"INIGVSIUJVSX35FT","created_at":"2026-07-05T03:48:19Z"},{"alias_kind":"pith_short_8","alias_value":"INIGVSIU","created_at":"2026-07-05T03:48:19Z"}],"graph_snapshots":[{"event_id":"sha256:8ccf0659f7bc74010091948178abe7a47a3167417cc328f98617559ba2505a6f","target":"graph","created_at":"2026-07-05T03:48:19Z","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/2109.02008/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mixture-of-Experts (MoE), a conditional computation architecture, achieved promising performance by scaling local module (i.e. feed-forward network) of transformer. However, scaling the cross-token module (i.e. self-attention) is challenging due to the unstable training. This work proposes Sparse-MLP, an all-MLP model which applies sparsely-activated MLPs to cross-token modeling. Specifically, in each Sparse block of our all-MLP model, we apply two stages of MoE layers: one with MLP experts mixing information within channels along image patch dimension, the other with MLP experts mixing inform","authors_text":"Fuzhao Xue, Yang You, Yuxuan Lou, Zangwei Zheng","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-05T06:43:08Z","title":"Cross-token Modeling with Conditional Computation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.02008","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:cff0c267a94bf68a0241c9723a75d07c01b2aac6f2b0d85022745012d942ff4c","target":"record","created_at":"2026-07-05T03:48:19Z","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":"d46d8f138c21aae9f9a03b901af052e3d4e327c8d238a489a7a37efbbc425d1f","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-05T06:43:08Z","title_canon_sha256":"8bf424a2b4b3faf1a2a254bebc72eb0d7628ae3eb3437f1b24afe9706f5e4027"},"schema_version":"1.0","source":{"id":"2109.02008","kind":"arxiv","version":3}},"canonical_sha256":"43506ac9144d657df4b333fbf6fccf75cf24aa149d905c231fbcaec3188033ec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43506ac9144d657df4b333fbf6fccf75cf24aa149d905c231fbcaec3188033ec","first_computed_at":"2026-07-05T03:48:19.027042Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:48:19.027042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"idn18ReFo/pzyCWPOI4jqRiXS5C/bg/NrLL9ar+vJhW3S7fhYIgxzXC6PZX2PBFdRP6GrZd2H1O1RHtdNhiiBg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:48:19.027551Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.02008","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cff0c267a94bf68a0241c9723a75d07c01b2aac6f2b0d85022745012d942ff4c","sha256:8ccf0659f7bc74010091948178abe7a47a3167417cc328f98617559ba2505a6f"],"state_sha256":"890d33e1fd9a2fc54c666b5961163350cb141d91a3f24e5a5740f7afb2da8951"}