{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:INIGVSIUJVSX35FTGP57N7GPOX","short_pith_number":"pith:INIGVSIU","canonical_record":{"source":{"id":"2109.02008","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-05T06:43:08Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"8bf424a2b4b3faf1a2a254bebc72eb0d7628ae3eb3437f1b24afe9706f5e4027","abstract_canon_sha256":"d46d8f138c21aae9f9a03b901af052e3d4e327c8d238a489a7a37efbbc425d1f"},"schema_version":"1.0"},"canonical_sha256":"43506ac9144d657df4b333fbf6fccf75cf24aa149d905c231fbcaec3188033ec","source":{"kind":"arxiv","id":"2109.02008","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:INIGVSIUJVSX35FTGP57N7GPOX","target":"record","payload":{"canonical_record":{"source":{"id":"2109.02008","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-05T06:43:08Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"8bf424a2b4b3faf1a2a254bebc72eb0d7628ae3eb3437f1b24afe9706f5e4027","abstract_canon_sha256":"d46d8f138c21aae9f9a03b901af052e3d4e327c8d238a489a7a37efbbc425d1f"},"schema_version":"1.0"},"canonical_sha256":"43506ac9144d657df4b333fbf6fccf75cf24aa149d905c231fbcaec3188033ec","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:48:19.027551Z","signature_b64":"idn18ReFo/pzyCWPOI4jqRiXS5C/bg/NrLL9ar+vJhW3S7fhYIgxzXC6PZX2PBFdRP6GrZd2H1O1RHtdNhiiBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43506ac9144d657df4b333fbf6fccf75cf24aa149d905c231fbcaec3188033ec","last_reissued_at":"2026-07-05T03:48:19.027042Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:48:19.027042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.02008","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:48:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4Z46stvG24XJLLGoldmJTzmXyi3oqX+F1V/evSxl7IImP+fh8ye5XVTHfffcV/sGOLSdOzlRXOcCnDUdYlYGCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:25:23.806301Z"},"content_sha256":"cff0c267a94bf68a0241c9723a75d07c01b2aac6f2b0d85022745012d942ff4c","schema_version":"1.0","event_id":"sha256:cff0c267a94bf68a0241c9723a75d07c01b2aac6f2b0d85022745012d942ff4c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:INIGVSIUJVSX35FTGP57N7GPOX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cross-token Modeling with Conditional Computation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Fuzhao Xue, Yang You, Yuxuan Lou, Zangwei Zheng","submitted_at":"2021-09-05T06:43:08Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.02008","kind":"arxiv","version":3},"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/2109.02008/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":"2026-07-05T03:48:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6vfQ6/8QlBcV8Us753HqWMiysS31B8ElJU0RmyUv/ZqGlK1j7KZYywnysNCeH+WYRPMGTIAUV7n3SmQy1Wo+AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:25:23.806797Z"},"content_sha256":"8ccf0659f7bc74010091948178abe7a47a3167417cc328f98617559ba2505a6f","schema_version":"1.0","event_id":"sha256:8ccf0659f7bc74010091948178abe7a47a3167417cc328f98617559ba2505a6f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/INIGVSIUJVSX35FTGP57N7GPOX/bundle.json","state_url":"https://pith.science/pith/INIGVSIUJVSX35FTGP57N7GPOX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/INIGVSIUJVSX35FTGP57N7GPOX/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":"2026-08-09T13:25:23Z","links":{"resolver":"https://pith.science/pith/INIGVSIUJVSX35FTGP57N7GPOX","bundle":"https://pith.science/pith/INIGVSIUJVSX35FTGP57N7GPOX/bundle.json","state":"https://pith.science/pith/INIGVSIUJVSX35FTGP57N7GPOX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/INIGVSIUJVSX35FTGP57N7GPOX/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gFOvF9mUeA6yQ/rOADOyR7diCRptOXpLrTOVgbkcgqyEEy+izH6ZRRnnrar9sUDJ9rneIKVHfXknswED266+DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T13:25:23.811874Z","bundle_sha256":"688e5ffa4bdbfe8bc0a4794d81acd5f24b31e8a19c567a6a848c5722604dfe2c"}}