{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VQRXQ2FB35O56N66UOSM7AVS37","short_pith_number":"pith:VQRXQ2FB","canonical_record":{"source":{"id":"2306.01470","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-02T11:51:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"13a1e0747dbd61f022c8d5be09f0df7205f3390a1538efbb62632cff6c6f9a56","abstract_canon_sha256":"ecefac3aa9b9896893d1b4a0f24a6a88fcb87f6a11c76209ecce86901b1600c6"},"schema_version":"1.0"},"canonical_sha256":"ac237868a1df5ddf37dea3a4cf82b2dff0f906361463d2145bd881b138f64c52","source":{"kind":"arxiv","id":"2306.01470","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.01470","created_at":"2026-07-05T08:16:07Z"},{"alias_kind":"arxiv_version","alias_value":"2306.01470v2","created_at":"2026-07-05T08:16:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01470","created_at":"2026-07-05T08:16:07Z"},{"alias_kind":"pith_short_12","alias_value":"VQRXQ2FB35O5","created_at":"2026-07-05T08:16:07Z"},{"alias_kind":"pith_short_16","alias_value":"VQRXQ2FB35O56N66","created_at":"2026-07-05T08:16:07Z"},{"alias_kind":"pith_short_8","alias_value":"VQRXQ2FB","created_at":"2026-07-05T08:16:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VQRXQ2FB35O56N66UOSM7AVS37","target":"record","payload":{"canonical_record":{"source":{"id":"2306.01470","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-02T11:51:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"13a1e0747dbd61f022c8d5be09f0df7205f3390a1538efbb62632cff6c6f9a56","abstract_canon_sha256":"ecefac3aa9b9896893d1b4a0f24a6a88fcb87f6a11c76209ecce86901b1600c6"},"schema_version":"1.0"},"canonical_sha256":"ac237868a1df5ddf37dea3a4cf82b2dff0f906361463d2145bd881b138f64c52","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:16:07.030544Z","signature_b64":"qt2wxNhoujfVsNT46GYYTBKjaNLIfnDFzcJI75iP12Bfse4hoXrD34jDfM94xaQS1QnBJLKCkW2yy39ypHyBAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac237868a1df5ddf37dea3a4cf82b2dff0f906361463d2145bd881b138f64c52","last_reissued_at":"2026-07-05T08:16:07.030064Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:16:07.030064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.01470","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:16:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PZ+WpVoKI3ZqYVWMJtgOGWarZKmISWTrMASLHn19KnPKosnT8sIiRZAA+Jm1cQCpn86hJpmV0L6HpzzJuswyCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:41:21.647137Z"},"content_sha256":"f5bdce77cea79e0a67b683c42bb9079d25d8c6d208e9e08e59c1c74df24b05fc","schema_version":"1.0","event_id":"sha256:f5bdce77cea79e0a67b683c42bb9079d25d8c6d208e9e08e59c1c74df24b05fc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VQRXQ2FB35O56N66UOSM7AVS37","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding MLP-Mixer as a Wide and Sparse MLP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ryo Karakida, Tomohiro Hayase","submitted_at":"2023-06-02T11:51:24Z","abstract_excerpt":"Multi-layer perceptron (MLP) is a fundamental component of deep learning, and recent MLP-based architectures, especially the MLP-Mixer, have achieved significant empirical success. Nevertheless, our understanding of why and how the MLP-Mixer outperforms conventional MLPs remains largely unexplored. In this work, we reveal that sparseness is a key mechanism underlying the MLP-Mixers. First, the Mixers have an effective expression as a wider MLP with Kronecker-product weights, clarifying that the Mixers efficiently embody several sparseness properties explored in deep learning. In the case of li"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01470","kind":"arxiv","version":2},"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/2306.01470/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":"2026-07-05T08:16:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KbV289YRRNUv97DUECHpV5+QrQ0zwkxLtCpTJtjZQdq1XIhQAW+z6YF7mlFr9Vif/e66WwaciR3QkS9LdnKSBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:41:21.647631Z"},"content_sha256":"1f7ed10b3af23b3900f6714c6b4a42e3c4e3406211b20eebe9dd6d35d4a9960d","schema_version":"1.0","event_id":"sha256:1f7ed10b3af23b3900f6714c6b4a42e3c4e3406211b20eebe9dd6d35d4a9960d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VQRXQ2FB35O56N66UOSM7AVS37/bundle.json","state_url":"https://pith.science/pith/VQRXQ2FB35O56N66UOSM7AVS37/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VQRXQ2FB35O56N66UOSM7AVS37/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":"2026-08-08T19:41:21Z","links":{"resolver":"https://pith.science/pith/VQRXQ2FB35O56N66UOSM7AVS37","bundle":"https://pith.science/pith/VQRXQ2FB35O56N66UOSM7AVS37/bundle.json","state":"https://pith.science/pith/VQRXQ2FB35O56N66UOSM7AVS37/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VQRXQ2FB35O56N66UOSM7AVS37/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VQRXQ2FB35O56N66UOSM7AVS37","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":"ecefac3aa9b9896893d1b4a0f24a6a88fcb87f6a11c76209ecce86901b1600c6","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-02T11:51:24Z","title_canon_sha256":"13a1e0747dbd61f022c8d5be09f0df7205f3390a1538efbb62632cff6c6f9a56"},"schema_version":"1.0","source":{"id":"2306.01470","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.01470","created_at":"2026-07-05T08:16:07Z"},{"alias_kind":"arxiv_version","alias_value":"2306.01470v2","created_at":"2026-07-05T08:16:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01470","created_at":"2026-07-05T08:16:07Z"},{"alias_kind":"pith_short_12","alias_value":"VQRXQ2FB35O5","created_at":"2026-07-05T08:16:07Z"},{"alias_kind":"pith_short_16","alias_value":"VQRXQ2FB35O56N66","created_at":"2026-07-05T08:16:07Z"},{"alias_kind":"pith_short_8","alias_value":"VQRXQ2FB","created_at":"2026-07-05T08:16:07Z"}],"graph_snapshots":[{"event_id":"sha256:1f7ed10b3af23b3900f6714c6b4a42e3c4e3406211b20eebe9dd6d35d4a9960d","target":"graph","created_at":"2026-07-05T08:16:07Z","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/2306.01470/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-layer perceptron (MLP) is a fundamental component of deep learning, and recent MLP-based architectures, especially the MLP-Mixer, have achieved significant empirical success. Nevertheless, our understanding of why and how the MLP-Mixer outperforms conventional MLPs remains largely unexplored. In this work, we reveal that sparseness is a key mechanism underlying the MLP-Mixers. First, the Mixers have an effective expression as a wider MLP with Kronecker-product weights, clarifying that the Mixers efficiently embody several sparseness properties explored in deep learning. In the case of li","authors_text":"Ryo Karakida, Tomohiro Hayase","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-02T11:51:24Z","title":"Understanding MLP-Mixer as a Wide and Sparse MLP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01470","kind":"arxiv","version":2},"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:f5bdce77cea79e0a67b683c42bb9079d25d8c6d208e9e08e59c1c74df24b05fc","target":"record","created_at":"2026-07-05T08:16:07Z","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":"ecefac3aa9b9896893d1b4a0f24a6a88fcb87f6a11c76209ecce86901b1600c6","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-02T11:51:24Z","title_canon_sha256":"13a1e0747dbd61f022c8d5be09f0df7205f3390a1538efbb62632cff6c6f9a56"},"schema_version":"1.0","source":{"id":"2306.01470","kind":"arxiv","version":2}},"canonical_sha256":"ac237868a1df5ddf37dea3a4cf82b2dff0f906361463d2145bd881b138f64c52","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac237868a1df5ddf37dea3a4cf82b2dff0f906361463d2145bd881b138f64c52","first_computed_at":"2026-07-05T08:16:07.030064Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:16:07.030064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qt2wxNhoujfVsNT46GYYTBKjaNLIfnDFzcJI75iP12Bfse4hoXrD34jDfM94xaQS1QnBJLKCkW2yy39ypHyBAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:16:07.030544Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.01470","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5bdce77cea79e0a67b683c42bb9079d25d8c6d208e9e08e59c1c74df24b05fc","sha256:1f7ed10b3af23b3900f6714c6b4a42e3c4e3406211b20eebe9dd6d35d4a9960d"],"state_sha256":"358af8d878362d191a57c9aed7d0247e7de6d5643443fb45bafa1ddd072b5f35"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QDKRKo8LHRkfOZuTDuJ4Kgyd8SUby/BZWK8xnEqcRM/n6f2qzDHRYtRa6102Lnmoa5CbIs7i92dKa3Vdcm49AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:41:21.652833Z","bundle_sha256":"d50beaed9199335225aa38fa06fbf172e761d6f544bd85cb704714047b814f87"}}