{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VQRXQ2FB35O56N66UOSM7AVS37","short_pith_number":"pith:VQRXQ2FB","schema_version":"1.0","canonical_sha256":"ac237868a1df5ddf37dea3a4cf82b2dff0f906361463d2145bd881b138f64c52","source":{"kind":"arxiv","id":"2306.01470","version":2},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2306.01470","created_at":"2026-07-05T08:16:07.030128+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.01470v2","created_at":"2026-07-05T08:16:07.030128+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01470","created_at":"2026-07-05T08:16:07.030128+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQRXQ2FB35O5","created_at":"2026-07-05T08:16:07.030128+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQRXQ2FB35O56N66","created_at":"2026-07-05T08:16:07.030128+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQRXQ2FB","created_at":"2026-07-05T08:16:07.030128+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.09204","citing_title":"A Topological Improvement of the Overall Performance of Sparse Evolutionary Training: Motif-Based Structural Optimization of Sparse MLPs Project","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VQRXQ2FB35O56N66UOSM7AVS37","json":"https://pith.science/pith/VQRXQ2FB35O56N66UOSM7AVS37.json","graph_json":"https://pith.science/api/pith-number/VQRXQ2FB35O56N66UOSM7AVS37/graph.json","events_json":"https://pith.science/api/pith-number/VQRXQ2FB35O56N66UOSM7AVS37/events.json","paper":"https://pith.science/paper/VQRXQ2FB"},"agent_actions":{"view_html":"https://pith.science/pith/VQRXQ2FB35O56N66UOSM7AVS37","download_json":"https://pith.science/pith/VQRXQ2FB35O56N66UOSM7AVS37.json","view_paper":"https://pith.science/paper/VQRXQ2FB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.01470&json=true","fetch_graph":"https://pith.science/api/pith-number/VQRXQ2FB35O56N66UOSM7AVS37/graph.json","fetch_events":"https://pith.science/api/pith-number/VQRXQ2FB35O56N66UOSM7AVS37/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQRXQ2FB35O56N66UOSM7AVS37/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQRXQ2FB35O56N66UOSM7AVS37/action/storage_attestation","attest_author":"https://pith.science/pith/VQRXQ2FB35O56N66UOSM7AVS37/action/author_attestation","sign_citation":"https://pith.science/pith/VQRXQ2FB35O56N66UOSM7AVS37/action/citation_signature","submit_replication":"https://pith.science/pith/VQRXQ2FB35O56N66UOSM7AVS37/action/replication_record"}},"created_at":"2026-07-05T08:16:07.030128+00:00","updated_at":"2026-07-05T08:16:07.030128+00:00"}