{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ISCP4YANF6VVNR63S5P32VLO5R","short_pith_number":"pith:ISCP4YAN","schema_version":"1.0","canonical_sha256":"4484fe600d2fab56c7db975fbd556eec4feef60d70413842d37c8699b76d519b","source":{"kind":"arxiv","id":"2406.16168","version":1},"attestation_state":"computed","paper":{"title":"An All-MLP Sequence Modeling Architecture That Excels at Copying","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenwei Cui, Gedeon Muhawenayo, Hannah Kerner, Zehao Yan","submitted_at":"2024-06-23T17:19:26Z","abstract_excerpt":"Recent work demonstrated Transformers' ability to efficiently copy strings of exponential sizes, distinguishing them from other architectures. We present the Causal Relation Network (CausalRN), an all-MLP sequence modeling architecture that can match Transformers on the copying task. Extending Relation Networks (RNs), we implemented key innovations to support autoregressive sequence modeling while maintaining computational feasibility. We discovered that exponentially-activated RNs are reducible to linear time complexity, and pre-activation normalization induces an infinitely growing memory po"},"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":"2406.16168","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-23T17:19:26Z","cross_cats_sorted":[],"title_canon_sha256":"960d27d5759374e4325b597132cacde276fecc0d921d02a601db2dc8d28d770a","abstract_canon_sha256":"02dc606d346acb07813d7bbc60071ccbd8f766b4b155476d860e7dc72c583000"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:54.371045Z","signature_b64":"sCeeMLAtO+CuQE0EqFzxmtJ/vS6bCWZ4psCovjlsEy7pMZggWop3W+JYMGE9jk3jOEe1Re8IPDE38cHVcBHTBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4484fe600d2fab56c7db975fbd556eec4feef60d70413842d37c8699b76d519b","last_reissued_at":"2026-07-05T08:35:54.370600Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:54.370600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An All-MLP Sequence Modeling Architecture That Excels at Copying","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenwei Cui, Gedeon Muhawenayo, Hannah Kerner, Zehao Yan","submitted_at":"2024-06-23T17:19:26Z","abstract_excerpt":"Recent work demonstrated Transformers' ability to efficiently copy strings of exponential sizes, distinguishing them from other architectures. We present the Causal Relation Network (CausalRN), an all-MLP sequence modeling architecture that can match Transformers on the copying task. Extending Relation Networks (RNs), we implemented key innovations to support autoregressive sequence modeling while maintaining computational feasibility. We discovered that exponentially-activated RNs are reducible to linear time complexity, and pre-activation normalization induces an infinitely growing memory po"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16168","kind":"arxiv","version":1},"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/2406.16168/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":"2406.16168","created_at":"2026-07-05T08:35:54.370655+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.16168v1","created_at":"2026-07-05T08:35:54.370655+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16168","created_at":"2026-07-05T08:35:54.370655+00:00"},{"alias_kind":"pith_short_12","alias_value":"ISCP4YANF6VV","created_at":"2026-07-05T08:35:54.370655+00:00"},{"alias_kind":"pith_short_16","alias_value":"ISCP4YANF6VVNR63","created_at":"2026-07-05T08:35:54.370655+00:00"},{"alias_kind":"pith_short_8","alias_value":"ISCP4YAN","created_at":"2026-07-05T08:35:54.370655+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ISCP4YANF6VVNR63S5P32VLO5R","json":"https://pith.science/pith/ISCP4YANF6VVNR63S5P32VLO5R.json","graph_json":"https://pith.science/api/pith-number/ISCP4YANF6VVNR63S5P32VLO5R/graph.json","events_json":"https://pith.science/api/pith-number/ISCP4YANF6VVNR63S5P32VLO5R/events.json","paper":"https://pith.science/paper/ISCP4YAN"},"agent_actions":{"view_html":"https://pith.science/pith/ISCP4YANF6VVNR63S5P32VLO5R","download_json":"https://pith.science/pith/ISCP4YANF6VVNR63S5P32VLO5R.json","view_paper":"https://pith.science/paper/ISCP4YAN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.16168&json=true","fetch_graph":"https://pith.science/api/pith-number/ISCP4YANF6VVNR63S5P32VLO5R/graph.json","fetch_events":"https://pith.science/api/pith-number/ISCP4YANF6VVNR63S5P32VLO5R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ISCP4YANF6VVNR63S5P32VLO5R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ISCP4YANF6VVNR63S5P32VLO5R/action/storage_attestation","attest_author":"https://pith.science/pith/ISCP4YANF6VVNR63S5P32VLO5R/action/author_attestation","sign_citation":"https://pith.science/pith/ISCP4YANF6VVNR63S5P32VLO5R/action/citation_signature","submit_replication":"https://pith.science/pith/ISCP4YANF6VVNR63S5P32VLO5R/action/replication_record"}},"created_at":"2026-07-05T08:35:54.370655+00:00","updated_at":"2026-07-05T08:35:54.370655+00:00"}