{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XG7ZB23BXWD6VJGD74Q66OKTSM","short_pith_number":"pith:XG7ZB23B","schema_version":"1.0","canonical_sha256":"b9bf90eb61bd87eaa4c3ff21ef39539302cf3c200c5a6d1866e094c4750a9547","source":{"kind":"arxiv","id":"2410.24023","version":2},"attestation_state":"computed","paper":{"title":"RAM: Replace Attention with MLP for Efficient Multivariate Time Series Forecasting","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Furao Shen, Hui Dou, Jiahong Deng, Jian Zhao, Suhan Guo, Yi Wei","submitted_at":"2024-10-31T15:23:34Z","abstract_excerpt":"Attention-based architectures have become ubiquitous in time series forecasting tasks, including spatio-temporal (STF) and long-term time series forecasting (LTSF). Yet, our understanding of the reasons for their effectiveness remains limited. In this work, we propose a novel pruning strategy, $\\textbf{R}$eplace $\\textbf{A}$ttention with $\\textbf{M}$LP (RAM), that approximates the attention mechanism using only feedforward layers, residual connections, and layer normalization for temporal and/or spatial modeling in multivariate time series forecasting. Specifically, the Q, K, and V projections"},"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":"2410.24023","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-31T15:23:34Z","cross_cats_sorted":[],"title_canon_sha256":"30ce140925cee28b91ab4559c4bb9c9ebe20213aa4bf7df9c1543f03a0cd47df","abstract_canon_sha256":"025fbe00957b7cec70002e6d62ef4cf439008ecf20e9e85ce662d90be1e9cec1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:02.177828Z","signature_b64":"uez7do7/UJs+3qnucnG0ZboFs5qjdeUtnN051wm7QMORW7coSOiJIermxc7JUR4ES/N2ohcYAHcL9bRGJZZYDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9bf90eb61bd87eaa4c3ff21ef39539302cf3c200c5a6d1866e094c4750a9547","last_reissued_at":"2026-07-05T11:01:02.177303Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:02.177303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RAM: Replace Attention with MLP for Efficient Multivariate Time Series Forecasting","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Furao Shen, Hui Dou, Jiahong Deng, Jian Zhao, Suhan Guo, Yi Wei","submitted_at":"2024-10-31T15:23:34Z","abstract_excerpt":"Attention-based architectures have become ubiquitous in time series forecasting tasks, including spatio-temporal (STF) and long-term time series forecasting (LTSF). Yet, our understanding of the reasons for their effectiveness remains limited. In this work, we propose a novel pruning strategy, $\\textbf{R}$eplace $\\textbf{A}$ttention with $\\textbf{M}$LP (RAM), that approximates the attention mechanism using only feedforward layers, residual connections, and layer normalization for temporal and/or spatial modeling in multivariate time series forecasting. Specifically, the Q, K, and V projections"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.24023","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/2410.24023/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":"2410.24023","created_at":"2026-07-05T11:01:02.177367+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.24023v2","created_at":"2026-07-05T11:01:02.177367+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.24023","created_at":"2026-07-05T11:01:02.177367+00:00"},{"alias_kind":"pith_short_12","alias_value":"XG7ZB23BXWD6","created_at":"2026-07-05T11:01:02.177367+00:00"},{"alias_kind":"pith_short_16","alias_value":"XG7ZB23BXWD6VJGD","created_at":"2026-07-05T11:01:02.177367+00:00"},{"alias_kind":"pith_short_8","alias_value":"XG7ZB23B","created_at":"2026-07-05T11:01:02.177367+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/XG7ZB23BXWD6VJGD74Q66OKTSM","json":"https://pith.science/pith/XG7ZB23BXWD6VJGD74Q66OKTSM.json","graph_json":"https://pith.science/api/pith-number/XG7ZB23BXWD6VJGD74Q66OKTSM/graph.json","events_json":"https://pith.science/api/pith-number/XG7ZB23BXWD6VJGD74Q66OKTSM/events.json","paper":"https://pith.science/paper/XG7ZB23B"},"agent_actions":{"view_html":"https://pith.science/pith/XG7ZB23BXWD6VJGD74Q66OKTSM","download_json":"https://pith.science/pith/XG7ZB23BXWD6VJGD74Q66OKTSM.json","view_paper":"https://pith.science/paper/XG7ZB23B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.24023&json=true","fetch_graph":"https://pith.science/api/pith-number/XG7ZB23BXWD6VJGD74Q66OKTSM/graph.json","fetch_events":"https://pith.science/api/pith-number/XG7ZB23BXWD6VJGD74Q66OKTSM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XG7ZB23BXWD6VJGD74Q66OKTSM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XG7ZB23BXWD6VJGD74Q66OKTSM/action/storage_attestation","attest_author":"https://pith.science/pith/XG7ZB23BXWD6VJGD74Q66OKTSM/action/author_attestation","sign_citation":"https://pith.science/pith/XG7ZB23BXWD6VJGD74Q66OKTSM/action/citation_signature","submit_replication":"https://pith.science/pith/XG7ZB23BXWD6VJGD74Q66OKTSM/action/replication_record"}},"created_at":"2026-07-05T11:01:02.177367+00:00","updated_at":"2026-07-05T11:01:02.177367+00:00"}