{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:NJ6Y6CVWIJ2JDW6ZFXZABWHVUN","short_pith_number":"pith:NJ6Y6CVW","schema_version":"1.0","canonical_sha256":"6a7d8f0ab6427491dbd92df200d8f5a36b76752ea6b3c86948ad05bfae9d92df","source":{"kind":"arxiv","id":"1808.05578","version":1},"attestation_state":"computed","paper":{"title":"LARNN: Linear Attention Recurrent Neural Network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Guillaume Chevalier","submitted_at":"2018-08-16T16:48:56Z","abstract_excerpt":"The Linear Attention Recurrent Neural Network (LARNN) is a recurrent attention module derived from the Long Short-Term Memory (LSTM) cell and ideas from the consciousness Recurrent Neural Network (RNN). Yes, it LARNNs. The LARNN uses attention on its past cell state values for a limited window size $k$. The formulas are also derived from the Batch Normalized LSTM (BN-LSTM) cell and the Transformer Network for its Multi-Head Attention Mechanism. The Multi-Head Attention Mechanism is used inside the cell such that it can query its own $k$ past values with the attention window. This has the effec"},"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":"1808.05578","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-08-16T16:48:56Z","cross_cats_sorted":["cs.CC","stat.ML"],"title_canon_sha256":"5c619ed4a74c544b947f057ced63039ee2d205af326c355ca1914e267023fa55","abstract_canon_sha256":"e8cdd854a746b43705b87a65f715e8400f982b0ab775a87498359b0c90dd77af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:56.569718Z","signature_b64":"frB4sBXD+eobyYRaCKCDWEEVeE5hSTpsvMCueWdY+MHlIKohB9ZKQt23RksSS6N01bwsVrehb3Lkb6I1cqp5Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a7d8f0ab6427491dbd92df200d8f5a36b76752ea6b3c86948ad05bfae9d92df","last_reissued_at":"2026-05-18T00:07:56.569012Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:56.569012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LARNN: Linear Attention Recurrent Neural Network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Guillaume Chevalier","submitted_at":"2018-08-16T16:48:56Z","abstract_excerpt":"The Linear Attention Recurrent Neural Network (LARNN) is a recurrent attention module derived from the Long Short-Term Memory (LSTM) cell and ideas from the consciousness Recurrent Neural Network (RNN). Yes, it LARNNs. The LARNN uses attention on its past cell state values for a limited window size $k$. The formulas are also derived from the Batch Normalized LSTM (BN-LSTM) cell and the Transformer Network for its Multi-Head Attention Mechanism. The Multi-Head Attention Mechanism is used inside the cell such that it can query its own $k$ past values with the attention window. This has the effec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.05578","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":""},"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":"1808.05578","created_at":"2026-05-18T00:07:56.569113+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.05578v1","created_at":"2026-05-18T00:07:56.569113+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.05578","created_at":"2026-05-18T00:07:56.569113+00:00"},{"alias_kind":"pith_short_12","alias_value":"NJ6Y6CVWIJ2J","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"NJ6Y6CVWIJ2JDW6Z","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"NJ6Y6CVW","created_at":"2026-05-18T12:32:40.477152+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/NJ6Y6CVWIJ2JDW6ZFXZABWHVUN","json":"https://pith.science/pith/NJ6Y6CVWIJ2JDW6ZFXZABWHVUN.json","graph_json":"https://pith.science/api/pith-number/NJ6Y6CVWIJ2JDW6ZFXZABWHVUN/graph.json","events_json":"https://pith.science/api/pith-number/NJ6Y6CVWIJ2JDW6ZFXZABWHVUN/events.json","paper":"https://pith.science/paper/NJ6Y6CVW"},"agent_actions":{"view_html":"https://pith.science/pith/NJ6Y6CVWIJ2JDW6ZFXZABWHVUN","download_json":"https://pith.science/pith/NJ6Y6CVWIJ2JDW6ZFXZABWHVUN.json","view_paper":"https://pith.science/paper/NJ6Y6CVW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.05578&json=true","fetch_graph":"https://pith.science/api/pith-number/NJ6Y6CVWIJ2JDW6ZFXZABWHVUN/graph.json","fetch_events":"https://pith.science/api/pith-number/NJ6Y6CVWIJ2JDW6ZFXZABWHVUN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NJ6Y6CVWIJ2JDW6ZFXZABWHVUN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NJ6Y6CVWIJ2JDW6ZFXZABWHVUN/action/storage_attestation","attest_author":"https://pith.science/pith/NJ6Y6CVWIJ2JDW6ZFXZABWHVUN/action/author_attestation","sign_citation":"https://pith.science/pith/NJ6Y6CVWIJ2JDW6ZFXZABWHVUN/action/citation_signature","submit_replication":"https://pith.science/pith/NJ6Y6CVWIJ2JDW6ZFXZABWHVUN/action/replication_record"}},"created_at":"2026-05-18T00:07:56.569113+00:00","updated_at":"2026-05-18T00:07:56.569113+00:00"}