{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WP7SBCTLQ3IBJQK4NYJ2CLOFZB","short_pith_number":"pith:WP7SBCTL","schema_version":"1.0","canonical_sha256":"b3ff208a6b86d014c15c6e13a12dc5c85ab8a953c8d92e616f6d6c85c61342d4","source":{"kind":"arxiv","id":"2206.06178","version":3},"attestation_state":"computed","paper":{"title":"Efficient recurrent architectures through activity sparsity and sparse back-propagation through time","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Anand Subramoney, Christian Mayr, David Kappel, Khaleelulla Khan Nazeer, Mark Sch\\\"one","submitted_at":"2022-06-13T14:07:56Z","abstract_excerpt":"Recurrent neural networks (RNNs) are well suited for solving sequence tasks in resource-constrained systems due to their expressivity and low computational requirements. However, there is still a need to bridge the gap between what RNNs are capable of in terms of efficiency and performance and real-world application requirements. The memory and computational requirements arising from propagating the activations of all the neurons at every time step to every connected neuron, together with the sequential dependence of activations, contribute to the inefficiency of training and using RNNs. We pr"},"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":"2206.06178","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-13T14:07:56Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"c5c22a33fc81747f6fd2bd9126272c40b4c8bc0507a5b311f32c7a71d0e2fdb3","abstract_canon_sha256":"0d49d335b65a01524f85d6ec89c7131bb41449c2ebbfd4729e07439793fc3bef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:49:43.218403Z","signature_b64":"HVRN2E3TrzRQVbSapXMsHCkQZLSdocbyllfmetAPKwbEaAjRY6wZWglDCPiouBbsonAYQy7aLoRc+aYe8x0hBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3ff208a6b86d014c15c6e13a12dc5c85ab8a953c8d92e616f6d6c85c61342d4","last_reissued_at":"2026-07-05T05:49:43.217946Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:49:43.217946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient recurrent architectures through activity sparsity and sparse back-propagation through time","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Anand Subramoney, Christian Mayr, David Kappel, Khaleelulla Khan Nazeer, Mark Sch\\\"one","submitted_at":"2022-06-13T14:07:56Z","abstract_excerpt":"Recurrent neural networks (RNNs) are well suited for solving sequence tasks in resource-constrained systems due to their expressivity and low computational requirements. However, there is still a need to bridge the gap between what RNNs are capable of in terms of efficiency and performance and real-world application requirements. The memory and computational requirements arising from propagating the activations of all the neurons at every time step to every connected neuron, together with the sequential dependence of activations, contribute to the inefficiency of training and using RNNs. We pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.06178","kind":"arxiv","version":3},"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/2206.06178/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":"2206.06178","created_at":"2026-07-05T05:49:43.218003+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.06178v3","created_at":"2026-07-05T05:49:43.218003+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.06178","created_at":"2026-07-05T05:49:43.218003+00:00"},{"alias_kind":"pith_short_12","alias_value":"WP7SBCTLQ3IB","created_at":"2026-07-05T05:49:43.218003+00:00"},{"alias_kind":"pith_short_16","alias_value":"WP7SBCTLQ3IBJQK4","created_at":"2026-07-05T05:49:43.218003+00:00"},{"alias_kind":"pith_short_8","alias_value":"WP7SBCTL","created_at":"2026-07-05T05:49:43.218003+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12895","citing_title":"LongSpike: Fractional Order Spiking State Space Models for Efficient Long Sequence Learning","ref_index":94,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WP7SBCTLQ3IBJQK4NYJ2CLOFZB","json":"https://pith.science/pith/WP7SBCTLQ3IBJQK4NYJ2CLOFZB.json","graph_json":"https://pith.science/api/pith-number/WP7SBCTLQ3IBJQK4NYJ2CLOFZB/graph.json","events_json":"https://pith.science/api/pith-number/WP7SBCTLQ3IBJQK4NYJ2CLOFZB/events.json","paper":"https://pith.science/paper/WP7SBCTL"},"agent_actions":{"view_html":"https://pith.science/pith/WP7SBCTLQ3IBJQK4NYJ2CLOFZB","download_json":"https://pith.science/pith/WP7SBCTLQ3IBJQK4NYJ2CLOFZB.json","view_paper":"https://pith.science/paper/WP7SBCTL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.06178&json=true","fetch_graph":"https://pith.science/api/pith-number/WP7SBCTLQ3IBJQK4NYJ2CLOFZB/graph.json","fetch_events":"https://pith.science/api/pith-number/WP7SBCTLQ3IBJQK4NYJ2CLOFZB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WP7SBCTLQ3IBJQK4NYJ2CLOFZB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WP7SBCTLQ3IBJQK4NYJ2CLOFZB/action/storage_attestation","attest_author":"https://pith.science/pith/WP7SBCTLQ3IBJQK4NYJ2CLOFZB/action/author_attestation","sign_citation":"https://pith.science/pith/WP7SBCTLQ3IBJQK4NYJ2CLOFZB/action/citation_signature","submit_replication":"https://pith.science/pith/WP7SBCTLQ3IBJQK4NYJ2CLOFZB/action/replication_record"}},"created_at":"2026-07-05T05:49:43.218003+00:00","updated_at":"2026-07-05T05:49:43.218003+00:00"}