{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QZQ7Y2QUDJ5XYITA6EMMSYQWFT","short_pith_number":"pith:QZQ7Y2QU","schema_version":"1.0","canonical_sha256":"8661fc6a141a7b7c2260f118c962162ceea90c76f9547fee40051b0c35eecbb2","source":{"kind":"arxiv","id":"2201.02571","version":2},"attestation_state":"computed","paper":{"title":"Neural Network Optimization for Reinforcement Learning Tasks Using Sparse Computations","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Denis Larionov, Dmitry Ivanov, Mikhail Kiselev","submitted_at":"2022-01-07T18:09:23Z","abstract_excerpt":"This article proposes a sparse computation-based method for optimizing neural networks for reinforcement learning (RL) tasks. This method combines two ideas: neural network pruning and taking into account input data correlations; it makes it possible to update neuron states only when changes in them exceed a certain threshold. It significantly reduces the number of multiplications when running neural networks. We tested different RL tasks and achieved 20-150x reduction in the number of multiplications. There were no substantial performance losses; sometimes the performance even improved."},"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":"2201.02571","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-07T18:09:23Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"3935b9dead4b94f6c3cb8d3421aa99be7f6c120f83ae04baa84ea78c0cb6a976","abstract_canon_sha256":"fd606bf15598559aa5495706719ba74b2d0914fc58db8e1ca9d9642584f23c44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:12:38.030767Z","signature_b64":"1vizAUvFvsTdnOkoiobW5UWc9KkX4q+uoUTNtUEvlFSe/C7XjZpAN0TCakUraXyezNuw93H23CNkwKdhJsedBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8661fc6a141a7b7c2260f118c962162ceea90c76f9547fee40051b0c35eecbb2","last_reissued_at":"2026-07-05T04:12:38.030378Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:12:38.030378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Network Optimization for Reinforcement Learning Tasks Using Sparse Computations","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Denis Larionov, Dmitry Ivanov, Mikhail Kiselev","submitted_at":"2022-01-07T18:09:23Z","abstract_excerpt":"This article proposes a sparse computation-based method for optimizing neural networks for reinforcement learning (RL) tasks. This method combines two ideas: neural network pruning and taking into account input data correlations; it makes it possible to update neuron states only when changes in them exceed a certain threshold. It significantly reduces the number of multiplications when running neural networks. We tested different RL tasks and achieved 20-150x reduction in the number of multiplications. There were no substantial performance losses; sometimes the performance even improved."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.02571","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/2201.02571/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":"2201.02571","created_at":"2026-07-05T04:12:38.030433+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.02571v2","created_at":"2026-07-05T04:12:38.030433+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.02571","created_at":"2026-07-05T04:12:38.030433+00:00"},{"alias_kind":"pith_short_12","alias_value":"QZQ7Y2QUDJ5X","created_at":"2026-07-05T04:12:38.030433+00:00"},{"alias_kind":"pith_short_16","alias_value":"QZQ7Y2QUDJ5XYITA","created_at":"2026-07-05T04:12:38.030433+00:00"},{"alias_kind":"pith_short_8","alias_value":"QZQ7Y2QU","created_at":"2026-07-05T04:12:38.030433+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/QZQ7Y2QUDJ5XYITA6EMMSYQWFT","json":"https://pith.science/pith/QZQ7Y2QUDJ5XYITA6EMMSYQWFT.json","graph_json":"https://pith.science/api/pith-number/QZQ7Y2QUDJ5XYITA6EMMSYQWFT/graph.json","events_json":"https://pith.science/api/pith-number/QZQ7Y2QUDJ5XYITA6EMMSYQWFT/events.json","paper":"https://pith.science/paper/QZQ7Y2QU"},"agent_actions":{"view_html":"https://pith.science/pith/QZQ7Y2QUDJ5XYITA6EMMSYQWFT","download_json":"https://pith.science/pith/QZQ7Y2QUDJ5XYITA6EMMSYQWFT.json","view_paper":"https://pith.science/paper/QZQ7Y2QU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.02571&json=true","fetch_graph":"https://pith.science/api/pith-number/QZQ7Y2QUDJ5XYITA6EMMSYQWFT/graph.json","fetch_events":"https://pith.science/api/pith-number/QZQ7Y2QUDJ5XYITA6EMMSYQWFT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QZQ7Y2QUDJ5XYITA6EMMSYQWFT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QZQ7Y2QUDJ5XYITA6EMMSYQWFT/action/storage_attestation","attest_author":"https://pith.science/pith/QZQ7Y2QUDJ5XYITA6EMMSYQWFT/action/author_attestation","sign_citation":"https://pith.science/pith/QZQ7Y2QUDJ5XYITA6EMMSYQWFT/action/citation_signature","submit_replication":"https://pith.science/pith/QZQ7Y2QUDJ5XYITA6EMMSYQWFT/action/replication_record"}},"created_at":"2026-07-05T04:12:38.030433+00:00","updated_at":"2026-07-05T04:12:38.030433+00:00"}