{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AAXDDEKTRAH7PZCPQ5GEMB72T7","short_pith_number":"pith:AAXDDEKT","schema_version":"1.0","canonical_sha256":"002e319153880ff7e44f874c4607fa9feb97a98b9e93b008b8420b956100d7e9","source":{"kind":"arxiv","id":"2302.06548","version":1},"attestation_state":"computed","paper":{"title":"Automatic Noise Filtering with Dynamic Sparse Training in Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bram Grooten, Decebal Constantin Mocanu, Elena Mocanu, Ghada Sokar, Matthew E. Taylor, Mykola Pechenizkiy, Shibhansh Dohare","submitted_at":"2023-02-13T17:45:03Z","abstract_excerpt":"Tomorrow's robots will need to distinguish useful information from noise when performing different tasks. A household robot for instance may continuously receive a plethora of information about the home, but needs to focus on just a small subset to successfully execute its current chore. Filtering distracting inputs that contain irrelevant data has received little attention in the reinforcement learning literature. To start resolving this, we formulate a problem setting in reinforcement learning called the $\\textit{extremely noisy environment}$ (ENE), where up to $99\\%$ of the input features a"},"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":"2302.06548","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-13T17:45:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b4eacbcec71a7da3635695aa89589b3e5da3cf14acad7e677f004cabcf81961d","abstract_canon_sha256":"c2783001bc685fcbc1e5628c03659ea5298e92853d4d33653860c8be4b22ab6b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:41:12.052704Z","signature_b64":"N74lsP8cm05iS+Aob71gHMFx7giSmCx6nkU4RO2OxTH6kQjh3RA5nv6Rmz9EjgbD1FjcRTSnQZEAZbcKZD4vAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"002e319153880ff7e44f874c4607fa9feb97a98b9e93b008b8420b956100d7e9","last_reissued_at":"2026-07-05T05:41:12.052333Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:41:12.052333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatic Noise Filtering with Dynamic Sparse Training in Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bram Grooten, Decebal Constantin Mocanu, Elena Mocanu, Ghada Sokar, Matthew E. Taylor, Mykola Pechenizkiy, Shibhansh Dohare","submitted_at":"2023-02-13T17:45:03Z","abstract_excerpt":"Tomorrow's robots will need to distinguish useful information from noise when performing different tasks. A household robot for instance may continuously receive a plethora of information about the home, but needs to focus on just a small subset to successfully execute its current chore. Filtering distracting inputs that contain irrelevant data has received little attention in the reinforcement learning literature. To start resolving this, we formulate a problem setting in reinforcement learning called the $\\textit{extremely noisy environment}$ (ENE), where up to $99\\%$ of the input features a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.06548","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/2302.06548/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":"2302.06548","created_at":"2026-07-05T05:41:12.052387+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.06548v1","created_at":"2026-07-05T05:41:12.052387+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.06548","created_at":"2026-07-05T05:41:12.052387+00:00"},{"alias_kind":"pith_short_12","alias_value":"AAXDDEKTRAH7","created_at":"2026-07-05T05:41:12.052387+00:00"},{"alias_kind":"pith_short_16","alias_value":"AAXDDEKTRAH7PZCP","created_at":"2026-07-05T05:41:12.052387+00:00"},{"alias_kind":"pith_short_8","alias_value":"AAXDDEKT","created_at":"2026-07-05T05:41:12.052387+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.17909","citing_title":"NeuroTrails: Training with Dynamic Sparse Heads as the Key to Effective Ensembling","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AAXDDEKTRAH7PZCPQ5GEMB72T7","json":"https://pith.science/pith/AAXDDEKTRAH7PZCPQ5GEMB72T7.json","graph_json":"https://pith.science/api/pith-number/AAXDDEKTRAH7PZCPQ5GEMB72T7/graph.json","events_json":"https://pith.science/api/pith-number/AAXDDEKTRAH7PZCPQ5GEMB72T7/events.json","paper":"https://pith.science/paper/AAXDDEKT"},"agent_actions":{"view_html":"https://pith.science/pith/AAXDDEKTRAH7PZCPQ5GEMB72T7","download_json":"https://pith.science/pith/AAXDDEKTRAH7PZCPQ5GEMB72T7.json","view_paper":"https://pith.science/paper/AAXDDEKT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.06548&json=true","fetch_graph":"https://pith.science/api/pith-number/AAXDDEKTRAH7PZCPQ5GEMB72T7/graph.json","fetch_events":"https://pith.science/api/pith-number/AAXDDEKTRAH7PZCPQ5GEMB72T7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AAXDDEKTRAH7PZCPQ5GEMB72T7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AAXDDEKTRAH7PZCPQ5GEMB72T7/action/storage_attestation","attest_author":"https://pith.science/pith/AAXDDEKTRAH7PZCPQ5GEMB72T7/action/author_attestation","sign_citation":"https://pith.science/pith/AAXDDEKTRAH7PZCPQ5GEMB72T7/action/citation_signature","submit_replication":"https://pith.science/pith/AAXDDEKTRAH7PZCPQ5GEMB72T7/action/replication_record"}},"created_at":"2026-07-05T05:41:12.052387+00:00","updated_at":"2026-07-05T05:41:12.052387+00:00"}