{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ZBVQRX7XVDURAPRXTFCYVF7NGK","short_pith_number":"pith:ZBVQRX7X","schema_version":"1.0","canonical_sha256":"c86b08dff7a8e9103e3799458a97ed32ac468299e1ee95f04a1aa9eb97d6c087","source":{"kind":"arxiv","id":"1809.05922","version":2},"attestation_state":"computed","paper":{"title":"Memory Efficient Experience Replay for Streaming Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christopher Kanan, Nathan D. Cahill, Tyler L. Hayes","submitted_at":"2018-09-16T18:04:33Z","abstract_excerpt":"In supervised machine learning, an agent is typically trained once and then deployed. While this works well for static settings, robots often operate in changing environments and must quickly learn new things from data streams. In this paradigm, known as streaming learning, a learner is trained online, in a single pass, from a data stream that cannot be assumed to be independent and identically distributed (iid). Streaming learning will cause conventional deep neural networks (DNNs) to fail for two reasons: 1) they need multiple passes through the entire dataset; and 2) non-iid data will cause"},"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":"1809.05922","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-16T18:04:33Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"4f02cb17db3a060d67d8db13c899ef94c25d3df766ca839928fbccc2e3275594","abstract_canon_sha256":"98a6437656d73fb98b4688fd1ff636861513dee3e8a9963827fe4491fef70d14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:52.239536Z","signature_b64":"IyXdB423k3/rg4fBbLk8wsq3haaWEXnPESKiZgPyi1AagOLdVed0Ouf0l8vCEGf4gEr4RxMSgEv/tzcc16s6DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c86b08dff7a8e9103e3799458a97ed32ac468299e1ee95f04a1aa9eb97d6c087","last_reissued_at":"2026-05-17T23:52:52.238696Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:52.238696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Memory Efficient Experience Replay for Streaming Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christopher Kanan, Nathan D. Cahill, Tyler L. Hayes","submitted_at":"2018-09-16T18:04:33Z","abstract_excerpt":"In supervised machine learning, an agent is typically trained once and then deployed. While this works well for static settings, robots often operate in changing environments and must quickly learn new things from data streams. In this paradigm, known as streaming learning, a learner is trained online, in a single pass, from a data stream that cannot be assumed to be independent and identically distributed (iid). Streaming learning will cause conventional deep neural networks (DNNs) to fail for two reasons: 1) they need multiple passes through the entire dataset; and 2) non-iid data will cause"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.05922","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":""},"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":"1809.05922","created_at":"2026-05-17T23:52:52.238832+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.05922v2","created_at":"2026-05-17T23:52:52.238832+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.05922","created_at":"2026-05-17T23:52:52.238832+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZBVQRX7XVDUR","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZBVQRX7XVDURAPRX","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZBVQRX7X","created_at":"2026-05-18T12:33:04.347982+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.18187","citing_title":"BRAIN: Bias-Mitigation Continual Learning Approach to Vision-Brain Understanding","ref_index":66,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZBVQRX7XVDURAPRXTFCYVF7NGK","json":"https://pith.science/pith/ZBVQRX7XVDURAPRXTFCYVF7NGK.json","graph_json":"https://pith.science/api/pith-number/ZBVQRX7XVDURAPRXTFCYVF7NGK/graph.json","events_json":"https://pith.science/api/pith-number/ZBVQRX7XVDURAPRXTFCYVF7NGK/events.json","paper":"https://pith.science/paper/ZBVQRX7X"},"agent_actions":{"view_html":"https://pith.science/pith/ZBVQRX7XVDURAPRXTFCYVF7NGK","download_json":"https://pith.science/pith/ZBVQRX7XVDURAPRXTFCYVF7NGK.json","view_paper":"https://pith.science/paper/ZBVQRX7X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.05922&json=true","fetch_graph":"https://pith.science/api/pith-number/ZBVQRX7XVDURAPRXTFCYVF7NGK/graph.json","fetch_events":"https://pith.science/api/pith-number/ZBVQRX7XVDURAPRXTFCYVF7NGK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZBVQRX7XVDURAPRXTFCYVF7NGK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZBVQRX7XVDURAPRXTFCYVF7NGK/action/storage_attestation","attest_author":"https://pith.science/pith/ZBVQRX7XVDURAPRXTFCYVF7NGK/action/author_attestation","sign_citation":"https://pith.science/pith/ZBVQRX7XVDURAPRXTFCYVF7NGK/action/citation_signature","submit_replication":"https://pith.science/pith/ZBVQRX7XVDURAPRXTFCYVF7NGK/action/replication_record"}},"created_at":"2026-05-17T23:52:52.238832+00:00","updated_at":"2026-05-17T23:52:52.238832+00:00"}