{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ACZUTWTJQDYULV43EJPPRJB3BA","short_pith_number":"pith:ACZUTWTJ","schema_version":"1.0","canonical_sha256":"00b349da6980f145d79b225ef8a43b0833e505540d633bfcf8c9eefe60b65258","source":{"kind":"arxiv","id":"1902.04179","version":1},"attestation_state":"computed","paper":{"title":"Performance Dynamics and Termination Errors in Reinforcement Learning: A Unifying Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Clement H. C. Leung, Nikki Lijing Kuang","submitted_at":"2019-02-11T23:13:50Z","abstract_excerpt":"In reinforcement learning, a decision needs to be made at some point as to whether it is worthwhile to carry on with the learning process or to terminate it. In many such situations, stochastic elements are often present which govern the occurrence of rewards, with the sequential occurrences of positive rewards randomly interleaved with negative rewards. For most practical learners, the learning is considered useful if the number of positive rewards always exceeds the negative ones. A situation that often calls for learning termination is when the number of negative rewards exceeds the number "},"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":"1902.04179","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-11T23:13:50Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"4096592f5ba32e00d1a456ea276b74c90604a9249be3e41ee2240bff0fe0cd57","abstract_canon_sha256":"67bc13d73f9eee94f665c3b26f7978433c5bb43e9768c8edd061dde8dba89267"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:12.872956Z","signature_b64":"wDFjwCUXvKAdTHLMvdUqavOQzItvLz/8pBSWu/LtMlzjAuwrnUM+TbYBLxBqrjqqPOf42eYXlRC+kxWeCq6xBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00b349da6980f145d79b225ef8a43b0833e505540d633bfcf8c9eefe60b65258","last_reissued_at":"2026-05-17T23:54:12.872510Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:12.872510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Performance Dynamics and Termination Errors in Reinforcement Learning: A Unifying Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Clement H. C. Leung, Nikki Lijing Kuang","submitted_at":"2019-02-11T23:13:50Z","abstract_excerpt":"In reinforcement learning, a decision needs to be made at some point as to whether it is worthwhile to carry on with the learning process or to terminate it. In many such situations, stochastic elements are often present which govern the occurrence of rewards, with the sequential occurrences of positive rewards randomly interleaved with negative rewards. For most practical learners, the learning is considered useful if the number of positive rewards always exceeds the negative ones. A situation that often calls for learning termination is when the number of negative rewards exceeds the number "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.04179","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":"1902.04179","created_at":"2026-05-17T23:54:12.872587+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.04179v1","created_at":"2026-05-17T23:54:12.872587+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.04179","created_at":"2026-05-17T23:54:12.872587+00:00"},{"alias_kind":"pith_short_12","alias_value":"ACZUTWTJQDYU","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"ACZUTWTJQDYULV43","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"ACZUTWTJ","created_at":"2026-05-18T12:33:12.712433+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/ACZUTWTJQDYULV43EJPPRJB3BA","json":"https://pith.science/pith/ACZUTWTJQDYULV43EJPPRJB3BA.json","graph_json":"https://pith.science/api/pith-number/ACZUTWTJQDYULV43EJPPRJB3BA/graph.json","events_json":"https://pith.science/api/pith-number/ACZUTWTJQDYULV43EJPPRJB3BA/events.json","paper":"https://pith.science/paper/ACZUTWTJ"},"agent_actions":{"view_html":"https://pith.science/pith/ACZUTWTJQDYULV43EJPPRJB3BA","download_json":"https://pith.science/pith/ACZUTWTJQDYULV43EJPPRJB3BA.json","view_paper":"https://pith.science/paper/ACZUTWTJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.04179&json=true","fetch_graph":"https://pith.science/api/pith-number/ACZUTWTJQDYULV43EJPPRJB3BA/graph.json","fetch_events":"https://pith.science/api/pith-number/ACZUTWTJQDYULV43EJPPRJB3BA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ACZUTWTJQDYULV43EJPPRJB3BA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ACZUTWTJQDYULV43EJPPRJB3BA/action/storage_attestation","attest_author":"https://pith.science/pith/ACZUTWTJQDYULV43EJPPRJB3BA/action/author_attestation","sign_citation":"https://pith.science/pith/ACZUTWTJQDYULV43EJPPRJB3BA/action/citation_signature","submit_replication":"https://pith.science/pith/ACZUTWTJQDYULV43EJPPRJB3BA/action/replication_record"}},"created_at":"2026-05-17T23:54:12.872587+00:00","updated_at":"2026-05-17T23:54:12.872587+00:00"}