{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:DS5CZTKLU7F3GHA2PVV2J5CG2L","short_pith_number":"pith:DS5CZTKL","schema_version":"1.0","canonical_sha256":"1cba2ccd4ba7cbb31c1a7d6ba4f446d2e4e07a5f3e1138304ca806219bf43c4b","source":{"kind":"arxiv","id":"1902.02907","version":1},"attestation_state":"computed","paper":{"title":"Source Traces for Temporal Difference Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Silviu Pitis","submitted_at":"2019-02-08T01:21:17Z","abstract_excerpt":"This paper motivates and develops source traces for temporal difference (TD) learning in the tabular setting. Source traces are like eligibility traces, but model potential histories rather than immediate ones. This allows TD errors to be propagated to potential causal states and leads to faster generalization. Source traces can be thought of as the model-based, backward view of successor representations (SR), and share many of the same benefits. This view, however, suggests several new ideas. First, a TD($\\lambda$)-like source learning algorithm is proposed and its convergence is proven. Then"},"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":"1902.02907","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-08T01:21:17Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"8c1c59c8de131fbb937efe81040bbec87da9929f77bbb4793ac1fad2e81e7197","abstract_canon_sha256":"c4b9d1ba8619a33d9c6455da2d1272396c3e10750e3dd5f48c4c9f248822b913"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:28.889541Z","signature_b64":"CnZIT4kiaqWYypQUq6qVh7lImEDRzHMHVY3sFKVYiePmYFPm4/FPpvbNAW01WkHeUpwTuw/rtk0TPmX8P2CFDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cba2ccd4ba7cbb31c1a7d6ba4f446d2e4e07a5f3e1138304ca806219bf43c4b","last_reissued_at":"2026-05-17T23:54:28.888936Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:28.888936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Source Traces for Temporal Difference Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Silviu Pitis","submitted_at":"2019-02-08T01:21:17Z","abstract_excerpt":"This paper motivates and develops source traces for temporal difference (TD) learning in the tabular setting. Source traces are like eligibility traces, but model potential histories rather than immediate ones. This allows TD errors to be propagated to potential causal states and leads to faster generalization. Source traces can be thought of as the model-based, backward view of successor representations (SR), and share many of the same benefits. This view, however, suggests several new ideas. First, a TD($\\lambda$)-like source learning algorithm is proposed and its convergence is proven. Then"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.02907","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":"1902.02907","created_at":"2026-05-17T23:54:28.889036+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.02907v1","created_at":"2026-05-17T23:54:28.889036+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.02907","created_at":"2026-05-17T23:54:28.889036+00:00"},{"alias_kind":"pith_short_12","alias_value":"DS5CZTKLU7F3","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"DS5CZTKLU7F3GHA2","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"DS5CZTKL","created_at":"2026-05-18T12:33:15.570797+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/DS5CZTKLU7F3GHA2PVV2J5CG2L","json":"https://pith.science/pith/DS5CZTKLU7F3GHA2PVV2J5CG2L.json","graph_json":"https://pith.science/api/pith-number/DS5CZTKLU7F3GHA2PVV2J5CG2L/graph.json","events_json":"https://pith.science/api/pith-number/DS5CZTKLU7F3GHA2PVV2J5CG2L/events.json","paper":"https://pith.science/paper/DS5CZTKL"},"agent_actions":{"view_html":"https://pith.science/pith/DS5CZTKLU7F3GHA2PVV2J5CG2L","download_json":"https://pith.science/pith/DS5CZTKLU7F3GHA2PVV2J5CG2L.json","view_paper":"https://pith.science/paper/DS5CZTKL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.02907&json=true","fetch_graph":"https://pith.science/api/pith-number/DS5CZTKLU7F3GHA2PVV2J5CG2L/graph.json","fetch_events":"https://pith.science/api/pith-number/DS5CZTKLU7F3GHA2PVV2J5CG2L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DS5CZTKLU7F3GHA2PVV2J5CG2L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DS5CZTKLU7F3GHA2PVV2J5CG2L/action/storage_attestation","attest_author":"https://pith.science/pith/DS5CZTKLU7F3GHA2PVV2J5CG2L/action/author_attestation","sign_citation":"https://pith.science/pith/DS5CZTKLU7F3GHA2PVV2J5CG2L/action/citation_signature","submit_replication":"https://pith.science/pith/DS5CZTKLU7F3GHA2PVV2J5CG2L/action/replication_record"}},"created_at":"2026-05-17T23:54:28.889036+00:00","updated_at":"2026-05-17T23:54:28.889036+00:00"}