{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:3JBANL6RRZL4Y6KQ7HB536PPTB","short_pith_number":"pith:3JBANL6R","canonical_record":{"source":{"id":"1503.04269","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-03-14T04:44:20Z","cross_cats_sorted":[],"title_canon_sha256":"aa0df89874f2565da404e1493bb5403163bab6ab3195903b2e4811b2f6ccd50d","abstract_canon_sha256":"a0ccb4b925655903f156215d60dec64d54a7eca8645db70094d7e7107533c801"},"schema_version":"1.0"},"canonical_sha256":"da4206afd18e57cc7950f9c3ddf9ef986d23e50d68630ece142382a17c2def3e","source":{"kind":"arxiv","id":"1503.04269","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1503.04269","created_at":"2026-05-18T01:10:46Z"},{"alias_kind":"arxiv_version","alias_value":"1503.04269v2","created_at":"2026-05-18T01:10:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.04269","created_at":"2026-05-18T01:10:46Z"},{"alias_kind":"pith_short_12","alias_value":"3JBANL6RRZL4","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_16","alias_value":"3JBANL6RRZL4Y6KQ","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_8","alias_value":"3JBANL6R","created_at":"2026-05-18T12:29:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:3JBANL6RRZL4Y6KQ7HB536PPTB","target":"record","payload":{"canonical_record":{"source":{"id":"1503.04269","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-03-14T04:44:20Z","cross_cats_sorted":[],"title_canon_sha256":"aa0df89874f2565da404e1493bb5403163bab6ab3195903b2e4811b2f6ccd50d","abstract_canon_sha256":"a0ccb4b925655903f156215d60dec64d54a7eca8645db70094d7e7107533c801"},"schema_version":"1.0"},"canonical_sha256":"da4206afd18e57cc7950f9c3ddf9ef986d23e50d68630ece142382a17c2def3e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:10:46.009849Z","signature_b64":"7lv6LMGIi+wDdpYRa7O79NJmfFhbld0WCJJTPDczzwU4WgfXox7kFH4fIIpxmCrhiubRFtHaxFCUc8FoH7NOAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da4206afd18e57cc7950f9c3ddf9ef986d23e50d68630ece142382a17c2def3e","last_reissued_at":"2026-05-18T01:10:46.009309Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:10:46.009309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1503.04269","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:10:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nO+7Wx2+PgNwtPRfRz5qLxyXIbUKdtTzqer+PVPX0ETK0PuftXM3hwhDHJE1YPFfyed0JhLixvRYR0DhAuk2Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T11:40:30.627440Z"},"content_sha256":"36e04ed9e56ea3912000e923b442c40692d94898a967d7ae5fb04aa81bc175ae","schema_version":"1.0","event_id":"sha256:36e04ed9e56ea3912000e923b442c40692d94898a967d7ae5fb04aa81bc175ae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:3JBANL6RRZL4Y6KQ7HB536PPTB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Emphatic Approach to the Problem of Off-policy Temporal-Difference Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"A. Rupam Mahmood, Martha White, Richard S. Sutton","submitted_at":"2015-03-14T04:44:20Z","abstract_excerpt":"In this paper we introduce the idea of improving the performance of parametric temporal-difference (TD) learning algorithms by selectively emphasizing or de-emphasizing their updates on different time steps. In particular, we show that varying the emphasis of linear TD($\\lambda$)'s updates in a particular way causes its expected update to become stable under off-policy training. The only prior model-free TD methods to achieve this with per-step computation linear in the number of function approximation parameters are the gradient-TD family of methods including TDC, GTD($\\lambda$), and GQ($\\lam"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.04269","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:10:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zTCNXV13CR/+Hgsezqmg7UCognnZ9GrHDKHhaHJJ6AXFeNEzqhY1zDZrzTvOUGbKA8Ei1LndP74MnB6fEv7SAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T11:40:30.628617Z"},"content_sha256":"1e49ed5aa70fd763ffddae9038e4967bab3be0511998f082f0fdff2ae6d11efd","schema_version":"1.0","event_id":"sha256:1e49ed5aa70fd763ffddae9038e4967bab3be0511998f082f0fdff2ae6d11efd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3JBANL6RRZL4Y6KQ7HB536PPTB/bundle.json","state_url":"https://pith.science/pith/3JBANL6RRZL4Y6KQ7HB536PPTB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3JBANL6RRZL4Y6KQ7HB536PPTB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-25T11:40:30Z","links":{"resolver":"https://pith.science/pith/3JBANL6RRZL4Y6KQ7HB536PPTB","bundle":"https://pith.science/pith/3JBANL6RRZL4Y6KQ7HB536PPTB/bundle.json","state":"https://pith.science/pith/3JBANL6RRZL4Y6KQ7HB536PPTB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3JBANL6RRZL4Y6KQ7HB536PPTB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:3JBANL6RRZL4Y6KQ7HB536PPTB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a0ccb4b925655903f156215d60dec64d54a7eca8645db70094d7e7107533c801","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-03-14T04:44:20Z","title_canon_sha256":"aa0df89874f2565da404e1493bb5403163bab6ab3195903b2e4811b2f6ccd50d"},"schema_version":"1.0","source":{"id":"1503.04269","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1503.04269","created_at":"2026-05-18T01:10:46Z"},{"alias_kind":"arxiv_version","alias_value":"1503.04269v2","created_at":"2026-05-18T01:10:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.04269","created_at":"2026-05-18T01:10:46Z"},{"alias_kind":"pith_short_12","alias_value":"3JBANL6RRZL4","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_16","alias_value":"3JBANL6RRZL4Y6KQ","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_8","alias_value":"3JBANL6R","created_at":"2026-05-18T12:29:02Z"}],"graph_snapshots":[{"event_id":"sha256:1e49ed5aa70fd763ffddae9038e4967bab3be0511998f082f0fdff2ae6d11efd","target":"graph","created_at":"2026-05-18T01:10:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"In this paper we introduce the idea of improving the performance of parametric temporal-difference (TD) learning algorithms by selectively emphasizing or de-emphasizing their updates on different time steps. In particular, we show that varying the emphasis of linear TD($\\lambda$)'s updates in a particular way causes its expected update to become stable under off-policy training. The only prior model-free TD methods to achieve this with per-step computation linear in the number of function approximation parameters are the gradient-TD family of methods including TDC, GTD($\\lambda$), and GQ($\\lam","authors_text":"A. Rupam Mahmood, Martha White, Richard S. Sutton","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-03-14T04:44:20Z","title":"An Emphatic Approach to the Problem of Off-policy Temporal-Difference Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.04269","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:36e04ed9e56ea3912000e923b442c40692d94898a967d7ae5fb04aa81bc175ae","target":"record","created_at":"2026-05-18T01:10:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a0ccb4b925655903f156215d60dec64d54a7eca8645db70094d7e7107533c801","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-03-14T04:44:20Z","title_canon_sha256":"aa0df89874f2565da404e1493bb5403163bab6ab3195903b2e4811b2f6ccd50d"},"schema_version":"1.0","source":{"id":"1503.04269","kind":"arxiv","version":2}},"canonical_sha256":"da4206afd18e57cc7950f9c3ddf9ef986d23e50d68630ece142382a17c2def3e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da4206afd18e57cc7950f9c3ddf9ef986d23e50d68630ece142382a17c2def3e","first_computed_at":"2026-05-18T01:10:46.009309Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:10:46.009309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7lv6LMGIi+wDdpYRa7O79NJmfFhbld0WCJJTPDczzwU4WgfXox7kFH4fIIpxmCrhiubRFtHaxFCUc8FoH7NOAg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:10:46.009849Z","signed_message":"canonical_sha256_bytes"},"source_id":"1503.04269","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36e04ed9e56ea3912000e923b442c40692d94898a967d7ae5fb04aa81bc175ae","sha256:1e49ed5aa70fd763ffddae9038e4967bab3be0511998f082f0fdff2ae6d11efd"],"state_sha256":"c1ffdfe4e8abb2510eeaa4c6f0ea7ca0fcef4ae6e50c7fa643626c8e4beccb45"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GuyyGwR89V8+GxCxV4fsIgQ7XbUs1eu2AofmHkt5bFN1J2BZFNA6wfjql85vWY7vVQqIMoFTnKkvA/O+KvZMBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T11:40:30.632215Z","bundle_sha256":"71f5c78de32bd0713bec26d19a19820720258d6a0e5cee277946191894de9df5"}}