{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:5N2G2FEI4FREWVGDPQISYKQIN4","short_pith_number":"pith:5N2G2FEI","canonical_record":{"source":{"id":"1511.07471","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-23T21:29:43Z","cross_cats_sorted":[],"title_canon_sha256":"2631191bc48070c9c94b80a5552585f8675c77f1b93e55dd49518bd83bc5056d","abstract_canon_sha256":"e7e8542c16b0ac17db6bb9b4c0e1f7f8e23dd10f282b6cf135cca2ebd568a47c"},"schema_version":"1.0"},"canonical_sha256":"eb746d1488e1624b54c37c112c2a086f364b7f354cb1364d2b3ccb689ebc9506","source":{"kind":"arxiv","id":"1511.07471","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.07471","created_at":"2026-05-18T00:52:28Z"},{"alias_kind":"arxiv_version","alias_value":"1511.07471v3","created_at":"2026-05-18T00:52:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.07471","created_at":"2026-05-18T00:52:28Z"},{"alias_kind":"pith_short_12","alias_value":"5N2G2FEI4FRE","created_at":"2026-05-18T12:29:05Z"},{"alias_kind":"pith_short_16","alias_value":"5N2G2FEI4FREWVGD","created_at":"2026-05-18T12:29:05Z"},{"alias_kind":"pith_short_8","alias_value":"5N2G2FEI","created_at":"2026-05-18T12:29:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:5N2G2FEI4FREWVGDPQISYKQIN4","target":"record","payload":{"canonical_record":{"source":{"id":"1511.07471","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-23T21:29:43Z","cross_cats_sorted":[],"title_canon_sha256":"2631191bc48070c9c94b80a5552585f8675c77f1b93e55dd49518bd83bc5056d","abstract_canon_sha256":"e7e8542c16b0ac17db6bb9b4c0e1f7f8e23dd10f282b6cf135cca2ebd568a47c"},"schema_version":"1.0"},"canonical_sha256":"eb746d1488e1624b54c37c112c2a086f364b7f354cb1364d2b3ccb689ebc9506","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:52:28.469987Z","signature_b64":"6wK14IZThYAPQgwxFwlUgSpPUgTQdi4pXcnXnXgdhaI+c8LqJAOEdhJ+QCkCO6gXvxJTmvko2hTXntaLt/G8Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb746d1488e1624b54c37c112c2a086f364b7f354cb1364d2b3ccb689ebc9506","last_reissued_at":"2026-05-18T00:52:28.469376Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:52:28.469376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1511.07471","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:52:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NiJB+IbwpdgpGkIlo25L/118L2+QPsWEKwcrac9j8eRxwtLUSe4EHaXEU+w5GicSckR4jcuUnqjMNI7oHvVeDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T04:34:34.363131Z"},"content_sha256":"7926a753fc0ffe0f18d3b54b8233c50f1d39773a4da5e37fa7f3af798d3eab9d","schema_version":"1.0","event_id":"sha256:7926a753fc0ffe0f18d3b54b8233c50f1d39773a4da5e37fa7f3af798d3eab9d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:5N2G2FEI4FREWVGDPQISYKQIN4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Weak Convergence Properties of Constrained Emphatic Temporal-difference Learning with Constant and Slowly Diminishing Stepsize","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Huizhen Yu","submitted_at":"2015-11-23T21:29:43Z","abstract_excerpt":"We consider the emphatic temporal-difference (TD) algorithm, ETD($\\lambda$), for learning the value functions of stationary policies in a discounted, finite state and action Markov decision process. The ETD($\\lambda$) algorithm was recently proposed by Sutton, Mahmood, and White to solve a long-standing divergence problem of the standard TD algorithm when it is applied to off-policy training, where data from an exploratory policy are used to evaluate other policies of interest. The almost sure convergence of ETD($\\lambda$) has been proved in our recent work under general off-policy training co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.07471","kind":"arxiv","version":3},"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":"2026-05-18T00:52:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hga7D+w0lD05utRbMNAQNn4dFpKCmqS9coyYGpuSGSdm4yCHvEtS/7PVw8g4PxErs7Z9437hwcC9XgxuWy/IAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T04:34:34.363487Z"},"content_sha256":"f13696d5a0b57868538217cf79a47ede07fe5d451ccc80cf4489e51abedf795c","schema_version":"1.0","event_id":"sha256:f13696d5a0b57868538217cf79a47ede07fe5d451ccc80cf4489e51abedf795c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5N2G2FEI4FREWVGDPQISYKQIN4/bundle.json","state_url":"https://pith.science/pith/5N2G2FEI4FREWVGDPQISYKQIN4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5N2G2FEI4FREWVGDPQISYKQIN4/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":"2026-06-30T04:34:34Z","links":{"resolver":"https://pith.science/pith/5N2G2FEI4FREWVGDPQISYKQIN4","bundle":"https://pith.science/pith/5N2G2FEI4FREWVGDPQISYKQIN4/bundle.json","state":"https://pith.science/pith/5N2G2FEI4FREWVGDPQISYKQIN4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5N2G2FEI4FREWVGDPQISYKQIN4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:5N2G2FEI4FREWVGDPQISYKQIN4","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":"e7e8542c16b0ac17db6bb9b4c0e1f7f8e23dd10f282b6cf135cca2ebd568a47c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-23T21:29:43Z","title_canon_sha256":"2631191bc48070c9c94b80a5552585f8675c77f1b93e55dd49518bd83bc5056d"},"schema_version":"1.0","source":{"id":"1511.07471","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.07471","created_at":"2026-05-18T00:52:28Z"},{"alias_kind":"arxiv_version","alias_value":"1511.07471v3","created_at":"2026-05-18T00:52:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.07471","created_at":"2026-05-18T00:52:28Z"},{"alias_kind":"pith_short_12","alias_value":"5N2G2FEI4FRE","created_at":"2026-05-18T12:29:05Z"},{"alias_kind":"pith_short_16","alias_value":"5N2G2FEI4FREWVGD","created_at":"2026-05-18T12:29:05Z"},{"alias_kind":"pith_short_8","alias_value":"5N2G2FEI","created_at":"2026-05-18T12:29:05Z"}],"graph_snapshots":[{"event_id":"sha256:f13696d5a0b57868538217cf79a47ede07fe5d451ccc80cf4489e51abedf795c","target":"graph","created_at":"2026-05-18T00:52:28Z","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":"We consider the emphatic temporal-difference (TD) algorithm, ETD($\\lambda$), for learning the value functions of stationary policies in a discounted, finite state and action Markov decision process. The ETD($\\lambda$) algorithm was recently proposed by Sutton, Mahmood, and White to solve a long-standing divergence problem of the standard TD algorithm when it is applied to off-policy training, where data from an exploratory policy are used to evaluate other policies of interest. The almost sure convergence of ETD($\\lambda$) has been proved in our recent work under general off-policy training co","authors_text":"Huizhen Yu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-23T21:29:43Z","title":"Weak Convergence Properties of Constrained Emphatic Temporal-difference Learning with Constant and Slowly Diminishing Stepsize"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.07471","kind":"arxiv","version":3},"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":"sha256:7926a753fc0ffe0f18d3b54b8233c50f1d39773a4da5e37fa7f3af798d3eab9d","target":"record","created_at":"2026-05-18T00:52:28Z","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":"e7e8542c16b0ac17db6bb9b4c0e1f7f8e23dd10f282b6cf135cca2ebd568a47c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-23T21:29:43Z","title_canon_sha256":"2631191bc48070c9c94b80a5552585f8675c77f1b93e55dd49518bd83bc5056d"},"schema_version":"1.0","source":{"id":"1511.07471","kind":"arxiv","version":3}},"canonical_sha256":"eb746d1488e1624b54c37c112c2a086f364b7f354cb1364d2b3ccb689ebc9506","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eb746d1488e1624b54c37c112c2a086f364b7f354cb1364d2b3ccb689ebc9506","first_computed_at":"2026-05-18T00:52:28.469376Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:52:28.469376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6wK14IZThYAPQgwxFwlUgSpPUgTQdi4pXcnXnXgdhaI+c8LqJAOEdhJ+QCkCO6gXvxJTmvko2hTXntaLt/G8Dw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:52:28.469987Z","signed_message":"canonical_sha256_bytes"},"source_id":"1511.07471","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7926a753fc0ffe0f18d3b54b8233c50f1d39773a4da5e37fa7f3af798d3eab9d","sha256:f13696d5a0b57868538217cf79a47ede07fe5d451ccc80cf4489e51abedf795c"],"state_sha256":"9fc6d3856834fb0afe04bddc3fa04c690eb8f611d2a941529d7909337703a6f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DSOMtDW7fFj3OsWJyFHFwSd/F+Sj/ghBncylMBpppHgrAn1Wv/mXWfsVJVhUUOxoGllH/ZvZDv0rjNvxVyGBAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T04:34:34.365620Z","bundle_sha256":"6352a5115698a30a73ec5a6b30de1ff31eddbb984c0b82227a9054a517797754"}}