{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:C5K4B3XGX56QIFQ3HQJJU77NBB","short_pith_number":"pith:C5K4B3XG","canonical_record":{"source":{"id":"1811.06225","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-15T08:18:33Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1423cedf15954481f5d257a6975209eb89ae2941710fd4e7df189f195e1bb7f8","abstract_canon_sha256":"8d9b51e47d39504b201afeaf975dcd8ad5152dd0f5b64e806b4a7f3afd3cec90"},"schema_version":"1.0"},"canonical_sha256":"1755c0eee6bf7d04161b3c129a7fed0858dc6f95f49a74a35f4209cf5a92c341","source":{"kind":"arxiv","id":"1811.06225","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.06225","created_at":"2026-05-18T00:00:38Z"},{"alias_kind":"arxiv_version","alias_value":"1811.06225v1","created_at":"2026-05-18T00:00:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.06225","created_at":"2026-05-18T00:00:38Z"},{"alias_kind":"pith_short_12","alias_value":"C5K4B3XGX56Q","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"C5K4B3XGX56QIFQ3","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"C5K4B3XG","created_at":"2026-05-18T12:32:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:C5K4B3XGX56QIFQ3HQJJU77NBB","target":"record","payload":{"canonical_record":{"source":{"id":"1811.06225","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-15T08:18:33Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1423cedf15954481f5d257a6975209eb89ae2941710fd4e7df189f195e1bb7f8","abstract_canon_sha256":"8d9b51e47d39504b201afeaf975dcd8ad5152dd0f5b64e806b4a7f3afd3cec90"},"schema_version":"1.0"},"canonical_sha256":"1755c0eee6bf7d04161b3c129a7fed0858dc6f95f49a74a35f4209cf5a92c341","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:38.303345Z","signature_b64":"d4EMc16Q6nkUxSuXoiHqJF/xq5NUaWXoEV78A27OjjJW5jGQVCYqgOcWjRU6QPiptV7Y6Lx2mw96DtrjyjuWAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1755c0eee6bf7d04161b3c129a7fed0858dc6f95f49a74a35f4209cf5a92c341","last_reissued_at":"2026-05-18T00:00:38.302890Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:38.302890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.06225","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:00:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TsoKPQ8OwPhC3/ZGkfKAARoIXsy3XnhUNUepUuUVNTmvst7rFR0Cc7T0b9nemlmSzoW1+tTVZF/8CJ812iNqBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T07:17:29.896562Z"},"content_sha256":"9277893fbabb841afd6044b508f99f1ddd5499a883a29206fceb4284dfb3dd91","schema_version":"1.0","event_id":"sha256:9277893fbabb841afd6044b508f99f1ddd5499a883a29206fceb4284dfb3dd91"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:C5K4B3XGX56QIFQ3HQJJU77NBB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reward-estimation variance elimination in sequential decision processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Sergey Pankov","submitted_at":"2018-11-15T08:18:33Z","abstract_excerpt":"Policy gradient methods are very attractive in reinforcement learning due to their model-free nature and convergence guarantees. These methods, however, suffer from high variance in gradient estimation, resulting in poor sample efficiency. To mitigate this issue, a number of variance-reduction approaches have been proposed. Unfortunately, in the challenging problems with delayed rewards, these approaches either bring a relatively modest improvement or do reduce variance at expense of introducing a bias and undermining convergence. The unbiased methods of gradient estimation, in general, only p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.06225","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:00:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Govh/J36FaqlpFM3vVhuYHDKJ/dU0AHbY+Cz2G+T45i4MLFmZZX2M4FG6nWbo21YMDf72gLUo+OKdstUSmH6DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T07:17:29.897288Z"},"content_sha256":"52b845e86676c94aaf16ece4ee2905fea6eacdede0d546fe94556af5781b0f7a","schema_version":"1.0","event_id":"sha256:52b845e86676c94aaf16ece4ee2905fea6eacdede0d546fe94556af5781b0f7a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C5K4B3XGX56QIFQ3HQJJU77NBB/bundle.json","state_url":"https://pith.science/pith/C5K4B3XGX56QIFQ3HQJJU77NBB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C5K4B3XGX56QIFQ3HQJJU77NBB/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":"2026-06-05T07:17:29Z","links":{"resolver":"https://pith.science/pith/C5K4B3XGX56QIFQ3HQJJU77NBB","bundle":"https://pith.science/pith/C5K4B3XGX56QIFQ3HQJJU77NBB/bundle.json","state":"https://pith.science/pith/C5K4B3XGX56QIFQ3HQJJU77NBB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C5K4B3XGX56QIFQ3HQJJU77NBB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:C5K4B3XGX56QIFQ3HQJJU77NBB","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":"8d9b51e47d39504b201afeaf975dcd8ad5152dd0f5b64e806b4a7f3afd3cec90","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-15T08:18:33Z","title_canon_sha256":"1423cedf15954481f5d257a6975209eb89ae2941710fd4e7df189f195e1bb7f8"},"schema_version":"1.0","source":{"id":"1811.06225","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.06225","created_at":"2026-05-18T00:00:38Z"},{"alias_kind":"arxiv_version","alias_value":"1811.06225v1","created_at":"2026-05-18T00:00:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.06225","created_at":"2026-05-18T00:00:38Z"},{"alias_kind":"pith_short_12","alias_value":"C5K4B3XGX56Q","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"C5K4B3XGX56QIFQ3","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"C5K4B3XG","created_at":"2026-05-18T12:32:16Z"}],"graph_snapshots":[{"event_id":"sha256:52b845e86676c94aaf16ece4ee2905fea6eacdede0d546fe94556af5781b0f7a","target":"graph","created_at":"2026-05-18T00:00:38Z","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":"Policy gradient methods are very attractive in reinforcement learning due to their model-free nature and convergence guarantees. These methods, however, suffer from high variance in gradient estimation, resulting in poor sample efficiency. To mitigate this issue, a number of variance-reduction approaches have been proposed. Unfortunately, in the challenging problems with delayed rewards, these approaches either bring a relatively modest improvement or do reduce variance at expense of introducing a bias and undermining convergence. The unbiased methods of gradient estimation, in general, only p","authors_text":"Sergey Pankov","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-15T08:18:33Z","title":"Reward-estimation variance elimination in sequential decision processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.06225","kind":"arxiv","version":1},"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":"sha256:9277893fbabb841afd6044b508f99f1ddd5499a883a29206fceb4284dfb3dd91","target":"record","created_at":"2026-05-18T00:00:38Z","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":"8d9b51e47d39504b201afeaf975dcd8ad5152dd0f5b64e806b4a7f3afd3cec90","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-15T08:18:33Z","title_canon_sha256":"1423cedf15954481f5d257a6975209eb89ae2941710fd4e7df189f195e1bb7f8"},"schema_version":"1.0","source":{"id":"1811.06225","kind":"arxiv","version":1}},"canonical_sha256":"1755c0eee6bf7d04161b3c129a7fed0858dc6f95f49a74a35f4209cf5a92c341","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1755c0eee6bf7d04161b3c129a7fed0858dc6f95f49a74a35f4209cf5a92c341","first_computed_at":"2026-05-18T00:00:38.302890Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:00:38.302890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d4EMc16Q6nkUxSuXoiHqJF/xq5NUaWXoEV78A27OjjJW5jGQVCYqgOcWjRU6QPiptV7Y6Lx2mw96DtrjyjuWAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:00:38.303345Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.06225","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9277893fbabb841afd6044b508f99f1ddd5499a883a29206fceb4284dfb3dd91","sha256:52b845e86676c94aaf16ece4ee2905fea6eacdede0d546fe94556af5781b0f7a"],"state_sha256":"a988640527704e7cf8a686fcd4b59978ef236eb3fe113d16a2e3a1d5e0c64084"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OFUwNj5kC+mfNK23s7Mx2A5XEDgc0yYSgZROKaOZgxbI3zWFt+PkwLgP7uqqREMrS2NoU8u7Suc9/NQmc6ZFAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T07:17:29.901425Z","bundle_sha256":"daf8617091edf8055e49fe4077fd227fc1d4857bbb4a37228db02a30b8520ee9"}}