{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:2E63GGYWXE4T6LF5AO4Y4ZAQE2","short_pith_number":"pith:2E63GGYW","canonical_record":{"source":{"id":"1809.02387","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-07T10:10:12Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"6f49cbb33733dc87266081050c3d1dbd24d55468a9ac632d7be995c8d683bdab","abstract_canon_sha256":"ee4b83d07b5ae6046dac71017776d10375506326bd366b86334ac0375552d5fa"},"schema_version":"1.0"},"canonical_sha256":"d13db31b16b9393f2cbd03b98e641026846e3bddb467a5772e7c6c814a714855","source":{"kind":"arxiv","id":"1809.02387","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.02387","created_at":"2026-05-18T00:06:17Z"},{"alias_kind":"arxiv_version","alias_value":"1809.02387v1","created_at":"2026-05-18T00:06:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.02387","created_at":"2026-05-18T00:06:17Z"},{"alias_kind":"pith_short_12","alias_value":"2E63GGYWXE4T","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"2E63GGYWXE4T6LF5","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"2E63GGYW","created_at":"2026-05-18T12:31:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:2E63GGYWXE4T6LF5AO4Y4ZAQE2","target":"record","payload":{"canonical_record":{"source":{"id":"1809.02387","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-07T10:10:12Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"6f49cbb33733dc87266081050c3d1dbd24d55468a9ac632d7be995c8d683bdab","abstract_canon_sha256":"ee4b83d07b5ae6046dac71017776d10375506326bd366b86334ac0375552d5fa"},"schema_version":"1.0"},"canonical_sha256":"d13db31b16b9393f2cbd03b98e641026846e3bddb467a5772e7c6c814a714855","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:17.268633Z","signature_b64":"Xv3udS5+3pgBn4/zdJrKPlB6TIqkQyGbbWd2isKpOI+bmT463kLv88CMmztiMrmpdEErrp/y4HWSSbmLCGmiBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d13db31b16b9393f2cbd03b98e641026846e3bddb467a5772e7c6c814a714855","last_reissued_at":"2026-05-18T00:06:17.268160Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:17.268160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.02387","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":"2026-05-18T00:06:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GLEfzz4B9myic63Eoemhh3KqqqKEORAcC06a2ilUEtvudI6dwTOAKAzXV18wFWAEvUn/zskz2lOHxwdDHb25Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T14:51:20.421819Z"},"content_sha256":"05f9f75a3a90f21dba90d61d4dd83afcf6604b40297ab6a75fae1aecb487bcef","schema_version":"1.0","event_id":"sha256:05f9f75a3a90f21dba90d61d4dd83afcf6604b40297ab6a75fae1aecb487bcef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:2E63GGYWXE4T6LF5AO4Y4ZAQE2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving On-policy Learning with Statistical Reward Accumulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chen Change Loy, Dahua Lin, Ke Yu, Xiaoou Tang, Yubin Deng","submitted_at":"2018-09-07T10:10:12Z","abstract_excerpt":"Deep reinforcement learning has obtained significant breakthroughs in recent years. Most methods in deep-RL achieve good results via the maximization of the reward signal provided by the environment, typically in the form of discounted cumulative returns. Such reward signals represent the immediate feedback of a particular action performed by an agent. However, tasks with sparse reward signals are still challenging to on-policy methods. In this paper, we introduce an effective characterization of past reward statistics (which can be seen as long-term feedback signals) to supplement this immedi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.02387","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":"2026-05-18T00:06:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gITkL6KJep+7WtkpW2nnqBWaqW4ZW8ZrObipYBAh0bEZkORINvUBSJkt0n8VK8F4HQppEAZfMn4tGoj7H+J4DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T14:51:20.422517Z"},"content_sha256":"48ee90bbea1f778b0a707f81902f11ce364d2941b2425a3ac3a03e46d3509cdb","schema_version":"1.0","event_id":"sha256:48ee90bbea1f778b0a707f81902f11ce364d2941b2425a3ac3a03e46d3509cdb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2E63GGYWXE4T6LF5AO4Y4ZAQE2/bundle.json","state_url":"https://pith.science/pith/2E63GGYWXE4T6LF5AO4Y4ZAQE2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2E63GGYWXE4T6LF5AO4Y4ZAQE2/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":"2026-06-07T14:51:20Z","links":{"resolver":"https://pith.science/pith/2E63GGYWXE4T6LF5AO4Y4ZAQE2","bundle":"https://pith.science/pith/2E63GGYWXE4T6LF5AO4Y4ZAQE2/bundle.json","state":"https://pith.science/pith/2E63GGYWXE4T6LF5AO4Y4ZAQE2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2E63GGYWXE4T6LF5AO4Y4ZAQE2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:2E63GGYWXE4T6LF5AO4Y4ZAQE2","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":"ee4b83d07b5ae6046dac71017776d10375506326bd366b86334ac0375552d5fa","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-07T10:10:12Z","title_canon_sha256":"6f49cbb33733dc87266081050c3d1dbd24d55468a9ac632d7be995c8d683bdab"},"schema_version":"1.0","source":{"id":"1809.02387","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.02387","created_at":"2026-05-18T00:06:17Z"},{"alias_kind":"arxiv_version","alias_value":"1809.02387v1","created_at":"2026-05-18T00:06:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.02387","created_at":"2026-05-18T00:06:17Z"},{"alias_kind":"pith_short_12","alias_value":"2E63GGYWXE4T","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"2E63GGYWXE4T6LF5","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"2E63GGYW","created_at":"2026-05-18T12:31:59Z"}],"graph_snapshots":[{"event_id":"sha256:48ee90bbea1f778b0a707f81902f11ce364d2941b2425a3ac3a03e46d3509cdb","target":"graph","created_at":"2026-05-18T00:06:17Z","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":"Deep reinforcement learning has obtained significant breakthroughs in recent years. Most methods in deep-RL achieve good results via the maximization of the reward signal provided by the environment, typically in the form of discounted cumulative returns. Such reward signals represent the immediate feedback of a particular action performed by an agent. However, tasks with sparse reward signals are still challenging to on-policy methods. In this paper, we introduce an effective characterization of past reward statistics (which can be seen as long-term feedback signals) to supplement this immedi","authors_text":"Chen Change Loy, Dahua Lin, Ke Yu, Xiaoou Tang, Yubin Deng","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-07T10:10:12Z","title":"Improving On-policy Learning with Statistical Reward Accumulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.02387","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":"sha256:05f9f75a3a90f21dba90d61d4dd83afcf6604b40297ab6a75fae1aecb487bcef","target":"record","created_at":"2026-05-18T00:06:17Z","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":"ee4b83d07b5ae6046dac71017776d10375506326bd366b86334ac0375552d5fa","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-07T10:10:12Z","title_canon_sha256":"6f49cbb33733dc87266081050c3d1dbd24d55468a9ac632d7be995c8d683bdab"},"schema_version":"1.0","source":{"id":"1809.02387","kind":"arxiv","version":1}},"canonical_sha256":"d13db31b16b9393f2cbd03b98e641026846e3bddb467a5772e7c6c814a714855","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d13db31b16b9393f2cbd03b98e641026846e3bddb467a5772e7c6c814a714855","first_computed_at":"2026-05-18T00:06:17.268160Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:06:17.268160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Xv3udS5+3pgBn4/zdJrKPlB6TIqkQyGbbWd2isKpOI+bmT463kLv88CMmztiMrmpdEErrp/y4HWSSbmLCGmiBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:06:17.268633Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.02387","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05f9f75a3a90f21dba90d61d4dd83afcf6604b40297ab6a75fae1aecb487bcef","sha256:48ee90bbea1f778b0a707f81902f11ce364d2941b2425a3ac3a03e46d3509cdb"],"state_sha256":"ea4ffc5dada83609c46ac36b492dddc6f3bceae6bfea446be9678671b6d1a442"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OwdEdH/8HCdSrOvD6xvgMrJ9y8Qsl24Ey3qXzZJ4lM9NwpeBvptWbSxvmA4u6flXLpF8o7I4nylcO4QbbkAKCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T14:51:20.426511Z","bundle_sha256":"871508afcac210f370d7b084b27d470f373b8e693bbbda2637df97db353178a7"}}