{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:MYBYKGXU3SYPNYZ4ONWAZKO4X3","short_pith_number":"pith:MYBYKGXU","canonical_record":{"source":{"id":"1909.10549","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-23T18:13:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"52009fd57cb96ad3d0e27458f4842bd6d49caa9219ecb257b838a07f35079435","abstract_canon_sha256":"ded3bf5a4d6b64ab921e43e4ebfb2d9655d583fac1f8a7984f3cfcb8ed5ae988"},"schema_version":"1.0"},"canonical_sha256":"6603851af4dcb0f6e33c736c0ca9dcbedc9ff0fe4c7ebb68b0267bbe85def7d7","source":{"kind":"arxiv","id":"1909.10549","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.10549","created_at":"2026-07-05T00:06:21Z"},{"alias_kind":"arxiv_version","alias_value":"1909.10549v1","created_at":"2026-07-05T00:06:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.10549","created_at":"2026-07-05T00:06:21Z"},{"alias_kind":"pith_short_12","alias_value":"MYBYKGXU3SYP","created_at":"2026-07-05T00:06:21Z"},{"alias_kind":"pith_short_16","alias_value":"MYBYKGXU3SYPNYZ4","created_at":"2026-07-05T00:06:21Z"},{"alias_kind":"pith_short_8","alias_value":"MYBYKGXU","created_at":"2026-07-05T00:06:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:MYBYKGXU3SYPNYZ4ONWAZKO4X3","target":"record","payload":{"canonical_record":{"source":{"id":"1909.10549","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-23T18:13:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"52009fd57cb96ad3d0e27458f4842bd6d49caa9219ecb257b838a07f35079435","abstract_canon_sha256":"ded3bf5a4d6b64ab921e43e4ebfb2d9655d583fac1f8a7984f3cfcb8ed5ae988"},"schema_version":"1.0"},"canonical_sha256":"6603851af4dcb0f6e33c736c0ca9dcbedc9ff0fe4c7ebb68b0267bbe85def7d7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:06:21.627926Z","signature_b64":"/gPhY2VSTzUiMswBssPYiQYooOi4Mygsv6tLBxcWS1Z8Ui4G7Ysf7iHWsNxIbxCo4+J+iEqDKcu+NH1mbq1tDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6603851af4dcb0f6e33c736c0ca9dcbedc9ff0fe4c7ebb68b0267bbe85def7d7","last_reissued_at":"2026-07-05T00:06:21.627489Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:06:21.627489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.10549","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":"2026-07-05T00:06:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"73aBOlipTDaPlNH4rMZ3S7Ln1PpT87OWCKIH6SC2SsCjYy9+U3tpTbIAFjC/s6DRJ5OSzTqE5ZmwecxPX4zMCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T08:57:29.634065Z"},"content_sha256":"d8550dd5f2304a10dc6fabf01007a9a7edd0b0cade79626beaf1c0943829d591","schema_version":"1.0","event_id":"sha256:d8550dd5f2304a10dc6fabf01007a9a7edd0b0cade79626beaf1c0943829d591"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:MYBYKGXU3SYPNYZ4ONWAZKO4X3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Loaded DiCE: Trading off Bias and Variance in Any-Order Score Function Estimators for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Gregory Farquhar, Jakob Foerster, Shimon Whiteson","submitted_at":"2019-09-23T18:13:50Z","abstract_excerpt":"Gradient-based methods for optimisation of objectives in stochastic settings with unknown or intractable dynamics require estimators of derivatives. We derive an objective that, under automatic differentiation, produces low-variance unbiased estimators of derivatives at any order. Our objective is compatible with arbitrary advantage estimators, which allows the control of the bias and variance of any-order derivatives when using function approximation. Furthermore, we propose a method to trade off bias and variance of higher order derivatives by discounting the impact of more distant causal de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.10549","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1909.10549/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T00:06:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0r8vrx5c+ZAt5YhlujTd2iAzdRrGSHxriPTX/mduq3gVBDenGeCVrXxJllx9wLjpPLnZd5lan4S4zY/slKgvCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T08:57:29.634603Z"},"content_sha256":"f39614aa5fb05d7778f8d1408011e691dc610f8ae0bd0c565206152b68d86068","schema_version":"1.0","event_id":"sha256:f39614aa5fb05d7778f8d1408011e691dc610f8ae0bd0c565206152b68d86068"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MYBYKGXU3SYPNYZ4ONWAZKO4X3/bundle.json","state_url":"https://pith.science/pith/MYBYKGXU3SYPNYZ4ONWAZKO4X3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MYBYKGXU3SYPNYZ4ONWAZKO4X3/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":"2026-08-11T08:57:29Z","links":{"resolver":"https://pith.science/pith/MYBYKGXU3SYPNYZ4ONWAZKO4X3","bundle":"https://pith.science/pith/MYBYKGXU3SYPNYZ4ONWAZKO4X3/bundle.json","state":"https://pith.science/pith/MYBYKGXU3SYPNYZ4ONWAZKO4X3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MYBYKGXU3SYPNYZ4ONWAZKO4X3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:MYBYKGXU3SYPNYZ4ONWAZKO4X3","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":"ded3bf5a4d6b64ab921e43e4ebfb2d9655d583fac1f8a7984f3cfcb8ed5ae988","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-23T18:13:50Z","title_canon_sha256":"52009fd57cb96ad3d0e27458f4842bd6d49caa9219ecb257b838a07f35079435"},"schema_version":"1.0","source":{"id":"1909.10549","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.10549","created_at":"2026-07-05T00:06:21Z"},{"alias_kind":"arxiv_version","alias_value":"1909.10549v1","created_at":"2026-07-05T00:06:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.10549","created_at":"2026-07-05T00:06:21Z"},{"alias_kind":"pith_short_12","alias_value":"MYBYKGXU3SYP","created_at":"2026-07-05T00:06:21Z"},{"alias_kind":"pith_short_16","alias_value":"MYBYKGXU3SYPNYZ4","created_at":"2026-07-05T00:06:21Z"},{"alias_kind":"pith_short_8","alias_value":"MYBYKGXU","created_at":"2026-07-05T00:06:21Z"}],"graph_snapshots":[{"event_id":"sha256:f39614aa5fb05d7778f8d1408011e691dc610f8ae0bd0c565206152b68d86068","target":"graph","created_at":"2026-07-05T00:06:21Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1909.10549/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Gradient-based methods for optimisation of objectives in stochastic settings with unknown or intractable dynamics require estimators of derivatives. We derive an objective that, under automatic differentiation, produces low-variance unbiased estimators of derivatives at any order. Our objective is compatible with arbitrary advantage estimators, which allows the control of the bias and variance of any-order derivatives when using function approximation. Furthermore, we propose a method to trade off bias and variance of higher order derivatives by discounting the impact of more distant causal de","authors_text":"Gregory Farquhar, Jakob Foerster, Shimon Whiteson","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-23T18:13:50Z","title":"Loaded DiCE: Trading off Bias and Variance in Any-Order Score Function Estimators for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.10549","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:d8550dd5f2304a10dc6fabf01007a9a7edd0b0cade79626beaf1c0943829d591","target":"record","created_at":"2026-07-05T00:06:21Z","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":"ded3bf5a4d6b64ab921e43e4ebfb2d9655d583fac1f8a7984f3cfcb8ed5ae988","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-23T18:13:50Z","title_canon_sha256":"52009fd57cb96ad3d0e27458f4842bd6d49caa9219ecb257b838a07f35079435"},"schema_version":"1.0","source":{"id":"1909.10549","kind":"arxiv","version":1}},"canonical_sha256":"6603851af4dcb0f6e33c736c0ca9dcbedc9ff0fe4c7ebb68b0267bbe85def7d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6603851af4dcb0f6e33c736c0ca9dcbedc9ff0fe4c7ebb68b0267bbe85def7d7","first_computed_at":"2026-07-05T00:06:21.627489Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:06:21.627489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/gPhY2VSTzUiMswBssPYiQYooOi4Mygsv6tLBxcWS1Z8Ui4G7Ysf7iHWsNxIbxCo4+J+iEqDKcu+NH1mbq1tDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:06:21.627926Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.10549","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d8550dd5f2304a10dc6fabf01007a9a7edd0b0cade79626beaf1c0943829d591","sha256:f39614aa5fb05d7778f8d1408011e691dc610f8ae0bd0c565206152b68d86068"],"state_sha256":"e56694a43832881ab51b22ee62ba5e05d55c4e47a3c858c370b1abd2d75a96b8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jt07uNdVBs0E4R23mD28YvQywyGXyCvGVzeJoq/EvS63KF9m6+xCM2egKOjWAxVpcDO/HCsd4CEgAhki7ty1CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T08:57:29.640024Z","bundle_sha256":"53c01d5365764741e7a65d13ca6a2e4f419177fd1432e008164353122d93ebe8"}}