{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:WUD56ZCHKECMEKZTAGAMTDM4JD","short_pith_number":"pith:WUD56ZCH","canonical_record":{"source":{"id":"2106.13125","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-24T15:58:01Z","cross_cats_sorted":[],"title_canon_sha256":"f1497946c3941e6c1b167910948def9c3788e3c19c6d2d608bcd5ddd2e473d02","abstract_canon_sha256":"ef30eb299a995cea76b3fad4b34ac234bc5e39c6e31588b819e4b0ce9530a5dd"},"schema_version":"1.0"},"canonical_sha256":"b507df64475104c22b330180c98d9c48dd54b69bfa0dc9ffb09f9601a2648612","source":{"kind":"arxiv","id":"2106.13125","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.13125","created_at":"2026-07-05T03:28:38Z"},{"alias_kind":"arxiv_version","alias_value":"2106.13125v2","created_at":"2026-07-05T03:28:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13125","created_at":"2026-07-05T03:28:38Z"},{"alias_kind":"pith_short_12","alias_value":"WUD56ZCHKECM","created_at":"2026-07-05T03:28:38Z"},{"alias_kind":"pith_short_16","alias_value":"WUD56ZCHKECMEKZT","created_at":"2026-07-05T03:28:38Z"},{"alias_kind":"pith_short_8","alias_value":"WUD56ZCH","created_at":"2026-07-05T03:28:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:WUD56ZCHKECMEKZTAGAMTDM4JD","target":"record","payload":{"canonical_record":{"source":{"id":"2106.13125","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-24T15:58:01Z","cross_cats_sorted":[],"title_canon_sha256":"f1497946c3941e6c1b167910948def9c3788e3c19c6d2d608bcd5ddd2e473d02","abstract_canon_sha256":"ef30eb299a995cea76b3fad4b34ac234bc5e39c6e31588b819e4b0ce9530a5dd"},"schema_version":"1.0"},"canonical_sha256":"b507df64475104c22b330180c98d9c48dd54b69bfa0dc9ffb09f9601a2648612","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:28:38.329259Z","signature_b64":"J7e4yo16STeIBuSWUlN1rJWZ7qbNqPjeYv4XgVBSGy2AZcE0mWidS048kBANZ3aT756aukHD66sntqNB2jHLCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b507df64475104c22b330180c98d9c48dd54b69bfa0dc9ffb09f9601a2648612","last_reissued_at":"2026-07-05T03:28:38.328810Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:28:38.328810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.13125","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":"2026-07-05T03:28:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"89fUMmwk8YAJAN4yGEzfOIgHnYnAehhfbOczallJ/fPaOik5FynMxLGgUgOkzrz5g0QszuIQvQoSHv0JE20pAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:11:02.400680Z"},"content_sha256":"5d4d65d07adbca1090c9ecb1994b256535f7a72fb09dd7129ef9e85b0204645c","schema_version":"1.0","event_id":"sha256:5d4d65d07adbca1090c9ecb1994b256535f7a72fb09dd7129ef9e85b0204645c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:WUD56ZCHKECMEKZTAGAMTDM4JD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unifying Gradient Estimators for Meta-Reinforcement Learning via Off-Policy Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Mark Rowland, Michal Valko, R\\'emi Munos, Tadashi Kozuno, Yunhao Tang","submitted_at":"2021-06-24T15:58:01Z","abstract_excerpt":"Model-agnostic meta-reinforcement learning requires estimating the Hessian matrix of value functions. This is challenging from an implementation perspective, as repeatedly differentiating policy gradient estimates may lead to biased Hessian estimates. In this work, we provide a unifying framework for estimating higher-order derivatives of value functions, based on off-policy evaluation. Our framework interprets a number of prior approaches as special cases and elucidates the bias and variance trade-off of Hessian estimates. This framework also opens the door to a new family of estimates, which"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13125","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2106.13125/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":"2026-07-05T03:28:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OJz2yy9grr6EAh2uf4FCTdHToYG/prjnn901Qm7l9rSN8Icvdu/84xCzw76ySKNI/eos+SE8lc9brVhPxdt4DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:11:02.401493Z"},"content_sha256":"cd176461ab250c2d93147f42a0dc48ecb8c3d4b188229198a7fbd2b8bea30859","schema_version":"1.0","event_id":"sha256:cd176461ab250c2d93147f42a0dc48ecb8c3d4b188229198a7fbd2b8bea30859"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WUD56ZCHKECMEKZTAGAMTDM4JD/bundle.json","state_url":"https://pith.science/pith/WUD56ZCHKECMEKZTAGAMTDM4JD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WUD56ZCHKECMEKZTAGAMTDM4JD/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":"2026-08-05T10:11:02Z","links":{"resolver":"https://pith.science/pith/WUD56ZCHKECMEKZTAGAMTDM4JD","bundle":"https://pith.science/pith/WUD56ZCHKECMEKZTAGAMTDM4JD/bundle.json","state":"https://pith.science/pith/WUD56ZCHKECMEKZTAGAMTDM4JD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WUD56ZCHKECMEKZTAGAMTDM4JD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:WUD56ZCHKECMEKZTAGAMTDM4JD","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":"ef30eb299a995cea76b3fad4b34ac234bc5e39c6e31588b819e4b0ce9530a5dd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-24T15:58:01Z","title_canon_sha256":"f1497946c3941e6c1b167910948def9c3788e3c19c6d2d608bcd5ddd2e473d02"},"schema_version":"1.0","source":{"id":"2106.13125","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.13125","created_at":"2026-07-05T03:28:38Z"},{"alias_kind":"arxiv_version","alias_value":"2106.13125v2","created_at":"2026-07-05T03:28:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13125","created_at":"2026-07-05T03:28:38Z"},{"alias_kind":"pith_short_12","alias_value":"WUD56ZCHKECM","created_at":"2026-07-05T03:28:38Z"},{"alias_kind":"pith_short_16","alias_value":"WUD56ZCHKECMEKZT","created_at":"2026-07-05T03:28:38Z"},{"alias_kind":"pith_short_8","alias_value":"WUD56ZCH","created_at":"2026-07-05T03:28:38Z"}],"graph_snapshots":[{"event_id":"sha256:cd176461ab250c2d93147f42a0dc48ecb8c3d4b188229198a7fbd2b8bea30859","target":"graph","created_at":"2026-07-05T03:28:38Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2106.13125/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-agnostic meta-reinforcement learning requires estimating the Hessian matrix of value functions. This is challenging from an implementation perspective, as repeatedly differentiating policy gradient estimates may lead to biased Hessian estimates. In this work, we provide a unifying framework for estimating higher-order derivatives of value functions, based on off-policy evaluation. Our framework interprets a number of prior approaches as special cases and elucidates the bias and variance trade-off of Hessian estimates. This framework also opens the door to a new family of estimates, which","authors_text":"Mark Rowland, Michal Valko, R\\'emi Munos, Tadashi Kozuno, Yunhao Tang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-24T15:58:01Z","title":"Unifying Gradient Estimators for Meta-Reinforcement Learning via Off-Policy Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13125","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":"sha256:5d4d65d07adbca1090c9ecb1994b256535f7a72fb09dd7129ef9e85b0204645c","target":"record","created_at":"2026-07-05T03:28:38Z","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":"ef30eb299a995cea76b3fad4b34ac234bc5e39c6e31588b819e4b0ce9530a5dd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-24T15:58:01Z","title_canon_sha256":"f1497946c3941e6c1b167910948def9c3788e3c19c6d2d608bcd5ddd2e473d02"},"schema_version":"1.0","source":{"id":"2106.13125","kind":"arxiv","version":2}},"canonical_sha256":"b507df64475104c22b330180c98d9c48dd54b69bfa0dc9ffb09f9601a2648612","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b507df64475104c22b330180c98d9c48dd54b69bfa0dc9ffb09f9601a2648612","first_computed_at":"2026-07-05T03:28:38.328810Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:28:38.328810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J7e4yo16STeIBuSWUlN1rJWZ7qbNqPjeYv4XgVBSGy2AZcE0mWidS048kBANZ3aT756aukHD66sntqNB2jHLCw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:28:38.329259Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.13125","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d4d65d07adbca1090c9ecb1994b256535f7a72fb09dd7129ef9e85b0204645c","sha256:cd176461ab250c2d93147f42a0dc48ecb8c3d4b188229198a7fbd2b8bea30859"],"state_sha256":"75a3822520e8b825aa17fdacfc4cebd6a809643bd4ac34710c5e22e6389e8bd6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v6K4WAIqEv3q+GNCD2SdqKzg53pOoLrsAtFqhOqfEilKj+b7RG0MmHtdJ1HOg+E0+gquWf3+Sd1D2HHPrRdKAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T10:11:02.406629Z","bundle_sha256":"686fd2c2407853feb47a558f6e7d8aaf056b9528cec954086dfba9e01252922c"}}