{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:VK3VN63RNXZODHUHO6EFFUJ3LZ","short_pith_number":"pith:VK3VN63R","canonical_record":{"source":{"id":"1805.09801","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-24T17:45:11Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"749ac15387e81fba1f2e10652dba71c41b5c7fc42fe35dea81db4d410109a0bf","abstract_canon_sha256":"06a9e66d5608d62b737325f42f10257e8bc3299ceb42afdeba0d12f78e905f6c"},"schema_version":"1.0"},"canonical_sha256":"aab756fb716df2e19e87778852d13b5e73f32101f2c4c2cbcfeb66093618900b","source":{"kind":"arxiv","id":"1805.09801","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.09801","created_at":"2026-05-18T00:15:02Z"},{"alias_kind":"arxiv_version","alias_value":"1805.09801v1","created_at":"2026-05-18T00:15:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09801","created_at":"2026-05-18T00:15:02Z"},{"alias_kind":"pith_short_12","alias_value":"VK3VN63RNXZO","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VK3VN63RNXZODHUH","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VK3VN63R","created_at":"2026-05-18T12:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:VK3VN63RNXZODHUHO6EFFUJ3LZ","target":"record","payload":{"canonical_record":{"source":{"id":"1805.09801","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-24T17:45:11Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"749ac15387e81fba1f2e10652dba71c41b5c7fc42fe35dea81db4d410109a0bf","abstract_canon_sha256":"06a9e66d5608d62b737325f42f10257e8bc3299ceb42afdeba0d12f78e905f6c"},"schema_version":"1.0"},"canonical_sha256":"aab756fb716df2e19e87778852d13b5e73f32101f2c4c2cbcfeb66093618900b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:02.791501Z","signature_b64":"2t8BfGIy0AzkuzWXYuT9xdjGW4WJe/U8ai/6a9s2ModSfgo6On1WeTjF7Ktc97q2B521B+H/M/B3/0LO6tBdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aab756fb716df2e19e87778852d13b5e73f32101f2c4c2cbcfeb66093618900b","last_reissued_at":"2026-05-18T00:15:02.790749Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:02.790749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.09801","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":"2026-05-18T00:15:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s+x/wDCdr521a1SITctprWcHCPnkV7IHb708DcoeXRzxcoXokJCfUcR6H67TZmnkiAcEry7yw9LwuXHqGcJBCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T22:04:06.730158Z"},"content_sha256":"46697d876f489ac09b2078f110e87cf03b7d381f69e9a10cf2b8c6cd7be5383b","schema_version":"1.0","event_id":"sha256:46697d876f489ac09b2078f110e87cf03b7d381f69e9a10cf2b8c6cd7be5383b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:VK3VN63RNXZODHUHO6EFFUJ3LZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Meta-Gradient Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Silver, Hado van Hasselt, Zhongwen Xu","submitted_at":"2018-05-24T17:45:11Z","abstract_excerpt":"The goal of reinforcement learning algorithms is to estimate and/or optimise the value function. However, unlike supervised learning, no teacher or oracle is available to provide the true value function. Instead, the majority of reinforcement learning algorithms estimate and/or optimise a proxy for the value function. This proxy is typically based on a sampled and bootstrapped approximation to the true value function, known as a return. The particular choice of return is one of the chief components determining the nature of the algorithm: the rate at which future rewards are discounted; when a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09801","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":"2026-05-18T00:15:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1c3RIvZQrz5vbcvlwxWEhgw3YBAgJ0Tx/dST6lkXwDA6G2DKPySuDX3KQ22u0eEAQ5FnspAOWNXJXfyZUhOMCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T22:04:06.730536Z"},"content_sha256":"e613e2a828872c6dd322f9b82c4f3d2fd0b845d4a1a0b8c2dfa21409e85123f6","schema_version":"1.0","event_id":"sha256:e613e2a828872c6dd322f9b82c4f3d2fd0b845d4a1a0b8c2dfa21409e85123f6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VK3VN63RNXZODHUHO6EFFUJ3LZ/bundle.json","state_url":"https://pith.science/pith/VK3VN63RNXZODHUHO6EFFUJ3LZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VK3VN63RNXZODHUHO6EFFUJ3LZ/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":"2026-05-25T22:04:06Z","links":{"resolver":"https://pith.science/pith/VK3VN63RNXZODHUHO6EFFUJ3LZ","bundle":"https://pith.science/pith/VK3VN63RNXZODHUHO6EFFUJ3LZ/bundle.json","state":"https://pith.science/pith/VK3VN63RNXZODHUHO6EFFUJ3LZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VK3VN63RNXZODHUHO6EFFUJ3LZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:VK3VN63RNXZODHUHO6EFFUJ3LZ","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":"06a9e66d5608d62b737325f42f10257e8bc3299ceb42afdeba0d12f78e905f6c","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-24T17:45:11Z","title_canon_sha256":"749ac15387e81fba1f2e10652dba71c41b5c7fc42fe35dea81db4d410109a0bf"},"schema_version":"1.0","source":{"id":"1805.09801","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.09801","created_at":"2026-05-18T00:15:02Z"},{"alias_kind":"arxiv_version","alias_value":"1805.09801v1","created_at":"2026-05-18T00:15:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09801","created_at":"2026-05-18T00:15:02Z"},{"alias_kind":"pith_short_12","alias_value":"VK3VN63RNXZO","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VK3VN63RNXZODHUH","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VK3VN63R","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:e613e2a828872c6dd322f9b82c4f3d2fd0b845d4a1a0b8c2dfa21409e85123f6","target":"graph","created_at":"2026-05-18T00:15:02Z","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":"The goal of reinforcement learning algorithms is to estimate and/or optimise the value function. However, unlike supervised learning, no teacher or oracle is available to provide the true value function. Instead, the majority of reinforcement learning algorithms estimate and/or optimise a proxy for the value function. This proxy is typically based on a sampled and bootstrapped approximation to the true value function, known as a return. The particular choice of return is one of the chief components determining the nature of the algorithm: the rate at which future rewards are discounted; when a","authors_text":"David Silver, Hado van Hasselt, Zhongwen Xu","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-24T17:45:11Z","title":"Meta-Gradient Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09801","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":"sha256:46697d876f489ac09b2078f110e87cf03b7d381f69e9a10cf2b8c6cd7be5383b","target":"record","created_at":"2026-05-18T00:15:02Z","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":"06a9e66d5608d62b737325f42f10257e8bc3299ceb42afdeba0d12f78e905f6c","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-24T17:45:11Z","title_canon_sha256":"749ac15387e81fba1f2e10652dba71c41b5c7fc42fe35dea81db4d410109a0bf"},"schema_version":"1.0","source":{"id":"1805.09801","kind":"arxiv","version":1}},"canonical_sha256":"aab756fb716df2e19e87778852d13b5e73f32101f2c4c2cbcfeb66093618900b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aab756fb716df2e19e87778852d13b5e73f32101f2c4c2cbcfeb66093618900b","first_computed_at":"2026-05-18T00:15:02.790749Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:02.790749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2t8BfGIy0AzkuzWXYuT9xdjGW4WJe/U8ai/6a9s2ModSfgo6On1WeTjF7Ktc97q2B521B+H/M/B3/0LO6tBdCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:02.791501Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.09801","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:46697d876f489ac09b2078f110e87cf03b7d381f69e9a10cf2b8c6cd7be5383b","sha256:e613e2a828872c6dd322f9b82c4f3d2fd0b845d4a1a0b8c2dfa21409e85123f6"],"state_sha256":"f8d8c53efb14fb2c6c1fde423f0528c5c12f897c900902d65fc132c71e1457e8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XdMNt0HEGCOuqTasR1Cdt5g/z37aWJwMscvPUbXfNfSO/16yZzuWf/GQ3Kd239pTgNWWi1WyoDI+klNesHYXAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T22:04:06.732972Z","bundle_sha256":"cf9f664881c087a40c75500487136dc2f5b8f63bf6198853bc218d4b6f40a2a9"}}