{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:WL2ENWWRC4M6UUZMHRZCN4VF5L","short_pith_number":"pith:WL2ENWWR","canonical_record":{"source":{"id":"1611.05763","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-17T16:29:11Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"8ee3556dfddc72ddf7cf235e11b7c6579d128d771cf60f0c807b207004c13b14","abstract_canon_sha256":"b62dae1211324e21f9250ae4deeea9f588474cdbf809fd3e76391371ecad238e"},"schema_version":"1.0"},"canonical_sha256":"b2f446dad11719ea532c3c7226f2a5eac69bd0f1e3279a4a490104d2db8965b2","source":{"kind":"arxiv","id":"1611.05763","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.05763","created_at":"2026-05-18T00:52:22Z"},{"alias_kind":"arxiv_version","alias_value":"1611.05763v3","created_at":"2026-05-18T00:52:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.05763","created_at":"2026-05-18T00:52:22Z"},{"alias_kind":"pith_short_12","alias_value":"WL2ENWWRC4M6","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_16","alias_value":"WL2ENWWRC4M6UUZM","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_8","alias_value":"WL2ENWWR","created_at":"2026-05-18T12:30:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:WL2ENWWRC4M6UUZMHRZCN4VF5L","target":"record","payload":{"canonical_record":{"source":{"id":"1611.05763","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-17T16:29:11Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"8ee3556dfddc72ddf7cf235e11b7c6579d128d771cf60f0c807b207004c13b14","abstract_canon_sha256":"b62dae1211324e21f9250ae4deeea9f588474cdbf809fd3e76391371ecad238e"},"schema_version":"1.0"},"canonical_sha256":"b2f446dad11719ea532c3c7226f2a5eac69bd0f1e3279a4a490104d2db8965b2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:52:22.467790Z","signature_b64":"iI2zxom9Z4f2oEqhxhKV2jl9m2kQX2dxU0rnJzEsjLEuLi4rsFeJa/9/8GJLn1vJpeOb5AnclXgiEyKcd+inBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2f446dad11719ea532c3c7226f2a5eac69bd0f1e3279a4a490104d2db8965b2","last_reissued_at":"2026-05-18T00:52:22.467230Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:52:22.467230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.05763","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:52:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nTZEqHXG/qTFSI8qQNwI4Iadtx5WturvNfi5pKVNzjqwWF+nBOKQubB9nBipDeEibOu350sgr/SUDKRRNqzbBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T21:41:38.623140Z"},"content_sha256":"cd7876b63028ac0c425ebccd78dfa4d080ca1235e70e40ac156e210b3ed999da","schema_version":"1.0","event_id":"sha256:cd7876b63028ac0c425ebccd78dfa4d080ca1235e70e40ac156e210b3ed999da"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:WL2ENWWRC4M6UUZMHRZCN4VF5L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to reinforcement learn","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Charles Blundell, Dharshan Kumaran, Dhruva Tirumala, Hubert Soyer, Jane X Wang, Joel Z Leibo, Matt Botvinick, Remi Munos, Zeb Kurth-Nelson","submitted_at":"2016-11-17T16:29:11Z","abstract_excerpt":"In recent years deep reinforcement learning (RL) systems have attained superhuman performance in a number of challenging task domains. However, a major limitation of such applications is their demand for massive amounts of training data. A critical present objective is thus to develop deep RL methods that can adapt rapidly to new tasks. In the present work we introduce a novel approach to this challenge, which we refer to as deep meta-reinforcement learning. Previous work has shown that recurrent networks can support meta-learning in a fully supervised context. We extend this approach to the R"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.05763","kind":"arxiv","version":3},"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":"2026-05-18T00:52:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"focv0XzJXRkO+2kRu+iewVWa6j6uwptbDL83EpzfMPa5/WfxGLstlaZ/MVmPmF5J+G0+WT8zZeiCc5xnoYfGCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T21:41:38.623889Z"},"content_sha256":"b4c4ddc207c40a07af9b02dfa643894905fc57a7a88d7d7037ed56ac8cea58db","schema_version":"1.0","event_id":"sha256:b4c4ddc207c40a07af9b02dfa643894905fc57a7a88d7d7037ed56ac8cea58db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WL2ENWWRC4M6UUZMHRZCN4VF5L/bundle.json","state_url":"https://pith.science/pith/WL2ENWWRC4M6UUZMHRZCN4VF5L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WL2ENWWRC4M6UUZMHRZCN4VF5L/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":"2026-05-30T21:41:38Z","links":{"resolver":"https://pith.science/pith/WL2ENWWRC4M6UUZMHRZCN4VF5L","bundle":"https://pith.science/pith/WL2ENWWRC4M6UUZMHRZCN4VF5L/bundle.json","state":"https://pith.science/pith/WL2ENWWRC4M6UUZMHRZCN4VF5L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WL2ENWWRC4M6UUZMHRZCN4VF5L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:WL2ENWWRC4M6UUZMHRZCN4VF5L","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":"b62dae1211324e21f9250ae4deeea9f588474cdbf809fd3e76391371ecad238e","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-17T16:29:11Z","title_canon_sha256":"8ee3556dfddc72ddf7cf235e11b7c6579d128d771cf60f0c807b207004c13b14"},"schema_version":"1.0","source":{"id":"1611.05763","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.05763","created_at":"2026-05-18T00:52:22Z"},{"alias_kind":"arxiv_version","alias_value":"1611.05763v3","created_at":"2026-05-18T00:52:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.05763","created_at":"2026-05-18T00:52:22Z"},{"alias_kind":"pith_short_12","alias_value":"WL2ENWWRC4M6","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_16","alias_value":"WL2ENWWRC4M6UUZM","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_8","alias_value":"WL2ENWWR","created_at":"2026-05-18T12:30:48Z"}],"graph_snapshots":[{"event_id":"sha256:b4c4ddc207c40a07af9b02dfa643894905fc57a7a88d7d7037ed56ac8cea58db","target":"graph","created_at":"2026-05-18T00:52:22Z","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":"In recent years deep reinforcement learning (RL) systems have attained superhuman performance in a number of challenging task domains. However, a major limitation of such applications is their demand for massive amounts of training data. A critical present objective is thus to develop deep RL methods that can adapt rapidly to new tasks. In the present work we introduce a novel approach to this challenge, which we refer to as deep meta-reinforcement learning. Previous work has shown that recurrent networks can support meta-learning in a fully supervised context. We extend this approach to the R","authors_text":"Charles Blundell, Dharshan Kumaran, Dhruva Tirumala, Hubert Soyer, Jane X Wang, Joel Z Leibo, Matt Botvinick, Remi Munos, Zeb Kurth-Nelson","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-17T16:29:11Z","title":"Learning to reinforcement learn"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.05763","kind":"arxiv","version":3},"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:cd7876b63028ac0c425ebccd78dfa4d080ca1235e70e40ac156e210b3ed999da","target":"record","created_at":"2026-05-18T00:52:22Z","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":"b62dae1211324e21f9250ae4deeea9f588474cdbf809fd3e76391371ecad238e","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-17T16:29:11Z","title_canon_sha256":"8ee3556dfddc72ddf7cf235e11b7c6579d128d771cf60f0c807b207004c13b14"},"schema_version":"1.0","source":{"id":"1611.05763","kind":"arxiv","version":3}},"canonical_sha256":"b2f446dad11719ea532c3c7226f2a5eac69bd0f1e3279a4a490104d2db8965b2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2f446dad11719ea532c3c7226f2a5eac69bd0f1e3279a4a490104d2db8965b2","first_computed_at":"2026-05-18T00:52:22.467230Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:52:22.467230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iI2zxom9Z4f2oEqhxhKV2jl9m2kQX2dxU0rnJzEsjLEuLi4rsFeJa/9/8GJLn1vJpeOb5AnclXgiEyKcd+inBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:52:22.467790Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.05763","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd7876b63028ac0c425ebccd78dfa4d080ca1235e70e40ac156e210b3ed999da","sha256:b4c4ddc207c40a07af9b02dfa643894905fc57a7a88d7d7037ed56ac8cea58db"],"state_sha256":"a2b8d536857474abb1405ce3557c768812bfd124b49be820d89f8530e5f6fe29"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I02070ibMQ3hJKVlP5s1kiMcGckJ08YiZ1ZX2zStl4bziEROhrOxZ47z++/uO+q5GHc7extOgwS6BZYPQdzSCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T21:41:38.628292Z","bundle_sha256":"6ec5d2990f82edfb1c8b5a1f52dba3195c5dfd0b2ed7febd850ef55fc1c491a0"}}