{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:3Z6UTH5JBA3YUKRXPFJ6SK5MUP","short_pith_number":"pith:3Z6UTH5J","canonical_record":{"source":{"id":"1611.02779","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-11-09T00:13:29Z","cross_cats_sorted":["cs.LG","cs.NE","stat.ML"],"title_canon_sha256":"c4cde087b46374f241a6892f8ba00973acd3ed656fed03604f6a33cbb5729415","abstract_canon_sha256":"c98c92656612e56cc683a6787c58f527f49370db6ff0ee09368ac329d038e5ce"},"schema_version":"1.0"},"canonical_sha256":"de7d499fa908378a2a377953e92baca3c52b3355323391983f925659fb173cf9","source":{"kind":"arxiv","id":"1611.02779","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.02779","created_at":"2026-05-18T00:59:41Z"},{"alias_kind":"arxiv_version","alias_value":"1611.02779v2","created_at":"2026-05-18T00:59:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.02779","created_at":"2026-05-18T00:59:41Z"},{"alias_kind":"pith_short_12","alias_value":"3Z6UTH5JBA3Y","created_at":"2026-05-18T12:29:58Z"},{"alias_kind":"pith_short_16","alias_value":"3Z6UTH5JBA3YUKRX","created_at":"2026-05-18T12:29:58Z"},{"alias_kind":"pith_short_8","alias_value":"3Z6UTH5J","created_at":"2026-05-18T12:29:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:3Z6UTH5JBA3YUKRXPFJ6SK5MUP","target":"record","payload":{"canonical_record":{"source":{"id":"1611.02779","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-11-09T00:13:29Z","cross_cats_sorted":["cs.LG","cs.NE","stat.ML"],"title_canon_sha256":"c4cde087b46374f241a6892f8ba00973acd3ed656fed03604f6a33cbb5729415","abstract_canon_sha256":"c98c92656612e56cc683a6787c58f527f49370db6ff0ee09368ac329d038e5ce"},"schema_version":"1.0"},"canonical_sha256":"de7d499fa908378a2a377953e92baca3c52b3355323391983f925659fb173cf9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:59:41.411466Z","signature_b64":"m0I5S1zAH2X2B7fiPvd5bKO9Z1rApqhfDfyVIAmRTyWueEMIpnlyjmeUpgw4VWnbKFeI0gmrZpkIefOdlMESDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de7d499fa908378a2a377953e92baca3c52b3355323391983f925659fb173cf9","last_reissued_at":"2026-05-18T00:59:41.410847Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:59:41.410847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.02779","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":"2026-05-18T00:59:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FWkAF7oheJKb79uOBrpXbgkofg7OGcXyV/xWA8vBOK9TZdrMl4PaNVN42gnmtp9FNy9AkqiP86FMc7XbBlubBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T15:52:15.857678Z"},"content_sha256":"fc1d7373dcd605674d61339f5249e1bc0ecc23d99239e98bef292caa524022b3","schema_version":"1.0","event_id":"sha256:fc1d7373dcd605674d61339f5249e1bc0ecc23d99239e98bef292caa524022b3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:3Z6UTH5JBA3YUKRXPFJ6SK5MUP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","stat.ML"],"primary_cat":"cs.AI","authors_text":"Ilya Sutskever, John Schulman, Peter L. Bartlett, Pieter Abbeel, Xi Chen, Yan Duan","submitted_at":"2016-11-09T00:13:29Z","abstract_excerpt":"Deep reinforcement learning (deep RL) has been successful in learning sophisticated behaviors automatically; however, the learning process requires a huge number of trials. In contrast, animals can learn new tasks in just a few trials, benefiting from their prior knowledge about the world. This paper seeks to bridge this gap. Rather than designing a \"fast\" reinforcement learning algorithm, we propose to represent it as a recurrent neural network (RNN) and learn it from data. In our proposed method, RL$^2$, the algorithm is encoded in the weights of the RNN, which are learned slowly through a g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.02779","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":""},"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":"2026-05-18T00:59:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KKUIKv7okf96N2+wH6HefzkjpYANVozzgUKIHgrjqD8zTs5f5/tGpwKiet5CTCWYOKKMIjpaeKDZJQ5M3ZmeAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T15:52:15.858023Z"},"content_sha256":"a26f18cd02bf43d8c738bc81d36590f780091dd930577ec10161491da44caa66","schema_version":"1.0","event_id":"sha256:a26f18cd02bf43d8c738bc81d36590f780091dd930577ec10161491da44caa66"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3Z6UTH5JBA3YUKRXPFJ6SK5MUP/bundle.json","state_url":"https://pith.science/pith/3Z6UTH5JBA3YUKRXPFJ6SK5MUP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3Z6UTH5JBA3YUKRXPFJ6SK5MUP/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":"2026-05-30T15:52:15Z","links":{"resolver":"https://pith.science/pith/3Z6UTH5JBA3YUKRXPFJ6SK5MUP","bundle":"https://pith.science/pith/3Z6UTH5JBA3YUKRXPFJ6SK5MUP/bundle.json","state":"https://pith.science/pith/3Z6UTH5JBA3YUKRXPFJ6SK5MUP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3Z6UTH5JBA3YUKRXPFJ6SK5MUP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:3Z6UTH5JBA3YUKRXPFJ6SK5MUP","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":"c98c92656612e56cc683a6787c58f527f49370db6ff0ee09368ac329d038e5ce","cross_cats_sorted":["cs.LG","cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-11-09T00:13:29Z","title_canon_sha256":"c4cde087b46374f241a6892f8ba00973acd3ed656fed03604f6a33cbb5729415"},"schema_version":"1.0","source":{"id":"1611.02779","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.02779","created_at":"2026-05-18T00:59:41Z"},{"alias_kind":"arxiv_version","alias_value":"1611.02779v2","created_at":"2026-05-18T00:59:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.02779","created_at":"2026-05-18T00:59:41Z"},{"alias_kind":"pith_short_12","alias_value":"3Z6UTH5JBA3Y","created_at":"2026-05-18T12:29:58Z"},{"alias_kind":"pith_short_16","alias_value":"3Z6UTH5JBA3YUKRX","created_at":"2026-05-18T12:29:58Z"},{"alias_kind":"pith_short_8","alias_value":"3Z6UTH5J","created_at":"2026-05-18T12:29:58Z"}],"graph_snapshots":[{"event_id":"sha256:a26f18cd02bf43d8c738bc81d36590f780091dd930577ec10161491da44caa66","target":"graph","created_at":"2026-05-18T00:59:41Z","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 (deep RL) has been successful in learning sophisticated behaviors automatically; however, the learning process requires a huge number of trials. In contrast, animals can learn new tasks in just a few trials, benefiting from their prior knowledge about the world. This paper seeks to bridge this gap. Rather than designing a \"fast\" reinforcement learning algorithm, we propose to represent it as a recurrent neural network (RNN) and learn it from data. In our proposed method, RL$^2$, the algorithm is encoded in the weights of the RNN, which are learned slowly through a g","authors_text":"Ilya Sutskever, John Schulman, Peter L. Bartlett, Pieter Abbeel, Xi Chen, Yan Duan","cross_cats":["cs.LG","cs.NE","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-11-09T00:13:29Z","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.02779","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:fc1d7373dcd605674d61339f5249e1bc0ecc23d99239e98bef292caa524022b3","target":"record","created_at":"2026-05-18T00:59:41Z","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":"c98c92656612e56cc683a6787c58f527f49370db6ff0ee09368ac329d038e5ce","cross_cats_sorted":["cs.LG","cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-11-09T00:13:29Z","title_canon_sha256":"c4cde087b46374f241a6892f8ba00973acd3ed656fed03604f6a33cbb5729415"},"schema_version":"1.0","source":{"id":"1611.02779","kind":"arxiv","version":2}},"canonical_sha256":"de7d499fa908378a2a377953e92baca3c52b3355323391983f925659fb173cf9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de7d499fa908378a2a377953e92baca3c52b3355323391983f925659fb173cf9","first_computed_at":"2026-05-18T00:59:41.410847Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:59:41.410847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m0I5S1zAH2X2B7fiPvd5bKO9Z1rApqhfDfyVIAmRTyWueEMIpnlyjmeUpgw4VWnbKFeI0gmrZpkIefOdlMESDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:59:41.411466Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.02779","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc1d7373dcd605674d61339f5249e1bc0ecc23d99239e98bef292caa524022b3","sha256:a26f18cd02bf43d8c738bc81d36590f780091dd930577ec10161491da44caa66"],"state_sha256":"78045af7e6c806bb30fc220bc73b298ed6bc16ee566a18daa41d6924519a109e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hyYFyGrtY1z1ebS393hVtQzs1tSPaLfazfaBD0d6nsHtQzEsxgEiXLaNCFQA6uU2L6dbAhZNW4L6OSC7BqHvCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T15:52:15.860038Z","bundle_sha256":"d322e1bf5735aa7f233e5e78bd1abe2b39a236165cd83d2071aa369a512eb54b"}}