{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:M6LGCLYZTI4GJNKXCJPIBE7YMK","short_pith_number":"pith:M6LGCLYZ","canonical_record":{"source":{"id":"2104.14644","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-29T20:34:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a04ed3481c0a752d8245202a7eae21d8d66261d7329d82c404a081d97d54f75f","abstract_canon_sha256":"3741ea5e4c5a25c2bcef561f2696c31bfebc85bce2df984fca3607e7262cccdd"},"schema_version":"1.0"},"canonical_sha256":"6796612f199a3864b557125e8093f862a17475d3b616f59ec96ae046d82d7fab","source":{"kind":"arxiv","id":"2104.14644","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.14644","created_at":"2026-07-05T02:36:25Z"},{"alias_kind":"arxiv_version","alias_value":"2104.14644v1","created_at":"2026-07-05T02:36:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.14644","created_at":"2026-07-05T02:36:25Z"},{"alias_kind":"pith_short_12","alias_value":"M6LGCLYZTI4G","created_at":"2026-07-05T02:36:25Z"},{"alias_kind":"pith_short_16","alias_value":"M6LGCLYZTI4GJNKX","created_at":"2026-07-05T02:36:25Z"},{"alias_kind":"pith_short_8","alias_value":"M6LGCLYZ","created_at":"2026-07-05T02:36:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:M6LGCLYZTI4GJNKXCJPIBE7YMK","target":"record","payload":{"canonical_record":{"source":{"id":"2104.14644","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-29T20:34:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a04ed3481c0a752d8245202a7eae21d8d66261d7329d82c404a081d97d54f75f","abstract_canon_sha256":"3741ea5e4c5a25c2bcef561f2696c31bfebc85bce2df984fca3607e7262cccdd"},"schema_version":"1.0"},"canonical_sha256":"6796612f199a3864b557125e8093f862a17475d3b616f59ec96ae046d82d7fab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:36:25.018770Z","signature_b64":"G3E0ACUo0Lbtr2nVrbhhojU+1RED9dlqWu9dFdBurH4pRUyUJz+C2c7bVehNLk8PutpgtpBJII1eYhGBdS7hAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6796612f199a3864b557125e8093f862a17475d3b616f59ec96ae046d82d7fab","last_reissued_at":"2026-07-05T02:36:25.018374Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:36:25.018374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.14644","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":"2026-07-05T02:36:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QDR2ml/YVqLex+O68MB9V/hZco+nHw0OS5dNqm6cce5JgZUDlISX877VcraWFV33LVwONQ4SyH3GBAivSyxwDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:52:59.022782Z"},"content_sha256":"44cf1fb0a56fd0e8950cb70735eadd7f2da5c706514f161e117c3f342018142d","schema_version":"1.0","event_id":"sha256:44cf1fb0a56fd0e8950cb70735eadd7f2da5c706514f161e117c3f342018142d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:M6LGCLYZTI4GJNKXCJPIBE7YMK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What is Going on Inside Recurrent Meta Reinforcement Learning Agents?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Doina Precup, Safa Alver","submitted_at":"2021-04-29T20:34:39Z","abstract_excerpt":"Recurrent meta reinforcement learning (meta-RL) agents are agents that employ a recurrent neural network (RNN) for the purpose of \"learning a learning algorithm\". After being trained on a pre-specified task distribution, the learned weights of the agent's RNN are said to implement an efficient learning algorithm through their activity dynamics, which allows the agent to quickly solve new tasks sampled from the same distribution. However, due to the black-box nature of these agents, the way in which they work is not yet fully understood. In this study, we shed light on the internal working mech"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.14644","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/2104.14644/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":"2026-07-05T02:36:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RJEpkXUdv1tho7c2xVl2YMszCln7yc0ToxaOruZ3xoSXDp2G5xvIq5llzYMS2mOuAOdpn0K/rOjPyKJTOKajCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:52:59.023352Z"},"content_sha256":"21e74ddb727024511a8590382ced3a5390aa81061c1904d42aa531bf66cd5433","schema_version":"1.0","event_id":"sha256:21e74ddb727024511a8590382ced3a5390aa81061c1904d42aa531bf66cd5433"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M6LGCLYZTI4GJNKXCJPIBE7YMK/bundle.json","state_url":"https://pith.science/pith/M6LGCLYZTI4GJNKXCJPIBE7YMK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M6LGCLYZTI4GJNKXCJPIBE7YMK/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":"2026-08-06T06:52:59Z","links":{"resolver":"https://pith.science/pith/M6LGCLYZTI4GJNKXCJPIBE7YMK","bundle":"https://pith.science/pith/M6LGCLYZTI4GJNKXCJPIBE7YMK/bundle.json","state":"https://pith.science/pith/M6LGCLYZTI4GJNKXCJPIBE7YMK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M6LGCLYZTI4GJNKXCJPIBE7YMK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:M6LGCLYZTI4GJNKXCJPIBE7YMK","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":"3741ea5e4c5a25c2bcef561f2696c31bfebc85bce2df984fca3607e7262cccdd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-29T20:34:39Z","title_canon_sha256":"a04ed3481c0a752d8245202a7eae21d8d66261d7329d82c404a081d97d54f75f"},"schema_version":"1.0","source":{"id":"2104.14644","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.14644","created_at":"2026-07-05T02:36:25Z"},{"alias_kind":"arxiv_version","alias_value":"2104.14644v1","created_at":"2026-07-05T02:36:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.14644","created_at":"2026-07-05T02:36:25Z"},{"alias_kind":"pith_short_12","alias_value":"M6LGCLYZTI4G","created_at":"2026-07-05T02:36:25Z"},{"alias_kind":"pith_short_16","alias_value":"M6LGCLYZTI4GJNKX","created_at":"2026-07-05T02:36:25Z"},{"alias_kind":"pith_short_8","alias_value":"M6LGCLYZ","created_at":"2026-07-05T02:36:25Z"}],"graph_snapshots":[{"event_id":"sha256:21e74ddb727024511a8590382ced3a5390aa81061c1904d42aa531bf66cd5433","target":"graph","created_at":"2026-07-05T02:36:25Z","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/2104.14644/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recurrent meta reinforcement learning (meta-RL) agents are agents that employ a recurrent neural network (RNN) for the purpose of \"learning a learning algorithm\". After being trained on a pre-specified task distribution, the learned weights of the agent's RNN are said to implement an efficient learning algorithm through their activity dynamics, which allows the agent to quickly solve new tasks sampled from the same distribution. However, due to the black-box nature of these agents, the way in which they work is not yet fully understood. In this study, we shed light on the internal working mech","authors_text":"Doina Precup, Safa Alver","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-29T20:34:39Z","title":"What is Going on Inside Recurrent Meta Reinforcement Learning Agents?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.14644","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":"sha256:44cf1fb0a56fd0e8950cb70735eadd7f2da5c706514f161e117c3f342018142d","target":"record","created_at":"2026-07-05T02:36:25Z","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":"3741ea5e4c5a25c2bcef561f2696c31bfebc85bce2df984fca3607e7262cccdd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-29T20:34:39Z","title_canon_sha256":"a04ed3481c0a752d8245202a7eae21d8d66261d7329d82c404a081d97d54f75f"},"schema_version":"1.0","source":{"id":"2104.14644","kind":"arxiv","version":1}},"canonical_sha256":"6796612f199a3864b557125e8093f862a17475d3b616f59ec96ae046d82d7fab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6796612f199a3864b557125e8093f862a17475d3b616f59ec96ae046d82d7fab","first_computed_at":"2026-07-05T02:36:25.018374Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:36:25.018374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G3E0ACUo0Lbtr2nVrbhhojU+1RED9dlqWu9dFdBurH4pRUyUJz+C2c7bVehNLk8PutpgtpBJII1eYhGBdS7hAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:36:25.018770Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.14644","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:44cf1fb0a56fd0e8950cb70735eadd7f2da5c706514f161e117c3f342018142d","sha256:21e74ddb727024511a8590382ced3a5390aa81061c1904d42aa531bf66cd5433"],"state_sha256":"184038867f8d6eefe91b646845cc42e311a17d236707eb35ad335fba19f6a475"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lkPJDUGOk/oe6Nj9/qNS/yAPjkn3zt42QxBOFKw1RUj3tynVtm4T6ojemBHj4590djvxIeJ429tyRKJbkM8XDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:52:59.028895Z","bundle_sha256":"1655f046478b1f72df06479d7a1b96796306c2ffc8c6ce8c66af1d1726850f78"}}