{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:3GFDT742PWQXCSS6HJ6CDAJEPR","short_pith_number":"pith:3GFDT742","canonical_record":{"source":{"id":"2112.15236","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-30T23:10:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4b6b8fa142abbd819dd4f438b86c77e52de4192a82d21d7cb88e50ddede3f709","abstract_canon_sha256":"6e53ef8d1b114b5f592de27c5b59c02bcafcc296bbb47cbfea0e682af670677b"},"schema_version":"1.0"},"canonical_sha256":"d98a39ff9a7da1714a5e3a7c2181247c60c4ece1e38e8596f77db04339e707fe","source":{"kind":"arxiv","id":"2112.15236","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.15236","created_at":"2026-07-05T03:44:37Z"},{"alias_kind":"arxiv_version","alias_value":"2112.15236v1","created_at":"2026-07-05T03:44:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.15236","created_at":"2026-07-05T03:44:37Z"},{"alias_kind":"pith_short_12","alias_value":"3GFDT742PWQX","created_at":"2026-07-05T03:44:37Z"},{"alias_kind":"pith_short_16","alias_value":"3GFDT742PWQXCSS6","created_at":"2026-07-05T03:44:37Z"},{"alias_kind":"pith_short_8","alias_value":"3GFDT742","created_at":"2026-07-05T03:44:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:3GFDT742PWQXCSS6HJ6CDAJEPR","target":"record","payload":{"canonical_record":{"source":{"id":"2112.15236","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-30T23:10:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4b6b8fa142abbd819dd4f438b86c77e52de4192a82d21d7cb88e50ddede3f709","abstract_canon_sha256":"6e53ef8d1b114b5f592de27c5b59c02bcafcc296bbb47cbfea0e682af670677b"},"schema_version":"1.0"},"canonical_sha256":"d98a39ff9a7da1714a5e3a7c2181247c60c4ece1e38e8596f77db04339e707fe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:44:37.814255Z","signature_b64":"MyJr6Pv8URc8Q6cgkzLgehzSeJLOxty5jfLaX650AEdnN4Lc3JQgSzsuFHTt+ggUdCKR9KOwFdECxPTBRTYcDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d98a39ff9a7da1714a5e3a7c2181247c60c4ece1e38e8596f77db04339e707fe","last_reissued_at":"2026-07-05T03:44:37.813835Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:44:37.813835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.15236","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":"2026-07-05T03:44:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VlhKxyxA3qdgIXT2m4RKLIAPbDC6+VM70+11XfRvfmO2vkB7vAzbRkf6oSEpEmnMT4jo7rkEYYCySPAsYFJdAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:50:40.285695Z"},"content_sha256":"cd6db15b95d74e09b4b52951362b0c555e2aeca3f837a4b0eb813da9832eaf8a","schema_version":"1.0","event_id":"sha256:cd6db15b95d74e09b4b52951362b0c555e2aeca3f837a4b0eb813da9832eaf8a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:3GFDT742PWQXCSS6HJ6CDAJEPR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Agent State Online with Recurrent Generate-and-Test","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amir Samani, Richard S. Sutton","submitted_at":"2021-12-30T23:10:32Z","abstract_excerpt":"Learning continually and online from a continuous stream of data is challenging, especially for a reinforcement learning agent with sequential data. When the environment only provides observations giving partial information about the state of the environment, the agent must learn the agent state based on the data stream of experience. We refer to the state learned directly from the data stream of experience as the agent state. Recurrent neural networks can learn the agent state, but the training methods are computationally expensive and sensitive to the hyper-parameters, making them unideal fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.15236","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/2112.15236/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":"2026-07-05T03:44:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JjShuxHfwu09XDeUxSxEsw/wxIxj9cpmD77Qg2cPW6LgeJwqyR8Lh6Xmp4anG7Bqx5bJQgscV5ChaBgIuI1zAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:50:40.286573Z"},"content_sha256":"9ff33d93c271b63086adf4bc6e12a858e07ac785d1d1e807ec3d239485f3ef2d","schema_version":"1.0","event_id":"sha256:9ff33d93c271b63086adf4bc6e12a858e07ac785d1d1e807ec3d239485f3ef2d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3GFDT742PWQXCSS6HJ6CDAJEPR/bundle.json","state_url":"https://pith.science/pith/3GFDT742PWQXCSS6HJ6CDAJEPR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3GFDT742PWQXCSS6HJ6CDAJEPR/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":"2026-08-05T07:50:40Z","links":{"resolver":"https://pith.science/pith/3GFDT742PWQXCSS6HJ6CDAJEPR","bundle":"https://pith.science/pith/3GFDT742PWQXCSS6HJ6CDAJEPR/bundle.json","state":"https://pith.science/pith/3GFDT742PWQXCSS6HJ6CDAJEPR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3GFDT742PWQXCSS6HJ6CDAJEPR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:3GFDT742PWQXCSS6HJ6CDAJEPR","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":"6e53ef8d1b114b5f592de27c5b59c02bcafcc296bbb47cbfea0e682af670677b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-30T23:10:32Z","title_canon_sha256":"4b6b8fa142abbd819dd4f438b86c77e52de4192a82d21d7cb88e50ddede3f709"},"schema_version":"1.0","source":{"id":"2112.15236","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.15236","created_at":"2026-07-05T03:44:37Z"},{"alias_kind":"arxiv_version","alias_value":"2112.15236v1","created_at":"2026-07-05T03:44:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.15236","created_at":"2026-07-05T03:44:37Z"},{"alias_kind":"pith_short_12","alias_value":"3GFDT742PWQX","created_at":"2026-07-05T03:44:37Z"},{"alias_kind":"pith_short_16","alias_value":"3GFDT742PWQXCSS6","created_at":"2026-07-05T03:44:37Z"},{"alias_kind":"pith_short_8","alias_value":"3GFDT742","created_at":"2026-07-05T03:44:37Z"}],"graph_snapshots":[{"event_id":"sha256:9ff33d93c271b63086adf4bc6e12a858e07ac785d1d1e807ec3d239485f3ef2d","target":"graph","created_at":"2026-07-05T03:44:37Z","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/2112.15236/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning continually and online from a continuous stream of data is challenging, especially for a reinforcement learning agent with sequential data. When the environment only provides observations giving partial information about the state of the environment, the agent must learn the agent state based on the data stream of experience. We refer to the state learned directly from the data stream of experience as the agent state. Recurrent neural networks can learn the agent state, but the training methods are computationally expensive and sensitive to the hyper-parameters, making them unideal fo","authors_text":"Amir Samani, Richard S. Sutton","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-30T23:10:32Z","title":"Learning Agent State Online with Recurrent Generate-and-Test"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.15236","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:cd6db15b95d74e09b4b52951362b0c555e2aeca3f837a4b0eb813da9832eaf8a","target":"record","created_at":"2026-07-05T03:44:37Z","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":"6e53ef8d1b114b5f592de27c5b59c02bcafcc296bbb47cbfea0e682af670677b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-30T23:10:32Z","title_canon_sha256":"4b6b8fa142abbd819dd4f438b86c77e52de4192a82d21d7cb88e50ddede3f709"},"schema_version":"1.0","source":{"id":"2112.15236","kind":"arxiv","version":1}},"canonical_sha256":"d98a39ff9a7da1714a5e3a7c2181247c60c4ece1e38e8596f77db04339e707fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d98a39ff9a7da1714a5e3a7c2181247c60c4ece1e38e8596f77db04339e707fe","first_computed_at":"2026-07-05T03:44:37.813835Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:44:37.813835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MyJr6Pv8URc8Q6cgkzLgehzSeJLOxty5jfLaX650AEdnN4Lc3JQgSzsuFHTt+ggUdCKR9KOwFdECxPTBRTYcDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:44:37.814255Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.15236","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd6db15b95d74e09b4b52951362b0c555e2aeca3f837a4b0eb813da9832eaf8a","sha256:9ff33d93c271b63086adf4bc6e12a858e07ac785d1d1e807ec3d239485f3ef2d"],"state_sha256":"17ade4be72a794cf639beeb1f2a4d64f186b1806bde4abfbba003a1993c6fc87"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IT3JAMBDuAsxCBvEb0y5OXW8YQgfGM6xQ+ELCZBbWTZ6DAYvv6GjzqtWd/pZ5EtPPN30mzS88RJXd9sQrKg0Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T07:50:40.290864Z","bundle_sha256":"7c6051ec910b5db8f69c73917cf92dcffd86df817f6f0cb4931d5c2e836cfeb4"}}