{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:AT3RYEHQPWPBGJRFX544V3H6G6","short_pith_number":"pith:AT3RYEHQ","canonical_record":{"source":{"id":"1509.03044","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-09-10T07:45:30Z","cross_cats_sorted":["cs.AI","cs.SY"],"title_canon_sha256":"e5cb3795d3956aa4315c4c87f3692e3d80ea9f43fffac2229f334392567b0d37","abstract_canon_sha256":"78b646ea258c799b5efa0b1209c52dd3f5c2ed7a04326062017f216d87ea7f7e"},"schema_version":"1.0"},"canonical_sha256":"04f71c10f07d9e132625bf79caecfe37ac07f65ff8e89d60975e07a066d98961","source":{"kind":"arxiv","id":"1509.03044","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1509.03044","created_at":"2026-05-18T01:26:31Z"},{"alias_kind":"arxiv_version","alias_value":"1509.03044v2","created_at":"2026-05-18T01:26:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1509.03044","created_at":"2026-05-18T01:26:31Z"},{"alias_kind":"pith_short_12","alias_value":"AT3RYEHQPWPB","created_at":"2026-05-18T12:29:10Z"},{"alias_kind":"pith_short_16","alias_value":"AT3RYEHQPWPBGJRF","created_at":"2026-05-18T12:29:10Z"},{"alias_kind":"pith_short_8","alias_value":"AT3RYEHQ","created_at":"2026-05-18T12:29:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:AT3RYEHQPWPBGJRFX544V3H6G6","target":"record","payload":{"canonical_record":{"source":{"id":"1509.03044","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-09-10T07:45:30Z","cross_cats_sorted":["cs.AI","cs.SY"],"title_canon_sha256":"e5cb3795d3956aa4315c4c87f3692e3d80ea9f43fffac2229f334392567b0d37","abstract_canon_sha256":"78b646ea258c799b5efa0b1209c52dd3f5c2ed7a04326062017f216d87ea7f7e"},"schema_version":"1.0"},"canonical_sha256":"04f71c10f07d9e132625bf79caecfe37ac07f65ff8e89d60975e07a066d98961","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:26:31.244252Z","signature_b64":"SCwL3vSGP6MS6uKoZJNhAKC16nXijYIEfhBMRIrdLkcgHKoWd7cfASarsE+5y9c+cemSv6bTTNsdp1Tm4lJuAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04f71c10f07d9e132625bf79caecfe37ac07f65ff8e89d60975e07a066d98961","last_reissued_at":"2026-05-18T01:26:31.243609Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:26:31.243609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1509.03044","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":"2026-05-18T01:26:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"20ZOSWMiLJ1CuosliwpXURQ0fuh4OVLwgJWNMbbA6lZcb415+cTK1pfbCm8IbGeDVaJoOavm640Z6TEgHh9uBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T12:54:31.398557Z"},"content_sha256":"ac602eed6098443304c2f472f278291f11b87c43a6ff87e6b450ee2f9e9629cc","schema_version":"1.0","event_id":"sha256:ac602eed6098443304c2f472f278291f11b87c43a6ff87e6b450ee2f9e9629cc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:AT3RYEHQPWPBGJRFX544V3H6G6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Recurrent Reinforcement Learning: A Hybrid Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY"],"primary_cat":"cs.LG","authors_text":"Jianfeng Gao, Jianshu Chen, Ji He, Li Deng, Lihong Li, Xiaodong He, Xiujun Li","submitted_at":"2015-09-10T07:45:30Z","abstract_excerpt":"Successful applications of reinforcement learning in real-world problems often require dealing with partially observable states. It is in general very challenging to construct and infer hidden states as they often depend on the agent's entire interaction history and may require substantial domain knowledge. In this work, we investigate a deep-learning approach to learning the representation of states in partially observable tasks, with minimal prior knowledge of the domain. In particular, we propose a new family of hybrid models that combines the strength of both supervised learning (SL) and r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1509.03044","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":"2026-05-18T01:26:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AC3H6PVmXzUPcngZLXpNpHrjdhxfndDICCtxD5jbdQ60YJkHvQ1UGbyP4QW9qkI3mOQPbdlMyWdFyYo9usdnDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T12:54:31.398902Z"},"content_sha256":"b3c1fd9fc8cd322b1d67770024165248085f61a07f54570c6e314420f756c5dd","schema_version":"1.0","event_id":"sha256:b3c1fd9fc8cd322b1d67770024165248085f61a07f54570c6e314420f756c5dd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AT3RYEHQPWPBGJRFX544V3H6G6/bundle.json","state_url":"https://pith.science/pith/AT3RYEHQPWPBGJRFX544V3H6G6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AT3RYEHQPWPBGJRFX544V3H6G6/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":"2026-06-05T12:54:31Z","links":{"resolver":"https://pith.science/pith/AT3RYEHQPWPBGJRFX544V3H6G6","bundle":"https://pith.science/pith/AT3RYEHQPWPBGJRFX544V3H6G6/bundle.json","state":"https://pith.science/pith/AT3RYEHQPWPBGJRFX544V3H6G6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AT3RYEHQPWPBGJRFX544V3H6G6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:AT3RYEHQPWPBGJRFX544V3H6G6","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":"78b646ea258c799b5efa0b1209c52dd3f5c2ed7a04326062017f216d87ea7f7e","cross_cats_sorted":["cs.AI","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-09-10T07:45:30Z","title_canon_sha256":"e5cb3795d3956aa4315c4c87f3692e3d80ea9f43fffac2229f334392567b0d37"},"schema_version":"1.0","source":{"id":"1509.03044","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1509.03044","created_at":"2026-05-18T01:26:31Z"},{"alias_kind":"arxiv_version","alias_value":"1509.03044v2","created_at":"2026-05-18T01:26:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1509.03044","created_at":"2026-05-18T01:26:31Z"},{"alias_kind":"pith_short_12","alias_value":"AT3RYEHQPWPB","created_at":"2026-05-18T12:29:10Z"},{"alias_kind":"pith_short_16","alias_value":"AT3RYEHQPWPBGJRF","created_at":"2026-05-18T12:29:10Z"},{"alias_kind":"pith_short_8","alias_value":"AT3RYEHQ","created_at":"2026-05-18T12:29:10Z"}],"graph_snapshots":[{"event_id":"sha256:b3c1fd9fc8cd322b1d67770024165248085f61a07f54570c6e314420f756c5dd","target":"graph","created_at":"2026-05-18T01:26:31Z","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":"Successful applications of reinforcement learning in real-world problems often require dealing with partially observable states. It is in general very challenging to construct and infer hidden states as they often depend on the agent's entire interaction history and may require substantial domain knowledge. In this work, we investigate a deep-learning approach to learning the representation of states in partially observable tasks, with minimal prior knowledge of the domain. In particular, we propose a new family of hybrid models that combines the strength of both supervised learning (SL) and r","authors_text":"Jianfeng Gao, Jianshu Chen, Ji He, Li Deng, Lihong Li, Xiaodong He, Xiujun Li","cross_cats":["cs.AI","cs.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-09-10T07:45:30Z","title":"Recurrent Reinforcement Learning: A Hybrid Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1509.03044","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:ac602eed6098443304c2f472f278291f11b87c43a6ff87e6b450ee2f9e9629cc","target":"record","created_at":"2026-05-18T01:26:31Z","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":"78b646ea258c799b5efa0b1209c52dd3f5c2ed7a04326062017f216d87ea7f7e","cross_cats_sorted":["cs.AI","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-09-10T07:45:30Z","title_canon_sha256":"e5cb3795d3956aa4315c4c87f3692e3d80ea9f43fffac2229f334392567b0d37"},"schema_version":"1.0","source":{"id":"1509.03044","kind":"arxiv","version":2}},"canonical_sha256":"04f71c10f07d9e132625bf79caecfe37ac07f65ff8e89d60975e07a066d98961","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"04f71c10f07d9e132625bf79caecfe37ac07f65ff8e89d60975e07a066d98961","first_computed_at":"2026-05-18T01:26:31.243609Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:26:31.243609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SCwL3vSGP6MS6uKoZJNhAKC16nXijYIEfhBMRIrdLkcgHKoWd7cfASarsE+5y9c+cemSv6bTTNsdp1Tm4lJuAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:26:31.244252Z","signed_message":"canonical_sha256_bytes"},"source_id":"1509.03044","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac602eed6098443304c2f472f278291f11b87c43a6ff87e6b450ee2f9e9629cc","sha256:b3c1fd9fc8cd322b1d67770024165248085f61a07f54570c6e314420f756c5dd"],"state_sha256":"8332dd41e845256c0ca689e10c06aa64e91c24cb2a488a1252a255ec605bdf30"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8WG16wwWujBghhq4hTmRTSFjcC8SODQ2HxTBdoB4kt5R8eLf8IUDHby4qJmWAaTCdA4CD4tvuCaeovPNKPPqAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T12:54:31.400850Z","bundle_sha256":"128d369539af168915cb47baee880fe5df100d9074377fd381ec79709611e233"}}