{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:5LNSAYFFO2FUZFR53FUAPUODKR","short_pith_number":"pith:5LNSAYFF","canonical_record":{"source":{"id":"1803.01489","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-05T03:59:48Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c4e2df910b29f1b44542bcd9a244ac2774e9a6fa90d3ca4c581201edd1d02db2","abstract_canon_sha256":"2662f4e6b09db08d29441bfdc47eece3705993aaccdd2d9fdf44265e4cd7bb5b"},"schema_version":"1.0"},"canonical_sha256":"eadb2060a5768b4c963dd96807d1c35461c6b51e7811109c38ea6fb48471bc6f","source":{"kind":"arxiv","id":"1803.01489","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.01489","created_at":"2026-05-18T00:22:00Z"},{"alias_kind":"arxiv_version","alias_value":"1803.01489v1","created_at":"2026-05-18T00:22:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.01489","created_at":"2026-05-18T00:22:00Z"},{"alias_kind":"pith_short_12","alias_value":"5LNSAYFFO2FU","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5LNSAYFFO2FUZFR5","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5LNSAYFF","created_at":"2026-05-18T12:32:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:5LNSAYFFO2FUZFR53FUAPUODKR","target":"record","payload":{"canonical_record":{"source":{"id":"1803.01489","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-05T03:59:48Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c4e2df910b29f1b44542bcd9a244ac2774e9a6fa90d3ca4c581201edd1d02db2","abstract_canon_sha256":"2662f4e6b09db08d29441bfdc47eece3705993aaccdd2d9fdf44265e4cd7bb5b"},"schema_version":"1.0"},"canonical_sha256":"eadb2060a5768b4c963dd96807d1c35461c6b51e7811109c38ea6fb48471bc6f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:00.513401Z","signature_b64":"GPmk2zGKXKZ0zbGQ2Q6EWOIoUypB9EJ590bp683O9eJXfYb/Fu180LdCOz78bdrGd7nrEAGFcS9ZYZs0I+5hDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eadb2060a5768b4c963dd96807d1c35461c6b51e7811109c38ea6fb48471bc6f","last_reissued_at":"2026-05-18T00:22:00.512870Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:00.512870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.01489","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":"2026-05-18T00:22:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X/uUVl8CslhKbWbtpWA1YKQs2vjMNXkTx0dFSMHqGqX3mPlxMHyH3RKbLV2Xjrf+B8dzU0kzQardc473b6FODg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T22:51:24.478465Z"},"content_sha256":"4ca0113c032c6d5407733d79ffef715986c5d92efabbb641e66377f7a1527827","schema_version":"1.0","event_id":"sha256:4ca0113c032c6d5407733d79ffef715986c5d92efabbb641e66377f7a1527827"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:5LNSAYFFO2FUZFR53FUAPUODKR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Recurrent Predictive State Policy Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Ahmed Hefny, Geoffrey Gordon, Siddhartha Srinivasa, Wen Sun, Zita Marinho","submitted_at":"2018-03-05T03:59:48Z","abstract_excerpt":"We introduce Recurrent Predictive State Policy (RPSP) networks, a recurrent architecture that brings insights from predictive state representations to reinforcement learning in partially observable environments. Predictive state policy networks consist of a recursive filter, which keeps track of a belief about the state of the environment, and a reactive policy that directly maps beliefs to actions, to maximize the cumulative reward. The recursive filter leverages predictive state representations (PSRs) (Rosencrantz and Gordon, 2004; Sun et al., 2016) by modeling predictive state-- a predictio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.01489","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":""},"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":"2026-05-18T00:22:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ebnO09ut4mWalEzCA5B8R8U0jJVVMVK/PV5+ltFMTKNXPVnVtWw2f16Zha3ysMs6ZxFeZ7d4ndh4llm5xB+6Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T22:51:24.479139Z"},"content_sha256":"f86a2eb8be70d3e1a0a6f57415395dacde6ed1e815ce0bfdd8e4fe4a98272499","schema_version":"1.0","event_id":"sha256:f86a2eb8be70d3e1a0a6f57415395dacde6ed1e815ce0bfdd8e4fe4a98272499"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5LNSAYFFO2FUZFR53FUAPUODKR/bundle.json","state_url":"https://pith.science/pith/5LNSAYFFO2FUZFR53FUAPUODKR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5LNSAYFFO2FUZFR53FUAPUODKR/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":"2026-05-20T22:51:24Z","links":{"resolver":"https://pith.science/pith/5LNSAYFFO2FUZFR53FUAPUODKR","bundle":"https://pith.science/pith/5LNSAYFFO2FUZFR53FUAPUODKR/bundle.json","state":"https://pith.science/pith/5LNSAYFFO2FUZFR53FUAPUODKR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5LNSAYFFO2FUZFR53FUAPUODKR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:5LNSAYFFO2FUZFR53FUAPUODKR","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":"2662f4e6b09db08d29441bfdc47eece3705993aaccdd2d9fdf44265e4cd7bb5b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-05T03:59:48Z","title_canon_sha256":"c4e2df910b29f1b44542bcd9a244ac2774e9a6fa90d3ca4c581201edd1d02db2"},"schema_version":"1.0","source":{"id":"1803.01489","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.01489","created_at":"2026-05-18T00:22:00Z"},{"alias_kind":"arxiv_version","alias_value":"1803.01489v1","created_at":"2026-05-18T00:22:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.01489","created_at":"2026-05-18T00:22:00Z"},{"alias_kind":"pith_short_12","alias_value":"5LNSAYFFO2FU","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5LNSAYFFO2FUZFR5","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5LNSAYFF","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:f86a2eb8be70d3e1a0a6f57415395dacde6ed1e815ce0bfdd8e4fe4a98272499","target":"graph","created_at":"2026-05-18T00:22:00Z","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":"We introduce Recurrent Predictive State Policy (RPSP) networks, a recurrent architecture that brings insights from predictive state representations to reinforcement learning in partially observable environments. Predictive state policy networks consist of a recursive filter, which keeps track of a belief about the state of the environment, and a reactive policy that directly maps beliefs to actions, to maximize the cumulative reward. The recursive filter leverages predictive state representations (PSRs) (Rosencrantz and Gordon, 2004; Sun et al., 2016) by modeling predictive state-- a predictio","authors_text":"Ahmed Hefny, Geoffrey Gordon, Siddhartha Srinivasa, Wen Sun, Zita Marinho","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-05T03:59:48Z","title":"Recurrent Predictive State Policy Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.01489","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":"sha256:4ca0113c032c6d5407733d79ffef715986c5d92efabbb641e66377f7a1527827","target":"record","created_at":"2026-05-18T00:22:00Z","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":"2662f4e6b09db08d29441bfdc47eece3705993aaccdd2d9fdf44265e4cd7bb5b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-05T03:59:48Z","title_canon_sha256":"c4e2df910b29f1b44542bcd9a244ac2774e9a6fa90d3ca4c581201edd1d02db2"},"schema_version":"1.0","source":{"id":"1803.01489","kind":"arxiv","version":1}},"canonical_sha256":"eadb2060a5768b4c963dd96807d1c35461c6b51e7811109c38ea6fb48471bc6f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eadb2060a5768b4c963dd96807d1c35461c6b51e7811109c38ea6fb48471bc6f","first_computed_at":"2026-05-18T00:22:00.512870Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:00.512870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GPmk2zGKXKZ0zbGQ2Q6EWOIoUypB9EJ590bp683O9eJXfYb/Fu180LdCOz78bdrGd7nrEAGFcS9ZYZs0I+5hDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:00.513401Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.01489","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ca0113c032c6d5407733d79ffef715986c5d92efabbb641e66377f7a1527827","sha256:f86a2eb8be70d3e1a0a6f57415395dacde6ed1e815ce0bfdd8e4fe4a98272499"],"state_sha256":"dc6373d2e0bee4bc50489881485b9e98724fb9f23c5a14af61974a448c83ab45"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6JGBQq1ddwKa2Uq1BDSyK5KvGF31JOewFZZB7lmdJv42iSEmMyZAhJoP0y9b/NGuQjhwQheHL91iPXg6Ol62Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T22:51:24.483403Z","bundle_sha256":"c13753bcf2ee557c35ccdcba58c99c2ddfe9547d52d2b21b9f1ae94ba01a571a"}}