{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:3R7T7N4J6PAQTKZEEUQZ7UTT6E","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":"835295a56dd39a861ac7a4ac02ae14e78709adad95238045c9e9fd1b08e9b66d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-06-26T21:53:47Z","title_canon_sha256":"e74241cd8d18fa7207456aea3612a2a7373d9366fc616ba1a2fe2f78aab1839f"},"schema_version":"1.0","source":{"id":"2006.15223","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.15223","created_at":"2026-07-05T01:14:03Z"},{"alias_kind":"arxiv_version","alias_value":"2006.15223v1","created_at":"2026-07-05T01:14:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.15223","created_at":"2026-07-05T01:14:03Z"},{"alias_kind":"pith_short_12","alias_value":"3R7T7N4J6PAQ","created_at":"2026-07-05T01:14:03Z"},{"alias_kind":"pith_short_16","alias_value":"3R7T7N4J6PAQTKZE","created_at":"2026-07-05T01:14:03Z"},{"alias_kind":"pith_short_8","alias_value":"3R7T7N4J","created_at":"2026-07-05T01:14:03Z"}],"graph_snapshots":[{"event_id":"sha256:fabcea1bf1a975c45f8a0a5e6b8f70d2f9b934f0de8d7518c8bf6868a65d9ba7","target":"graph","created_at":"2026-07-05T01:14:03Z","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/2006.15223/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a new recurrent agent architecture and associated auxiliary losses which improve reinforcement learning in partially observable tasks requiring long-term memory. We employ a temporal hierarchy, using a slow-ticking recurrent core to allow information to flow more easily over long time spans, and three fast-ticking recurrent cores with connections designed to create an information asymmetry. The \\emph{reaction} core incorporates new observations with input from the slow core to produce the agent's policy; the \\emph{perception} core accesses only short-term observations and informs ","authors_text":"Adam Stooke, Max Jaderberg, Siddhant M. Jayakumar, Valentin Dalibard, Wojciech M. Czarnecki","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-06-26T21:53:47Z","title":"Perception-Prediction-Reaction Agents for Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.15223","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":"sha256:9e2db1f0bc7f6956eb3b89b1567380aee9261528a8be4791e9389db672a61b18","target":"record","created_at":"2026-07-05T01:14:03Z","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":"835295a56dd39a861ac7a4ac02ae14e78709adad95238045c9e9fd1b08e9b66d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-06-26T21:53:47Z","title_canon_sha256":"e74241cd8d18fa7207456aea3612a2a7373d9366fc616ba1a2fe2f78aab1839f"},"schema_version":"1.0","source":{"id":"2006.15223","kind":"arxiv","version":1}},"canonical_sha256":"dc7f3fb789f3c109ab2425219fd273f1190a18ae6ec3c1f79c38dd6ec354325c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc7f3fb789f3c109ab2425219fd273f1190a18ae6ec3c1f79c38dd6ec354325c","first_computed_at":"2026-07-05T01:14:03.400984Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:14:03.400984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V6hrzFI5HU6Rx3M7+tL7G+Gl3Tx/uiuUjx/1IPgnN2msZi9Bp7S1u2lTP2HZ0TLYBRIRUKV2R0xG0c9cHDb6Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:14:03.401349Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.15223","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e2db1f0bc7f6956eb3b89b1567380aee9261528a8be4791e9389db672a61b18","sha256:fabcea1bf1a975c45f8a0a5e6b8f70d2f9b934f0de8d7518c8bf6868a65d9ba7"],"state_sha256":"776696e1ae5c74889d3ff75d1b768684fef2fee5eafa74d139ed8f1601ce9072"}