{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SVXXI4RIQ7KUZA5HU44OOASDE4","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":"b1e2b9a28aee2532bbb2140c7f884cc4e4a1f862d25a9ac14d4bbe079d8ba0fe","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-18T13:18:36Z","title_canon_sha256":"1e790a721b3806224733327cabed0d31f602746fecdf50ec32709768cdd242dd"},"schema_version":"1.0","source":{"id":"2506.15446","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.15446","created_at":"2026-07-05T11:23:43Z"},{"alias_kind":"arxiv_version","alias_value":"2506.15446v1","created_at":"2026-07-05T11:23:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15446","created_at":"2026-07-05T11:23:43Z"},{"alias_kind":"pith_short_12","alias_value":"SVXXI4RIQ7KU","created_at":"2026-07-05T11:23:43Z"},{"alias_kind":"pith_short_16","alias_value":"SVXXI4RIQ7KUZA5H","created_at":"2026-07-05T11:23:43Z"},{"alias_kind":"pith_short_8","alias_value":"SVXXI4RI","created_at":"2026-07-05T11:23:43Z"}],"graph_snapshots":[{"event_id":"sha256:8a369e987ea3748a7ce1f5b28c0f30fcfe143eba86c7e1e906e570ba45715ab8","target":"graph","created_at":"2026-07-05T11:23:43Z","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/2506.15446/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work has shown that, under certain assumptions, zero-shot reinforcement learning (RL) methods can generalise to any unseen task in an environment after reward-free pre-training. Access to Markov states is one such assumption, yet, in many real-world applications, the Markov state is only partially observable. Here, we explore how the performance of standard zero-shot RL methods degrades when subjected to partially observability, and show that, as in single-task RL, memory-based architectures are an effective remedy. We evaluate our memory-based zero-shot RL methods in domains where the ","authors_text":"Jonathan M. Cullen, Scott Jeen, Tom Bewley","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-18T13:18:36Z","title":"Zero-Shot Reinforcement Learning Under Partial Observability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15446","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:e91639527a3f06efdd8d48455ea6885fe6d30d5bcbbc30788642a2116067f190","target":"record","created_at":"2026-07-05T11:23:43Z","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":"b1e2b9a28aee2532bbb2140c7f884cc4e4a1f862d25a9ac14d4bbe079d8ba0fe","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-18T13:18:36Z","title_canon_sha256":"1e790a721b3806224733327cabed0d31f602746fecdf50ec32709768cdd242dd"},"schema_version":"1.0","source":{"id":"2506.15446","kind":"arxiv","version":1}},"canonical_sha256":"956f74722887d54c83a7a738e70243272d70121fb2f6fe642bdba285a1bb4db5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"956f74722887d54c83a7a738e70243272d70121fb2f6fe642bdba285a1bb4db5","first_computed_at":"2026-07-05T11:23:43.677989Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:23:43.677989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yNcjCP3JV8BCkD+esox9Fx82fJ6aNJeTDT97aPWNYFNmdBV3jOP7KuGM9Fdm7eN+Ov2aUgCAmi0VAnqK6gHdDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:23:43.678468Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.15446","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e91639527a3f06efdd8d48455ea6885fe6d30d5bcbbc30788642a2116067f190","sha256:8a369e987ea3748a7ce1f5b28c0f30fcfe143eba86c7e1e906e570ba45715ab8"],"state_sha256":"27cb11f16da11e9fa06fec1c6322660c06c2d565e948a410f7fbc43519c0f6b3"}