{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5I3ARD4PLAVX73E3GHVK2VGMQL","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":"f6a1c8d0d967f28dc8481f253031d2439d2b72dd697d8b944ff599017b5ecc4f","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-15T17:47:31Z","title_canon_sha256":"a062c3190cb5c4c47a726d0535f902f2e817775c7a1ce223e9efdee4e119acfa"},"schema_version":"1.0","source":{"id":"2306.09312","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.09312","created_at":"2026-07-05T07:05:44Z"},{"alias_kind":"arxiv_version","alias_value":"2306.09312v2","created_at":"2026-07-05T07:05:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09312","created_at":"2026-07-05T07:05:44Z"},{"alias_kind":"pith_short_12","alias_value":"5I3ARD4PLAVX","created_at":"2026-07-05T07:05:44Z"},{"alias_kind":"pith_short_16","alias_value":"5I3ARD4PLAVX73E3","created_at":"2026-07-05T07:05:44Z"},{"alias_kind":"pith_short_8","alias_value":"5I3ARD4P","created_at":"2026-07-05T07:05:44Z"}],"graph_snapshots":[{"event_id":"sha256:38d2fc2a06735005c4fd2714a0f57ce81d080b7cea7f4d2533b6d4f0ef2dea95","target":"graph","created_at":"2026-07-05T07:05:44Z","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/2306.09312/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning agents deployed in the real world often have to cope with partially observable environments. Therefore, most agents employ memory mechanisms to approximate the state of the environment. Recently, there have been impressive success stories in mastering partially observable environments, mostly in the realm of computer games like Dota 2, StarCraft II, or MineCraft. However, existing methods lack interpretability in the sense that it is not comprehensible for humans what the agent stores in its memory. In this regard, we propose a novel memory mechanism that represents past","authors_text":"Fabian Paischer, Markus Hofmarcher, Sepp Hochreiter, Thomas Adler","cross_cats":["cs.AI","cs.CL","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-15T17:47:31Z","title":"Semantic HELM: A Human-Readable Memory for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09312","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:f80e8a5b2c5f1bc658384a4321652ed1f4952087aef725aa1bbaf6ab4ca67c80","target":"record","created_at":"2026-07-05T07:05:44Z","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":"f6a1c8d0d967f28dc8481f253031d2439d2b72dd697d8b944ff599017b5ecc4f","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-15T17:47:31Z","title_canon_sha256":"a062c3190cb5c4c47a726d0535f902f2e817775c7a1ce223e9efdee4e119acfa"},"schema_version":"1.0","source":{"id":"2306.09312","kind":"arxiv","version":2}},"canonical_sha256":"ea36088f8f582b7fec9b31eaad54cc82c7288833f30099abffa163465b6683a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea36088f8f582b7fec9b31eaad54cc82c7288833f30099abffa163465b6683a4","first_computed_at":"2026-07-05T07:05:44.550249Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:05:44.550249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AsJinFxx1OW3nEoBvKHbfz1Dz+it8VqXcb/msR8hJV7R3d0PXq1zLpSGufG8nhqYt+7rlya2i0gjjQHFPMkBCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:05:44.550888Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.09312","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f80e8a5b2c5f1bc658384a4321652ed1f4952087aef725aa1bbaf6ab4ca67c80","sha256:38d2fc2a06735005c4fd2714a0f57ce81d080b7cea7f4d2533b6d4f0ef2dea95"],"state_sha256":"69cc56b3b263996082c8d78138ab84785676dff6822d922774567c8096864e23"}