{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BQBLH7FRBPHCKW6G2Q3GRBDO2K","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":"8ea8e5126ca3f99380e40a0164a1494c87d274fb11a3b4fac366918a83d02d48","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-10T03:04:20Z","title_canon_sha256":"1e5ba439ce8e377f2b517be15e25c3d7689d20593598eed77647026462e0fdf1"},"schema_version":"1.0","source":{"id":"2407.07333","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.07333","created_at":"2026-07-05T09:35:34Z"},{"alias_kind":"arxiv_version","alias_value":"2407.07333v3","created_at":"2026-07-05T09:35:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07333","created_at":"2026-07-05T09:35:34Z"},{"alias_kind":"pith_short_12","alias_value":"BQBLH7FRBPHC","created_at":"2026-07-05T09:35:34Z"},{"alias_kind":"pith_short_16","alias_value":"BQBLH7FRBPHCKW6G","created_at":"2026-07-05T09:35:34Z"},{"alias_kind":"pith_short_8","alias_value":"BQBLH7FR","created_at":"2026-07-05T09:35:34Z"}],"graph_snapshots":[{"event_id":"sha256:948ab788f7270595a85e79dc45cbf8e847a03ea9008d57c3b0d52ab53344a13a","target":"graph","created_at":"2026-07-05T09:35:34Z","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/2407.07333/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning algorithms typically rely on the assumption that the environment dynamics and value function can be expressed in terms of a Markovian state representation. However, when state information is only partially observable, how can an agent learn such a state representation, and how can it detect when it has found one? We introduce a metric that can accomplish both objectives, without requiring access to -- or knowledge of -- an underlying, unobservable state space. Our metric, the $\\lambda$-discrepancy, is the difference between two distinct temporal difference (TD) value est","authors_text":"Aaron Kirtland, Cameron Allen, Daniel Scott, George Konidaris, Michael L. Littman, Nicholas Petrocelli, Omer Gottesman, Ronald Parr, Ruo Yu Tao, Sam Lobel","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-10T03:04:20Z","title":"Mitigating Partial Observability in Sequential Decision Processes via the Lambda Discrepancy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07333","kind":"arxiv","version":3},"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":"sha256:39d259a83c422fc045757881e8c9a579deeafe8594c2945a7ed0673980fd4d7a","target":"record","created_at":"2026-07-05T09:35:34Z","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":"8ea8e5126ca3f99380e40a0164a1494c87d274fb11a3b4fac366918a83d02d48","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-10T03:04:20Z","title_canon_sha256":"1e5ba439ce8e377f2b517be15e25c3d7689d20593598eed77647026462e0fdf1"},"schema_version":"1.0","source":{"id":"2407.07333","kind":"arxiv","version":3}},"canonical_sha256":"0c02b3fcb10bce255bc6d43668846ed29c685ce212e8b8a7ab43eaa36cd22ecc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0c02b3fcb10bce255bc6d43668846ed29c685ce212e8b8a7ab43eaa36cd22ecc","first_computed_at":"2026-07-05T09:35:34.717620Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:35:34.717620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QdBsST53xNN689bEG7o1/tWZEKgRDqzwQCUpx/I4qRzX/RPOi9hBB2BZfnSGaMcJVdOcKNQHKjiNoh3+55N7Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:35:34.718120Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.07333","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39d259a83c422fc045757881e8c9a579deeafe8594c2945a7ed0673980fd4d7a","sha256:948ab788f7270595a85e79dc45cbf8e847a03ea9008d57c3b0d52ab53344a13a"],"state_sha256":"e39dd2ecf423739f37e8c6ed58a8c61543b9a1a0f6371b24e4669aa97e85bfae"}