{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:5LU5SX4YPVRXWTHCULJ4NM32CW","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":"4f4eaaeb82898b53843701d4a60de65fe0f50c5cfbe0395a6736165b934e0555","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-27T22:06:57Z","title_canon_sha256":"731641f95bc7ad134cb36f41d0b456a77d7b6600b15dad2a4594955ef7c7a185"},"schema_version":"1.0","source":{"id":"2010.14641","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.14641","created_at":"2026-07-05T03:39:55Z"},{"alias_kind":"arxiv_version","alias_value":"2010.14641v3","created_at":"2026-07-05T03:39:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.14641","created_at":"2026-07-05T03:39:55Z"},{"alias_kind":"pith_short_12","alias_value":"5LU5SX4YPVRX","created_at":"2026-07-05T03:39:55Z"},{"alias_kind":"pith_short_16","alias_value":"5LU5SX4YPVRXWTHC","created_at":"2026-07-05T03:39:55Z"},{"alias_kind":"pith_short_8","alias_value":"5LU5SX4Y","created_at":"2026-07-05T03:39:55Z"}],"graph_snapshots":[{"event_id":"sha256:e2d988a461cab31a4d30c1a6e0d1877a944c565e9272120ee7bfb6fa3194f9f5","target":"graph","created_at":"2026-07-05T03:39:55Z","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/2010.14641/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning complex robot behaviors through interaction requires structured exploration. Planning should target interactions with the potential to optimize long-term performance, while only reducing uncertainty where conducive to this objective. This paper presents Latent Optimistic Value Exploration (LOVE), a strategy that enables deep exploration through optimism in the face of uncertain long-term rewards. We combine latent world models with value function estimation to predict infinite-horizon returns and recover associated uncertainty via ensembling. The policy is then trained on an upper con","authors_text":"Daniela Rus, Sertac Karaman, Tim Seyde, Wilko Schwarting","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-27T22:06:57Z","title":"Learning to Plan Optimistically: Uncertainty-Guided Deep Exploration via Latent Model Ensembles"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.14641","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":"sha256:3a54f307919b0233f7738d1ebdf4f4ef7fe223593b2754d056b8360db4e7a905","target":"record","created_at":"2026-07-05T03:39:55Z","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":"4f4eaaeb82898b53843701d4a60de65fe0f50c5cfbe0395a6736165b934e0555","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-27T22:06:57Z","title_canon_sha256":"731641f95bc7ad134cb36f41d0b456a77d7b6600b15dad2a4594955ef7c7a185"},"schema_version":"1.0","source":{"id":"2010.14641","kind":"arxiv","version":3}},"canonical_sha256":"eae9d95f987d637b4ce2a2d3c6b37a1593340a801960370ba8bcf06c1d0018ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eae9d95f987d637b4ce2a2d3c6b37a1593340a801960370ba8bcf06c1d0018ab","first_computed_at":"2026-07-05T03:39:55.686727Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:39:55.686727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DalD7cxLO2WK0Ef6hVX7qj5aMPUdKN5Wb52R6wBGy5KP4+CsSaIGGYpzJc9heeRfrM/o/hvCUt+5BhjPQMHrBw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:39:55.687070Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.14641","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3a54f307919b0233f7738d1ebdf4f4ef7fe223593b2754d056b8360db4e7a905","sha256:e2d988a461cab31a4d30c1a6e0d1877a944c565e9272120ee7bfb6fa3194f9f5"],"state_sha256":"4cf86fe8d96bc442270761894cb245a0288be0fe85134ff98d08f2be1a52a435"}