{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2YSORSCBNCRDD6KRWPWD7Y2YQQ","short_pith_number":"pith:2YSORSCB","schema_version":"1.0","canonical_sha256":"d624e8c84168a231f951b3ec3fe358841b3b1d7f55e5d970b29cd30861f8162d","source":{"kind":"arxiv","id":"1903.07665","version":2},"attestation_state":"computed","paper":{"title":"Unpredictable Planning Under Partial Observability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Bo Wu, Michael Hibbard, Takashi Tanaka, Ufuk Topcu, Yagiz Savas","submitted_at":"2019-03-18T18:41:49Z","abstract_excerpt":"We study the problem of synthesizing a controller that maximizes the entropy of a partially observable Markov decision process (POMDP) subject to a constraint on the expected total reward. Such a controller minimizes the predictability of a decision-maker's trajectories while guaranteeing the completion of a task expressed by a reward function. First, we prove that a decision-maker with perfect observations can randomize its paths at least as well as a decision-maker with partial observations. Then, focusing on finite-state controllers, we recast the entropy maximization problem as a so-called"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1903.07665","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-03-18T18:41:49Z","cross_cats_sorted":[],"title_canon_sha256":"22912fc76ed9323e554ec3f0def95637f192ba22315c0dee11e836bcacfa1ef3","abstract_canon_sha256":"e0aacf4e0651e70992881f1cf95ef3e5b6facdfab319e015971e62c8905e88fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:04:27.289911Z","signature_b64":"kbzMj/iAdwfdOkVVm4CF2fYcUNMZllN5g4a1qtZEvQ2FEWNZR3SWoyC9y/hwQHSw8/usuFxTTj5lN43BBJqFCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d624e8c84168a231f951b3ec3fe358841b3b1d7f55e5d970b29cd30861f8162d","last_reissued_at":"2026-07-05T00:04:27.289439Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:04:27.289439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unpredictable Planning Under Partial Observability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Bo Wu, Michael Hibbard, Takashi Tanaka, Ufuk Topcu, Yagiz Savas","submitted_at":"2019-03-18T18:41:49Z","abstract_excerpt":"We study the problem of synthesizing a controller that maximizes the entropy of a partially observable Markov decision process (POMDP) subject to a constraint on the expected total reward. Such a controller minimizes the predictability of a decision-maker's trajectories while guaranteeing the completion of a task expressed by a reward function. First, we prove that a decision-maker with perfect observations can randomize its paths at least as well as a decision-maker with partial observations. Then, focusing on finite-state controllers, we recast the entropy maximization problem as a so-called"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.07665","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1903.07665/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1903.07665","created_at":"2026-07-05T00:04:27.289504+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.07665v2","created_at":"2026-07-05T00:04:27.289504+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.07665","created_at":"2026-07-05T00:04:27.289504+00:00"},{"alias_kind":"pith_short_12","alias_value":"2YSORSCBNCRD","created_at":"2026-07-05T00:04:27.289504+00:00"},{"alias_kind":"pith_short_16","alias_value":"2YSORSCBNCRDD6KR","created_at":"2026-07-05T00:04:27.289504+00:00"},{"alias_kind":"pith_short_8","alias_value":"2YSORSCB","created_at":"2026-07-05T00:04:27.289504+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2YSORSCBNCRDD6KRWPWD7Y2YQQ","json":"https://pith.science/pith/2YSORSCBNCRDD6KRWPWD7Y2YQQ.json","graph_json":"https://pith.science/api/pith-number/2YSORSCBNCRDD6KRWPWD7Y2YQQ/graph.json","events_json":"https://pith.science/api/pith-number/2YSORSCBNCRDD6KRWPWD7Y2YQQ/events.json","paper":"https://pith.science/paper/2YSORSCB"},"agent_actions":{"view_html":"https://pith.science/pith/2YSORSCBNCRDD6KRWPWD7Y2YQQ","download_json":"https://pith.science/pith/2YSORSCBNCRDD6KRWPWD7Y2YQQ.json","view_paper":"https://pith.science/paper/2YSORSCB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.07665&json=true","fetch_graph":"https://pith.science/api/pith-number/2YSORSCBNCRDD6KRWPWD7Y2YQQ/graph.json","fetch_events":"https://pith.science/api/pith-number/2YSORSCBNCRDD6KRWPWD7Y2YQQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2YSORSCBNCRDD6KRWPWD7Y2YQQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2YSORSCBNCRDD6KRWPWD7Y2YQQ/action/storage_attestation","attest_author":"https://pith.science/pith/2YSORSCBNCRDD6KRWPWD7Y2YQQ/action/author_attestation","sign_citation":"https://pith.science/pith/2YSORSCBNCRDD6KRWPWD7Y2YQQ/action/citation_signature","submit_replication":"https://pith.science/pith/2YSORSCBNCRDD6KRWPWD7Y2YQQ/action/replication_record"}},"created_at":"2026-07-05T00:04:27.289504+00:00","updated_at":"2026-07-05T00:04:27.289504+00:00"}