{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:TKBYRYQHYHJ7IICBDN77HXZUE2","short_pith_number":"pith:TKBYRYQH","schema_version":"1.0","canonical_sha256":"9a8388e207c1d3f420411b7ff3df3426b9d5121584c4769bafe011b67474b1ce","source":{"kind":"arxiv","id":"2105.14239","version":1},"attestation_state":"computed","paper":{"title":"Simplified Belief-Dependent Reward MCTS Planning with Guaranteed Tree Consistency","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Andrey Zhitnikov, Ori Sztyglic, Vadim Indelman","submitted_at":"2021-05-29T07:25:11Z","abstract_excerpt":"Partially Observable Markov Decision Processes (POMDPs) are notoriously hard to solve. Most advanced state-of-the-art online solvers leverage ideas of Monte Carlo Tree Search (MCTS). These solvers rapidly converge to the most promising branches of the belief tree, avoiding the suboptimal sections. Most of these algorithms are designed to utilize straightforward access to the state reward and assume the belief-dependent reward is nothing but expectation over the state reward. Thus, they are inapplicable to a more general and essential setting of belief-dependent rewards. One example of such rew"},"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":"2105.14239","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-05-29T07:25:11Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"897f57a177e8c5df94d2ef5b7ee9fe2767c9bdb8f7dd04ae3303667ec1c5baaa","abstract_canon_sha256":"f9f7698ad1eaca7127fba5c3074a8baf164c689b0bb50c50c69b3ce592cb14af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:44:21.714837Z","signature_b64":"Q9s0d1PgqTK7WBjwFAkzPQ5W95qNHOYuCap7IpGsk/AxsThqLDaXQGcZPXkxh8FWeupaoqmTjnQmpbxQNKvLAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a8388e207c1d3f420411b7ff3df3426b9d5121584c4769bafe011b67474b1ce","last_reissued_at":"2026-07-05T02:44:21.714338Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:44:21.714338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simplified Belief-Dependent Reward MCTS Planning with Guaranteed Tree Consistency","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Andrey Zhitnikov, Ori Sztyglic, Vadim Indelman","submitted_at":"2021-05-29T07:25:11Z","abstract_excerpt":"Partially Observable Markov Decision Processes (POMDPs) are notoriously hard to solve. Most advanced state-of-the-art online solvers leverage ideas of Monte Carlo Tree Search (MCTS). These solvers rapidly converge to the most promising branches of the belief tree, avoiding the suboptimal sections. Most of these algorithms are designed to utilize straightforward access to the state reward and assume the belief-dependent reward is nothing but expectation over the state reward. Thus, they are inapplicable to a more general and essential setting of belief-dependent rewards. One example of such rew"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.14239","kind":"arxiv","version":1},"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/2105.14239/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":"2105.14239","created_at":"2026-07-05T02:44:21.714399+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.14239v1","created_at":"2026-07-05T02:44:21.714399+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.14239","created_at":"2026-07-05T02:44:21.714399+00:00"},{"alias_kind":"pith_short_12","alias_value":"TKBYRYQHYHJ7","created_at":"2026-07-05T02:44:21.714399+00:00"},{"alias_kind":"pith_short_16","alias_value":"TKBYRYQHYHJ7IICB","created_at":"2026-07-05T02:44:21.714399+00:00"},{"alias_kind":"pith_short_8","alias_value":"TKBYRYQH","created_at":"2026-07-05T02:44:21.714399+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.16855","citing_title":"Monte Carlo Planning with Large Language Model for Text-Based Game Agents","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TKBYRYQHYHJ7IICBDN77HXZUE2","json":"https://pith.science/pith/TKBYRYQHYHJ7IICBDN77HXZUE2.json","graph_json":"https://pith.science/api/pith-number/TKBYRYQHYHJ7IICBDN77HXZUE2/graph.json","events_json":"https://pith.science/api/pith-number/TKBYRYQHYHJ7IICBDN77HXZUE2/events.json","paper":"https://pith.science/paper/TKBYRYQH"},"agent_actions":{"view_html":"https://pith.science/pith/TKBYRYQHYHJ7IICBDN77HXZUE2","download_json":"https://pith.science/pith/TKBYRYQHYHJ7IICBDN77HXZUE2.json","view_paper":"https://pith.science/paper/TKBYRYQH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.14239&json=true","fetch_graph":"https://pith.science/api/pith-number/TKBYRYQHYHJ7IICBDN77HXZUE2/graph.json","fetch_events":"https://pith.science/api/pith-number/TKBYRYQHYHJ7IICBDN77HXZUE2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TKBYRYQHYHJ7IICBDN77HXZUE2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TKBYRYQHYHJ7IICBDN77HXZUE2/action/storage_attestation","attest_author":"https://pith.science/pith/TKBYRYQHYHJ7IICBDN77HXZUE2/action/author_attestation","sign_citation":"https://pith.science/pith/TKBYRYQHYHJ7IICBDN77HXZUE2/action/citation_signature","submit_replication":"https://pith.science/pith/TKBYRYQHYHJ7IICBDN77HXZUE2/action/replication_record"}},"created_at":"2026-07-05T02:44:21.714399+00:00","updated_at":"2026-07-05T02:44:21.714399+00:00"}