{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ATKBZNJORJU65IEZGZP4VXBIKB","short_pith_number":"pith:ATKBZNJO","schema_version":"1.0","canonical_sha256":"04d41cb52e8a69eea099365fcadc2850489ce29ec46dfaadc266be247704f004","source":{"kind":"arxiv","id":"2305.16209","version":4},"attestation_state":"computed","paper":{"title":"C-MCTS: Safe Planning with Monte Carlo Tree Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Axel Plinge, Christopher Mutschler, Dinesh Parthasarathy, Georgios Kontes","submitted_at":"2023-05-25T16:08:30Z","abstract_excerpt":"The Constrained Markov Decision Process (CMDP) formulation allows to solve safety-critical decision making tasks that are subject to constraints. While CMDPs have been extensively studied in the Reinforcement Learning literature, little attention has been given to sampling-based planning algorithms such as MCTS for solving them. Previous approaches perform conservatively with respect to costs as they avoid constraint violations by using Monte Carlo cost estimates that suffer from high variance. We propose Constrained MCTS (C-MCTS), which estimates cost using a safety critic that is trained wit"},"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":"2305.16209","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-25T16:08:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0d63b6db25d63f8a139ec87b0602a37742c337ce93a5fa57d62a2e28932e33e0","abstract_canon_sha256":"65f3d1f3996e9d9447d710f04b215f456c681c8821b72625aa9af4cd698155b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:26:21.388650Z","signature_b64":"pt8jD4LR6VBv5bOqxG+xb7aUqYw1yb2IbE1hd+KtTtJ99gix9j4qcH+4EwOygtWgXVxwO08MJXLYDRRb5W3GAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04d41cb52e8a69eea099365fcadc2850489ce29ec46dfaadc266be247704f004","last_reissued_at":"2026-07-05T09:26:21.388156Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:26:21.388156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"C-MCTS: Safe Planning with Monte Carlo Tree Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Axel Plinge, Christopher Mutschler, Dinesh Parthasarathy, Georgios Kontes","submitted_at":"2023-05-25T16:08:30Z","abstract_excerpt":"The Constrained Markov Decision Process (CMDP) formulation allows to solve safety-critical decision making tasks that are subject to constraints. While CMDPs have been extensively studied in the Reinforcement Learning literature, little attention has been given to sampling-based planning algorithms such as MCTS for solving them. Previous approaches perform conservatively with respect to costs as they avoid constraint violations by using Monte Carlo cost estimates that suffer from high variance. We propose Constrained MCTS (C-MCTS), which estimates cost using a safety critic that is trained wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16209","kind":"arxiv","version":4},"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/2305.16209/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":"2305.16209","created_at":"2026-07-05T09:26:21.388213+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.16209v4","created_at":"2026-07-05T09:26:21.388213+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16209","created_at":"2026-07-05T09:26:21.388213+00:00"},{"alias_kind":"pith_short_12","alias_value":"ATKBZNJORJU6","created_at":"2026-07-05T09:26:21.388213+00:00"},{"alias_kind":"pith_short_16","alias_value":"ATKBZNJORJU65IEZ","created_at":"2026-07-05T09:26:21.388213+00:00"},{"alias_kind":"pith_short_8","alias_value":"ATKBZNJO","created_at":"2026-07-05T09:26:21.388213+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.17679","citing_title":"A Hamilton-Jacobi Reachability-Guided Search Framework for Efficient and Safe Indoor Planar Robot Navigation","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ATKBZNJORJU65IEZGZP4VXBIKB","json":"https://pith.science/pith/ATKBZNJORJU65IEZGZP4VXBIKB.json","graph_json":"https://pith.science/api/pith-number/ATKBZNJORJU65IEZGZP4VXBIKB/graph.json","events_json":"https://pith.science/api/pith-number/ATKBZNJORJU65IEZGZP4VXBIKB/events.json","paper":"https://pith.science/paper/ATKBZNJO"},"agent_actions":{"view_html":"https://pith.science/pith/ATKBZNJORJU65IEZGZP4VXBIKB","download_json":"https://pith.science/pith/ATKBZNJORJU65IEZGZP4VXBIKB.json","view_paper":"https://pith.science/paper/ATKBZNJO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.16209&json=true","fetch_graph":"https://pith.science/api/pith-number/ATKBZNJORJU65IEZGZP4VXBIKB/graph.json","fetch_events":"https://pith.science/api/pith-number/ATKBZNJORJU65IEZGZP4VXBIKB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ATKBZNJORJU65IEZGZP4VXBIKB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ATKBZNJORJU65IEZGZP4VXBIKB/action/storage_attestation","attest_author":"https://pith.science/pith/ATKBZNJORJU65IEZGZP4VXBIKB/action/author_attestation","sign_citation":"https://pith.science/pith/ATKBZNJORJU65IEZGZP4VXBIKB/action/citation_signature","submit_replication":"https://pith.science/pith/ATKBZNJORJU65IEZGZP4VXBIKB/action/replication_record"}},"created_at":"2026-07-05T09:26:21.388213+00:00","updated_at":"2026-07-05T09:26:21.388213+00:00"}