{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:ASDZV3ML4DUU6VFE3QVFU6SFW4","short_pith_number":"pith:ASDZV3ML","schema_version":"1.0","canonical_sha256":"04879aed8be0e94f54a4dc2a5a7a45b721af63533533417f0c792490607613f3","source":{"kind":"arxiv","id":"1207.4166","version":1},"attestation_state":"computed","paper":{"title":"Heuristic Search Value Iteration for POMDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Reid Simmons, Trey Smith","submitted_at":"2012-07-11T15:04:47Z","abstract_excerpt":"We present a novel POMDP planning algorithm called heuristic search value iteration (HSVI).HSVI is an anytime algorithm that returns a policy and a provable bound on its regret with respect to the optimal policy. HSVI gets its power by combining two well-known techniques: attention-focusing search heuristics and piecewise linear convex representations of the value function. HSVI's soundness and convergence have been proven. On some benchmark problems from the literature, HSVI displays speedups of greater than 100 with respect to other state-of-the-art POMDP value iteration algorithms. We also "},"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":"1207.4166","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-07-11T15:04:47Z","cross_cats_sorted":[],"title_canon_sha256":"3aaccc0cf623a82d012bbd3a89c5146d6e4e497046f6c715d078a8938fa5539d","abstract_canon_sha256":"61ea628813801c89fe4a028172b74471034c22c074d46a36fb05c7e2cd864903"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:50:47.497978Z","signature_b64":"Rw4cfO5PwnKJUo3SSyZIskz/OmuHQ0FOzB+EIo+Ad10IPdVGqkVMzr/4hks66mZNZiynMqAMzZf28Bx8F65bBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04879aed8be0e94f54a4dc2a5a7a45b721af63533533417f0c792490607613f3","last_reissued_at":"2026-05-18T03:50:47.497290Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:50:47.497290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Heuristic Search Value Iteration for POMDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Reid Simmons, Trey Smith","submitted_at":"2012-07-11T15:04:47Z","abstract_excerpt":"We present a novel POMDP planning algorithm called heuristic search value iteration (HSVI).HSVI is an anytime algorithm that returns a policy and a provable bound on its regret with respect to the optimal policy. HSVI gets its power by combining two well-known techniques: attention-focusing search heuristics and piecewise linear convex representations of the value function. HSVI's soundness and convergence have been proven. On some benchmark problems from the literature, HSVI displays speedups of greater than 100 with respect to other state-of-the-art POMDP value iteration algorithms. We also "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1207.4166","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":""},"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":"1207.4166","created_at":"2026-05-18T03:50:47.497405+00:00"},{"alias_kind":"arxiv_version","alias_value":"1207.4166v1","created_at":"2026-05-18T03:50:47.497405+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1207.4166","created_at":"2026-05-18T03:50:47.497405+00:00"},{"alias_kind":"pith_short_12","alias_value":"ASDZV3ML4DUU","created_at":"2026-05-18T12:26:58.693483+00:00"},{"alias_kind":"pith_short_16","alias_value":"ASDZV3ML4DUU6VFE","created_at":"2026-05-18T12:26:58.693483+00:00"},{"alias_kind":"pith_short_8","alias_value":"ASDZV3ML","created_at":"2026-05-18T12:26:58.693483+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.14440","citing_title":"Synthesizing POMDP Policies: Sampling Meets Model-checking via Learning","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ASDZV3ML4DUU6VFE3QVFU6SFW4","json":"https://pith.science/pith/ASDZV3ML4DUU6VFE3QVFU6SFW4.json","graph_json":"https://pith.science/api/pith-number/ASDZV3ML4DUU6VFE3QVFU6SFW4/graph.json","events_json":"https://pith.science/api/pith-number/ASDZV3ML4DUU6VFE3QVFU6SFW4/events.json","paper":"https://pith.science/paper/ASDZV3ML"},"agent_actions":{"view_html":"https://pith.science/pith/ASDZV3ML4DUU6VFE3QVFU6SFW4","download_json":"https://pith.science/pith/ASDZV3ML4DUU6VFE3QVFU6SFW4.json","view_paper":"https://pith.science/paper/ASDZV3ML","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1207.4166&json=true","fetch_graph":"https://pith.science/api/pith-number/ASDZV3ML4DUU6VFE3QVFU6SFW4/graph.json","fetch_events":"https://pith.science/api/pith-number/ASDZV3ML4DUU6VFE3QVFU6SFW4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ASDZV3ML4DUU6VFE3QVFU6SFW4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ASDZV3ML4DUU6VFE3QVFU6SFW4/action/storage_attestation","attest_author":"https://pith.science/pith/ASDZV3ML4DUU6VFE3QVFU6SFW4/action/author_attestation","sign_citation":"https://pith.science/pith/ASDZV3ML4DUU6VFE3QVFU6SFW4/action/citation_signature","submit_replication":"https://pith.science/pith/ASDZV3ML4DUU6VFE3QVFU6SFW4/action/replication_record"}},"created_at":"2026-05-18T03:50:47.497405+00:00","updated_at":"2026-05-18T03:50:47.497405+00:00"}