{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IT5XAPC3YL6NMVIVA2OWNEUFWP","short_pith_number":"pith:IT5XAPC3","schema_version":"1.0","canonical_sha256":"44fb703c5bc2fcd65515069d669285b3fe82442abb81c6c5e3d39141674d0629","source":{"kind":"arxiv","id":"2506.12254","version":1},"attestation_state":"computed","paper":{"title":"Lower Bound on Howard Policy Iteration for Deterministic Markov Decision Processes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DM"],"primary_cat":"cs.AI","authors_text":"Ali Asadi, Jakob de Raaij, Krishnendu Chatterjee","submitted_at":"2025-06-13T22:00:36Z","abstract_excerpt":"Deterministic Markov Decision Processes (DMDPs) are a mathematical framework for decision-making where the outcomes and future possible actions are deterministically determined by the current action taken. DMDPs can be viewed as a finite directed weighted graph, where in each step, the controller chooses an outgoing edge. An objective is a measurable function on runs (or infinite trajectories) of the DMDP, and the value for an objective is the maximal cumulative reward (or weight) that the controller can guarantee. We consider the classical mean-payoff (aka limit-average) objective, which is a"},"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":"2506.12254","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-13T22:00:36Z","cross_cats_sorted":["cs.DM"],"title_canon_sha256":"eb73cbfb27402551c2ef3aba940bdce50c115a757475a72654b208daa0185801","abstract_canon_sha256":"7c0bbfdbb7181556e4dcb3155569970a3a0b5f4e605d769b1e445fd82e2f4ec7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:50.225556Z","signature_b64":"o5sYCPo08NhWoW0Zw7NDX9ZWkFJwc7ee0B/knrQhjfGhX2D0XxtuiiPatK+vnDu7UZ8n88rbsl6Y1cY0j2t3Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44fb703c5bc2fcd65515069d669285b3fe82442abb81c6c5e3d39141674d0629","last_reissued_at":"2026-07-05T11:21:50.225045Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:50.225045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lower Bound on Howard Policy Iteration for Deterministic Markov Decision Processes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DM"],"primary_cat":"cs.AI","authors_text":"Ali Asadi, Jakob de Raaij, Krishnendu Chatterjee","submitted_at":"2025-06-13T22:00:36Z","abstract_excerpt":"Deterministic Markov Decision Processes (DMDPs) are a mathematical framework for decision-making where the outcomes and future possible actions are deterministically determined by the current action taken. DMDPs can be viewed as a finite directed weighted graph, where in each step, the controller chooses an outgoing edge. An objective is a measurable function on runs (or infinite trajectories) of the DMDP, and the value for an objective is the maximal cumulative reward (or weight) that the controller can guarantee. We consider the classical mean-payoff (aka limit-average) objective, which is a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12254","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/2506.12254/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":"2506.12254","created_at":"2026-07-05T11:21:50.225101+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.12254v1","created_at":"2026-07-05T11:21:50.225101+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12254","created_at":"2026-07-05T11:21:50.225101+00:00"},{"alias_kind":"pith_short_12","alias_value":"IT5XAPC3YL6N","created_at":"2026-07-05T11:21:50.225101+00:00"},{"alias_kind":"pith_short_16","alias_value":"IT5XAPC3YL6NMVIV","created_at":"2026-07-05T11:21:50.225101+00:00"},{"alias_kind":"pith_short_8","alias_value":"IT5XAPC3","created_at":"2026-07-05T11:21:50.225101+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/IT5XAPC3YL6NMVIVA2OWNEUFWP","json":"https://pith.science/pith/IT5XAPC3YL6NMVIVA2OWNEUFWP.json","graph_json":"https://pith.science/api/pith-number/IT5XAPC3YL6NMVIVA2OWNEUFWP/graph.json","events_json":"https://pith.science/api/pith-number/IT5XAPC3YL6NMVIVA2OWNEUFWP/events.json","paper":"https://pith.science/paper/IT5XAPC3"},"agent_actions":{"view_html":"https://pith.science/pith/IT5XAPC3YL6NMVIVA2OWNEUFWP","download_json":"https://pith.science/pith/IT5XAPC3YL6NMVIVA2OWNEUFWP.json","view_paper":"https://pith.science/paper/IT5XAPC3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.12254&json=true","fetch_graph":"https://pith.science/api/pith-number/IT5XAPC3YL6NMVIVA2OWNEUFWP/graph.json","fetch_events":"https://pith.science/api/pith-number/IT5XAPC3YL6NMVIVA2OWNEUFWP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IT5XAPC3YL6NMVIVA2OWNEUFWP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IT5XAPC3YL6NMVIVA2OWNEUFWP/action/storage_attestation","attest_author":"https://pith.science/pith/IT5XAPC3YL6NMVIVA2OWNEUFWP/action/author_attestation","sign_citation":"https://pith.science/pith/IT5XAPC3YL6NMVIVA2OWNEUFWP/action/citation_signature","submit_replication":"https://pith.science/pith/IT5XAPC3YL6NMVIVA2OWNEUFWP/action/replication_record"}},"created_at":"2026-07-05T11:21:50.225101+00:00","updated_at":"2026-07-05T11:21:50.225101+00:00"}