{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:IJH7XGRC5NBRILNTJXGIB5G3XH","short_pith_number":"pith:IJH7XGRC","schema_version":"1.0","canonical_sha256":"424ffb9a22eb43142db34dcc80f4dbb9e58761d1b78d1c018eb3246bb07b9b45","source":{"kind":"arxiv","id":"1705.02326","version":3},"attestation_state":"computed","paper":{"title":"Value Iteration for Long-run Average Reward in Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SY","authors_text":"Jan K\\v{r}et\\'insk\\'y, Krishnendu Chatterjee, Pranav Ashok, Przemyslaw Daca, Tobias Meggendorfer","submitted_at":"2017-05-05T17:48:13Z","abstract_excerpt":"Markov decision processes (MDPs) are standard models for probabilistic systems with non-deterministic behaviours. Long-run average rewards provide a mathematically elegant formalism for expressing long term performance. Value iteration (VI) is one of the simplest and most efficient algorithmic approaches to MDPs with other properties, such as reachability objectives. Unfortunately, a naive extension of VI does not work for MDPs with long-run average rewards, as there is no known stopping criterion. In this work our contributions are threefold. (1) We refute a conjecture related to stopping cri"},"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":"1705.02326","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2017-05-05T17:48:13Z","cross_cats_sorted":[],"title_canon_sha256":"412e0fa63c274580c4762e0c9d4a8f9f97a16b8518fce178703e0742aa8de041","abstract_canon_sha256":"836d4a0924e4c7ff3219eb0285113833ac587c8a3117c8dc8ad879b3aa5504f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:36:19.232686Z","signature_b64":"44vSJCctDfw9B4uajYwY9axuvPcTJrZ1M9fHYprG4NqWxZqQf0ViUVY34OhX1JfHrERvKeEBqzK/Uvj7dKaLCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"424ffb9a22eb43142db34dcc80f4dbb9e58761d1b78d1c018eb3246bb07b9b45","last_reissued_at":"2026-05-18T00:36:19.232048Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:36:19.232048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Value Iteration for Long-run Average Reward in Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SY","authors_text":"Jan K\\v{r}et\\'insk\\'y, Krishnendu Chatterjee, Pranav Ashok, Przemyslaw Daca, Tobias Meggendorfer","submitted_at":"2017-05-05T17:48:13Z","abstract_excerpt":"Markov decision processes (MDPs) are standard models for probabilistic systems with non-deterministic behaviours. Long-run average rewards provide a mathematically elegant formalism for expressing long term performance. Value iteration (VI) is one of the simplest and most efficient algorithmic approaches to MDPs with other properties, such as reachability objectives. Unfortunately, a naive extension of VI does not work for MDPs with long-run average rewards, as there is no known stopping criterion. In this work our contributions are threefold. (1) We refute a conjecture related to stopping cri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.02326","kind":"arxiv","version":3},"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":"1705.02326","created_at":"2026-05-18T00:36:19.232141+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.02326v3","created_at":"2026-05-18T00:36:19.232141+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.02326","created_at":"2026-05-18T00:36:19.232141+00:00"},{"alias_kind":"pith_short_12","alias_value":"IJH7XGRC5NBR","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_16","alias_value":"IJH7XGRC5NBRILNT","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_8","alias_value":"IJH7XGRC","created_at":"2026-05-18T12:31:21.493067+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/IJH7XGRC5NBRILNTJXGIB5G3XH","json":"https://pith.science/pith/IJH7XGRC5NBRILNTJXGIB5G3XH.json","graph_json":"https://pith.science/api/pith-number/IJH7XGRC5NBRILNTJXGIB5G3XH/graph.json","events_json":"https://pith.science/api/pith-number/IJH7XGRC5NBRILNTJXGIB5G3XH/events.json","paper":"https://pith.science/paper/IJH7XGRC"},"agent_actions":{"view_html":"https://pith.science/pith/IJH7XGRC5NBRILNTJXGIB5G3XH","download_json":"https://pith.science/pith/IJH7XGRC5NBRILNTJXGIB5G3XH.json","view_paper":"https://pith.science/paper/IJH7XGRC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.02326&json=true","fetch_graph":"https://pith.science/api/pith-number/IJH7XGRC5NBRILNTJXGIB5G3XH/graph.json","fetch_events":"https://pith.science/api/pith-number/IJH7XGRC5NBRILNTJXGIB5G3XH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IJH7XGRC5NBRILNTJXGIB5G3XH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IJH7XGRC5NBRILNTJXGIB5G3XH/action/storage_attestation","attest_author":"https://pith.science/pith/IJH7XGRC5NBRILNTJXGIB5G3XH/action/author_attestation","sign_citation":"https://pith.science/pith/IJH7XGRC5NBRILNTJXGIB5G3XH/action/citation_signature","submit_replication":"https://pith.science/pith/IJH7XGRC5NBRILNTJXGIB5G3XH/action/replication_record"}},"created_at":"2026-05-18T00:36:19.232141+00:00","updated_at":"2026-05-18T00:36:19.232141+00:00"}