{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:A6EQL2V3MGWB3KWMKVZA4NXQMN","short_pith_number":"pith:A6EQL2V3","schema_version":"1.0","canonical_sha256":"078905eabb61ac1daacc55720e36f0634352d1dee5023f164e4afd3f45a04f54","source":{"kind":"arxiv","id":"2508.18252","version":1},"attestation_state":"computed","paper":{"title":"Efficient Computation of Blackwell Optimal Policies using Rational Functions","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dibyangshu Mukherjee, Shivaram Kalyanakrishnan","submitted_at":"2025-08-25T17:41:30Z","abstract_excerpt":"Markov Decision Problems (MDPs) provide a foundational framework for modelling sequential decision-making across diverse domains, guided by optimality criteria such as discounted and average rewards. However, these criteria have inherent limitations: discounted optimality may overly prioritise short-term rewards, while average optimality relies on strong structural assumptions. Blackwell optimality addresses these challenges, offering a robust and comprehensive criterion that ensures optimality under both discounted and average reward frameworks. Despite its theoretical appeal, existing algori"},"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":"2508.18252","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-25T17:41:30Z","cross_cats_sorted":[],"title_canon_sha256":"2a8305df022b051d0259c4e22ae795272d4a08e052f8e050a6fd86be01bdcef7","abstract_canon_sha256":"49e34e83c0f6c0559a10ba58e7acb0cca42ab999a3139853822c794f0726f9ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:56.324628Z","signature_b64":"GPOmexqB0YE/e1gc2MNJ6PaglV1AM94+KTbrZbaYbwzVrz4QNYMuE+EN488UvuHqnZtQshtFsc46GP/lPByoCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"078905eabb61ac1daacc55720e36f0634352d1dee5023f164e4afd3f45a04f54","last_reissued_at":"2026-07-05T11:58:56.323876Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:56.323876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Computation of Blackwell Optimal Policies using Rational Functions","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dibyangshu Mukherjee, Shivaram Kalyanakrishnan","submitted_at":"2025-08-25T17:41:30Z","abstract_excerpt":"Markov Decision Problems (MDPs) provide a foundational framework for modelling sequential decision-making across diverse domains, guided by optimality criteria such as discounted and average rewards. However, these criteria have inherent limitations: discounted optimality may overly prioritise short-term rewards, while average optimality relies on strong structural assumptions. Blackwell optimality addresses these challenges, offering a robust and comprehensive criterion that ensures optimality under both discounted and average reward frameworks. Despite its theoretical appeal, existing algori"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.18252","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/2508.18252/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":"2508.18252","created_at":"2026-07-05T11:58:56.323963+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.18252v1","created_at":"2026-07-05T11:58:56.323963+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.18252","created_at":"2026-07-05T11:58:56.323963+00:00"},{"alias_kind":"pith_short_12","alias_value":"A6EQL2V3MGWB","created_at":"2026-07-05T11:58:56.323963+00:00"},{"alias_kind":"pith_short_16","alias_value":"A6EQL2V3MGWB3KWM","created_at":"2026-07-05T11:58:56.323963+00:00"},{"alias_kind":"pith_short_8","alias_value":"A6EQL2V3","created_at":"2026-07-05T11:58:56.323963+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/A6EQL2V3MGWB3KWMKVZA4NXQMN","json":"https://pith.science/pith/A6EQL2V3MGWB3KWMKVZA4NXQMN.json","graph_json":"https://pith.science/api/pith-number/A6EQL2V3MGWB3KWMKVZA4NXQMN/graph.json","events_json":"https://pith.science/api/pith-number/A6EQL2V3MGWB3KWMKVZA4NXQMN/events.json","paper":"https://pith.science/paper/A6EQL2V3"},"agent_actions":{"view_html":"https://pith.science/pith/A6EQL2V3MGWB3KWMKVZA4NXQMN","download_json":"https://pith.science/pith/A6EQL2V3MGWB3KWMKVZA4NXQMN.json","view_paper":"https://pith.science/paper/A6EQL2V3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.18252&json=true","fetch_graph":"https://pith.science/api/pith-number/A6EQL2V3MGWB3KWMKVZA4NXQMN/graph.json","fetch_events":"https://pith.science/api/pith-number/A6EQL2V3MGWB3KWMKVZA4NXQMN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A6EQL2V3MGWB3KWMKVZA4NXQMN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A6EQL2V3MGWB3KWMKVZA4NXQMN/action/storage_attestation","attest_author":"https://pith.science/pith/A6EQL2V3MGWB3KWMKVZA4NXQMN/action/author_attestation","sign_citation":"https://pith.science/pith/A6EQL2V3MGWB3KWMKVZA4NXQMN/action/citation_signature","submit_replication":"https://pith.science/pith/A6EQL2V3MGWB3KWMKVZA4NXQMN/action/replication_record"}},"created_at":"2026-07-05T11:58:56.323963+00:00","updated_at":"2026-07-05T11:58:56.323963+00:00"}