{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:R6RWQ47IAQWIYIFDZXEEBI65WN","short_pith_number":"pith:R6RWQ47I","canonical_record":{"source":{"id":"2302.03811","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-08T00:30:58Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"title_canon_sha256":"97d66adcd149eb36f8d5a77cefacbf4d2dc1a3df508be56c69f639b37286ead2","abstract_canon_sha256":"af3d681d8dacfb8c4786f719738e2a98a8f8067ff78c46afd43f5459ca4d6845"},"schema_version":"1.0"},"canonical_sha256":"8fa36873e8042c8c20a3cdc840a3ddb365e067567a8ad731d52ac43f315eb56b","source":{"kind":"arxiv","id":"2302.03811","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.03811","created_at":"2026-07-05T07:45:26Z"},{"alias_kind":"arxiv_version","alias_value":"2302.03811v2","created_at":"2026-07-05T07:45:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.03811","created_at":"2026-07-05T07:45:26Z"},{"alias_kind":"pith_short_12","alias_value":"R6RWQ47IAQWI","created_at":"2026-07-05T07:45:26Z"},{"alias_kind":"pith_short_16","alias_value":"R6RWQ47IAQWIYIFD","created_at":"2026-07-05T07:45:26Z"},{"alias_kind":"pith_short_8","alias_value":"R6RWQ47I","created_at":"2026-07-05T07:45:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:R6RWQ47IAQWIYIFDZXEEBI65WN","target":"record","payload":{"canonical_record":{"source":{"id":"2302.03811","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-08T00:30:58Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"title_canon_sha256":"97d66adcd149eb36f8d5a77cefacbf4d2dc1a3df508be56c69f639b37286ead2","abstract_canon_sha256":"af3d681d8dacfb8c4786f719738e2a98a8f8067ff78c46afd43f5459ca4d6845"},"schema_version":"1.0"},"canonical_sha256":"8fa36873e8042c8c20a3cdc840a3ddb365e067567a8ad731d52ac43f315eb56b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:45:26.125514Z","signature_b64":"6mZNxRRc+tgdqL2eLbQgYxsJSkrv6NDE/C6NP5LzrR7LBgbJB5qLX12biwUVbU1mcMODtghPGD9asJ40nzZ4Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fa36873e8042c8c20a3cdc840a3ddb365e067567a8ad731d52ac43f315eb56b","last_reissued_at":"2026-07-05T07:45:26.125073Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:45:26.125073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.03811","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:45:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"it+In+9zW6yoQYQuoi5XOrNAyggSYbRSBicMTu0h/qI7RyaWukDcKp5urxPdSnaZl6e8CvSIxs3w9bnJtmNvBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T02:47:57.822615Z"},"content_sha256":"f6f5a46c913217fe56a5451ad4c7769489893ab65a2b8afca2ae061006fa50ef","schema_version":"1.0","event_id":"sha256:f6f5a46c913217fe56a5451ad4c7769489893ab65a2b8afca2ae061006fa50ef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:R6RWQ47IAQWIYIFDZXEEBI65WN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Convergence of Modified Policy Iteration in Risk Sensitive Exponential Cost Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Mehrdad Moharrami, R. Srikant, Yashaswini Murthy","submitted_at":"2023-02-08T00:30:58Z","abstract_excerpt":"Modified policy iteration (MPI) is a dynamic programming algorithm that combines elements of policy iteration and value iteration. The convergence of MPI has been well studied in the context of discounted and average-cost MDPs. In this work, we consider the exponential cost risk-sensitive MDP formulation, which is known to provide some robustness to model parameters. Although policy iteration and value iteration have been well studied in the context of risk sensitive MDPs, MPI is unexplored. We provide the first proof that MPI also converges for the risk-sensitive problem in the case of finite"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.03811","kind":"arxiv","version":2},"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/2302.03811/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:45:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yti+PZ517y4e2JJkCgfqcLdVYBkp7+RBOWH/c/2JO6mQBm7bqHFbyHwQZSVupwC9M9HTPTGi86Cp7Dq8iYtwCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T02:47:57.822988Z"},"content_sha256":"cb7768533187bd0462d4a1b0df9acd38c3e6f7df3176d5c940803d1221f21a33","schema_version":"1.0","event_id":"sha256:cb7768533187bd0462d4a1b0df9acd38c3e6f7df3176d5c940803d1221f21a33"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R6RWQ47IAQWIYIFDZXEEBI65WN/bundle.json","state_url":"https://pith.science/pith/R6RWQ47IAQWIYIFDZXEEBI65WN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R6RWQ47IAQWIYIFDZXEEBI65WN/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-09T02:47:57Z","links":{"resolver":"https://pith.science/pith/R6RWQ47IAQWIYIFDZXEEBI65WN","bundle":"https://pith.science/pith/R6RWQ47IAQWIYIFDZXEEBI65WN/bundle.json","state":"https://pith.science/pith/R6RWQ47IAQWIYIFDZXEEBI65WN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R6RWQ47IAQWIYIFDZXEEBI65WN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:R6RWQ47IAQWIYIFDZXEEBI65WN","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"af3d681d8dacfb8c4786f719738e2a98a8f8067ff78c46afd43f5459ca4d6845","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-08T00:30:58Z","title_canon_sha256":"97d66adcd149eb36f8d5a77cefacbf4d2dc1a3df508be56c69f639b37286ead2"},"schema_version":"1.0","source":{"id":"2302.03811","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.03811","created_at":"2026-07-05T07:45:26Z"},{"alias_kind":"arxiv_version","alias_value":"2302.03811v2","created_at":"2026-07-05T07:45:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.03811","created_at":"2026-07-05T07:45:26Z"},{"alias_kind":"pith_short_12","alias_value":"R6RWQ47IAQWI","created_at":"2026-07-05T07:45:26Z"},{"alias_kind":"pith_short_16","alias_value":"R6RWQ47IAQWIYIFD","created_at":"2026-07-05T07:45:26Z"},{"alias_kind":"pith_short_8","alias_value":"R6RWQ47I","created_at":"2026-07-05T07:45:26Z"}],"graph_snapshots":[{"event_id":"sha256:cb7768533187bd0462d4a1b0df9acd38c3e6f7df3176d5c940803d1221f21a33","target":"graph","created_at":"2026-07-05T07:45:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2302.03811/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modified policy iteration (MPI) is a dynamic programming algorithm that combines elements of policy iteration and value iteration. The convergence of MPI has been well studied in the context of discounted and average-cost MDPs. In this work, we consider the exponential cost risk-sensitive MDP formulation, which is known to provide some robustness to model parameters. Although policy iteration and value iteration have been well studied in the context of risk sensitive MDPs, MPI is unexplored. We provide the first proof that MPI also converges for the risk-sensitive problem in the case of finite","authors_text":"Mehrdad Moharrami, R. Srikant, Yashaswini Murthy","cross_cats":["cs.AI","cs.SY","eess.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-08T00:30:58Z","title":"On the Convergence of Modified Policy Iteration in Risk Sensitive Exponential Cost Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.03811","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f6f5a46c913217fe56a5451ad4c7769489893ab65a2b8afca2ae061006fa50ef","target":"record","created_at":"2026-07-05T07:45:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"af3d681d8dacfb8c4786f719738e2a98a8f8067ff78c46afd43f5459ca4d6845","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-08T00:30:58Z","title_canon_sha256":"97d66adcd149eb36f8d5a77cefacbf4d2dc1a3df508be56c69f639b37286ead2"},"schema_version":"1.0","source":{"id":"2302.03811","kind":"arxiv","version":2}},"canonical_sha256":"8fa36873e8042c8c20a3cdc840a3ddb365e067567a8ad731d52ac43f315eb56b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8fa36873e8042c8c20a3cdc840a3ddb365e067567a8ad731d52ac43f315eb56b","first_computed_at":"2026-07-05T07:45:26.125073Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:45:26.125073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6mZNxRRc+tgdqL2eLbQgYxsJSkrv6NDE/C6NP5LzrR7LBgbJB5qLX12biwUVbU1mcMODtghPGD9asJ40nzZ4Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:45:26.125514Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.03811","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6f5a46c913217fe56a5451ad4c7769489893ab65a2b8afca2ae061006fa50ef","sha256:cb7768533187bd0462d4a1b0df9acd38c3e6f7df3176d5c940803d1221f21a33"],"state_sha256":"60246b7532bfff80caf30d2112104264b8f3a7eb7bc28935d9eb973a84504e2e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"axMbP2X4eHlJ1bHceM/BLr3Y+lApswN0seT3IYxBiqYOzCEKjwqN4pGC4pVrhjS+Orqv/wrGXzWzgqIUSwxgBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T02:47:57.825051Z","bundle_sha256":"3821eef4a7f78db3a60c28217e7b5f35ec35542219b18833e3a0924f556b1006"}}