{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:AESDKJEGSWEKHTLMUSINRQ3J6Z","short_pith_number":"pith:AESDKJEG","canonical_record":{"source":{"id":"1704.00621","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2017-04-03T14:40:58Z","cross_cats_sorted":[],"title_canon_sha256":"00aca284355ebd8485289862cc9776d8dbe056e9a1ca00c3db75cbd4b1352319","abstract_canon_sha256":"d8130d276a0ab22b59f324b02f98229bf21ab3e0b5e4f59434208567129a51db"},"schema_version":"1.0"},"canonical_sha256":"01243524869588a3cd6ca490d8c369f67873b2dccd896aef5e2369b513b4947d","source":{"kind":"arxiv","id":"1704.00621","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.00621","created_at":"2026-05-18T00:47:21Z"},{"alias_kind":"arxiv_version","alias_value":"1704.00621v1","created_at":"2026-05-18T00:47:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.00621","created_at":"2026-05-18T00:47:21Z"},{"alias_kind":"pith_short_12","alias_value":"AESDKJEGSWEK","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"AESDKJEGSWEKHTLM","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"AESDKJEG","created_at":"2026-05-18T12:31:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:AESDKJEGSWEKHTLMUSINRQ3J6Z","target":"record","payload":{"canonical_record":{"source":{"id":"1704.00621","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2017-04-03T14:40:58Z","cross_cats_sorted":[],"title_canon_sha256":"00aca284355ebd8485289862cc9776d8dbe056e9a1ca00c3db75cbd4b1352319","abstract_canon_sha256":"d8130d276a0ab22b59f324b02f98229bf21ab3e0b5e4f59434208567129a51db"},"schema_version":"1.0"},"canonical_sha256":"01243524869588a3cd6ca490d8c369f67873b2dccd896aef5e2369b513b4947d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:47:21.826466Z","signature_b64":"p/vrHAKfplLZnx04Ys1T6jsnvpezbomLiZJipRyVLyavdOKqS3yswyravo75lQO0aUOb0eacqYhV7SDPtbT8AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01243524869588a3cd6ca490d8c369f67873b2dccd896aef5e2369b513b4947d","last_reissued_at":"2026-05-18T00:47:21.825991Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:47:21.825991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1704.00621","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:47:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+4ghB4HNoeO0B8wuIkpYMrtrum70Ud61gTE95MuUUY1AsjdX0NlBy/Hhs2q9/sJgqIZbtF8xqJFREehRYaC0Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T11:30:53.521649Z"},"content_sha256":"8a5a32e502b3cf31f12de1b6c38756e97a00a864b6a9ab86346d74338b1f320f","schema_version":"1.0","event_id":"sha256:8a5a32e502b3cf31f12de1b6c38756e97a00a864b6a9ab86346d74338b1f320f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:AESDKJEGSWEKHTLMUSINRQ3J6Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Computing monotone policies for Markov decision processes: a nearly-isotonic penalty approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SY","authors_text":"Bo Wahlberg, Cristian R. Rojas, Robert Mattila, Vikram Krishnamurthy","submitted_at":"2017-04-03T14:40:58Z","abstract_excerpt":"This paper discusses algorithms for solving Markov decision processes (MDPs) that have monotone optimal policies. We propose a two-stage alternating convex optimization scheme that can accelerate the search for an optimal policy by exploiting the monotone property. The first stage is a linear program formulated in terms of the joint state-action probabilities. The second stage is a regularized problem formulated in terms of the conditional probabilities of actions given states. The regularization uses techniques from nearly-isotonic regression. While a variety of iterative method can be used i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.00621","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:47:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"swyTi+nl2Wq2+82UxvtgTGe5ir2pGd/8G+x+A/LQglyImUJsWNmEUvj6hVgHJem6TxWQlHGYEujBTI5JOsrTDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T11:30:53.521993Z"},"content_sha256":"e53dac9dd2c4308aa221036570f496b9d6e392c86c87d0c343a419566ca74da3","schema_version":"1.0","event_id":"sha256:e53dac9dd2c4308aa221036570f496b9d6e392c86c87d0c343a419566ca74da3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AESDKJEGSWEKHTLMUSINRQ3J6Z/bundle.json","state_url":"https://pith.science/pith/AESDKJEGSWEKHTLMUSINRQ3J6Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AESDKJEGSWEKHTLMUSINRQ3J6Z/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":"2026-05-28T11:30:53Z","links":{"resolver":"https://pith.science/pith/AESDKJEGSWEKHTLMUSINRQ3J6Z","bundle":"https://pith.science/pith/AESDKJEGSWEKHTLMUSINRQ3J6Z/bundle.json","state":"https://pith.science/pith/AESDKJEGSWEKHTLMUSINRQ3J6Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AESDKJEGSWEKHTLMUSINRQ3J6Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:AESDKJEGSWEKHTLMUSINRQ3J6Z","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":"d8130d276a0ab22b59f324b02f98229bf21ab3e0b5e4f59434208567129a51db","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2017-04-03T14:40:58Z","title_canon_sha256":"00aca284355ebd8485289862cc9776d8dbe056e9a1ca00c3db75cbd4b1352319"},"schema_version":"1.0","source":{"id":"1704.00621","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.00621","created_at":"2026-05-18T00:47:21Z"},{"alias_kind":"arxiv_version","alias_value":"1704.00621v1","created_at":"2026-05-18T00:47:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.00621","created_at":"2026-05-18T00:47:21Z"},{"alias_kind":"pith_short_12","alias_value":"AESDKJEGSWEK","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"AESDKJEGSWEKHTLM","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"AESDKJEG","created_at":"2026-05-18T12:31:05Z"}],"graph_snapshots":[{"event_id":"sha256:e53dac9dd2c4308aa221036570f496b9d6e392c86c87d0c343a419566ca74da3","target":"graph","created_at":"2026-05-18T00:47:21Z","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"},"paper":{"abstract_excerpt":"This paper discusses algorithms for solving Markov decision processes (MDPs) that have monotone optimal policies. We propose a two-stage alternating convex optimization scheme that can accelerate the search for an optimal policy by exploiting the monotone property. The first stage is a linear program formulated in terms of the joint state-action probabilities. The second stage is a regularized problem formulated in terms of the conditional probabilities of actions given states. The regularization uses techniques from nearly-isotonic regression. While a variety of iterative method can be used i","authors_text":"Bo Wahlberg, Cristian R. Rojas, Robert Mattila, Vikram Krishnamurthy","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2017-04-03T14:40:58Z","title":"Computing monotone policies for Markov decision processes: a nearly-isotonic penalty approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.00621","kind":"arxiv","version":1},"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":"sha256:8a5a32e502b3cf31f12de1b6c38756e97a00a864b6a9ab86346d74338b1f320f","target":"record","created_at":"2026-05-18T00:47:21Z","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":"d8130d276a0ab22b59f324b02f98229bf21ab3e0b5e4f59434208567129a51db","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2017-04-03T14:40:58Z","title_canon_sha256":"00aca284355ebd8485289862cc9776d8dbe056e9a1ca00c3db75cbd4b1352319"},"schema_version":"1.0","source":{"id":"1704.00621","kind":"arxiv","version":1}},"canonical_sha256":"01243524869588a3cd6ca490d8c369f67873b2dccd896aef5e2369b513b4947d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"01243524869588a3cd6ca490d8c369f67873b2dccd896aef5e2369b513b4947d","first_computed_at":"2026-05-18T00:47:21.825991Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:47:21.825991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p/vrHAKfplLZnx04Ys1T6jsnvpezbomLiZJipRyVLyavdOKqS3yswyravo75lQO0aUOb0eacqYhV7SDPtbT8AA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:47:21.826466Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.00621","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a5a32e502b3cf31f12de1b6c38756e97a00a864b6a9ab86346d74338b1f320f","sha256:e53dac9dd2c4308aa221036570f496b9d6e392c86c87d0c343a419566ca74da3"],"state_sha256":"afb51629222f4a6d527432c805f0784fc7f488ad2d3b728e43f05f4a77e29f6c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s7vpbHarqKIn7/ugGdeb2iu+UhSwltNmi6wYDxBVFCoNVI2pJYhaEhSnNTb03mFfQhpvCFZ9UMQX5+ErbVM/CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T11:30:53.523910Z","bundle_sha256":"b8c5ad1dce025e0a0c7000653b1efe0abea9dd961a3aaf15ccc250dec60110fa"}}