{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:LIVHWWCKG53RBDAUAMY6FCJAMD","short_pith_number":"pith:LIVHWWCK","canonical_record":{"source":{"id":"2012.04626","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-12-08T18:48:14Z","cross_cats_sorted":[],"title_canon_sha256":"acb4bdee4dcead88f859d9bed06939fa7f6c6c1024cd68d7d513a8b4b1a331dc","abstract_canon_sha256":"3fc7e0c25867e64181c9465eb817ce0995834d88c4c3246a473ca51bfbdadc45"},"schema_version":"1.0"},"canonical_sha256":"5a2a7b584a3777108c140331e2892060ded32e14d7ef4acaae2e60be8e88b114","source":{"kind":"arxiv","id":"2012.04626","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.04626","created_at":"2026-07-05T05:40:41Z"},{"alias_kind":"arxiv_version","alias_value":"2012.04626v2","created_at":"2026-07-05T05:40:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.04626","created_at":"2026-07-05T05:40:41Z"},{"alias_kind":"pith_short_12","alias_value":"LIVHWWCKG53R","created_at":"2026-07-05T05:40:41Z"},{"alias_kind":"pith_short_16","alias_value":"LIVHWWCKG53RBDAU","created_at":"2026-07-05T05:40:41Z"},{"alias_kind":"pith_short_8","alias_value":"LIVHWWCK","created_at":"2026-07-05T05:40:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:LIVHWWCKG53RBDAUAMY6FCJAMD","target":"record","payload":{"canonical_record":{"source":{"id":"2012.04626","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-12-08T18:48:14Z","cross_cats_sorted":[],"title_canon_sha256":"acb4bdee4dcead88f859d9bed06939fa7f6c6c1024cd68d7d513a8b4b1a331dc","abstract_canon_sha256":"3fc7e0c25867e64181c9465eb817ce0995834d88c4c3246a473ca51bfbdadc45"},"schema_version":"1.0"},"canonical_sha256":"5a2a7b584a3777108c140331e2892060ded32e14d7ef4acaae2e60be8e88b114","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:41.870177Z","signature_b64":"DiJYh1dV0Mi1R+94t5dEkUjDgTzTzPHInNOIAgbfLqV+/8tr6x2kP/AAgewJuHlXZ3mf8zczKHqd0L6dHeZqDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a2a7b584a3777108c140331e2892060ded32e14d7ef4acaae2e60be8e88b114","last_reissued_at":"2026-07-05T05:40:41.869772Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:41.869772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.04626","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":"2026-07-05T05:40:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OxKRuDofq4BXEyNWD94Uw/yAiC7F8JFmibitx9hhynYpGVFna9m2khlfTBQ4rQi6IXff/1lTe0sTVCn2WDzEDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T06:53:36.296218Z"},"content_sha256":"9e966688754cb5e1a270125497cdd2585ce559ddeca60a19818c19f241901298","schema_version":"1.0","event_id":"sha256:9e966688754cb5e1a270125497cdd2585ce559ddeca60a19818c19f241901298"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:LIVHWWCKG53RBDAUAMY6FCJAMD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Minimax Regret Optimisation for Robust Planning in Uncertain Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bruno Lacerda, Marc Rigter, Nick Hawes","submitted_at":"2020-12-08T18:48:14Z","abstract_excerpt":"The parameters for a Markov Decision Process (MDP) often cannot be specified exactly. Uncertain MDPs (UMDPs) capture this model ambiguity by defining sets which the parameters belong to. Minimax regret has been proposed as an objective for planning in UMDPs to find robust policies which are not overly conservative. In this work, we focus on planning for Stochastic Shortest Path (SSP) UMDPs with uncertain cost and transition functions. We introduce a Bellman equation to compute the regret for a policy. We propose a dynamic programming algorithm that utilises the regret Bellman equation, and sho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.04626","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/2012.04626/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":"2026-07-05T05:40:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mOTAzOTPRhrCYS0FYKVMmJXf/zSZcRlwS52i/w+QMV+vDpzOlUqCaeWyFtZioUIfgcUgTrQqRq6cwHrgKhgMCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T06:53:36.296719Z"},"content_sha256":"9518a85cf677ce61c79dfb80cce42ffbee3e0c4293a75e015d6922c02772a606","schema_version":"1.0","event_id":"sha256:9518a85cf677ce61c79dfb80cce42ffbee3e0c4293a75e015d6922c02772a606"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LIVHWWCKG53RBDAUAMY6FCJAMD/bundle.json","state_url":"https://pith.science/pith/LIVHWWCKG53RBDAUAMY6FCJAMD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LIVHWWCKG53RBDAUAMY6FCJAMD/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":"2026-08-19T06:53:36Z","links":{"resolver":"https://pith.science/pith/LIVHWWCKG53RBDAUAMY6FCJAMD","bundle":"https://pith.science/pith/LIVHWWCKG53RBDAUAMY6FCJAMD/bundle.json","state":"https://pith.science/pith/LIVHWWCKG53RBDAUAMY6FCJAMD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LIVHWWCKG53RBDAUAMY6FCJAMD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:LIVHWWCKG53RBDAUAMY6FCJAMD","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":"3fc7e0c25867e64181c9465eb817ce0995834d88c4c3246a473ca51bfbdadc45","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-12-08T18:48:14Z","title_canon_sha256":"acb4bdee4dcead88f859d9bed06939fa7f6c6c1024cd68d7d513a8b4b1a331dc"},"schema_version":"1.0","source":{"id":"2012.04626","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.04626","created_at":"2026-07-05T05:40:41Z"},{"alias_kind":"arxiv_version","alias_value":"2012.04626v2","created_at":"2026-07-05T05:40:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.04626","created_at":"2026-07-05T05:40:41Z"},{"alias_kind":"pith_short_12","alias_value":"LIVHWWCKG53R","created_at":"2026-07-05T05:40:41Z"},{"alias_kind":"pith_short_16","alias_value":"LIVHWWCKG53RBDAU","created_at":"2026-07-05T05:40:41Z"},{"alias_kind":"pith_short_8","alias_value":"LIVHWWCK","created_at":"2026-07-05T05:40:41Z"}],"graph_snapshots":[{"event_id":"sha256:9518a85cf677ce61c79dfb80cce42ffbee3e0c4293a75e015d6922c02772a606","target":"graph","created_at":"2026-07-05T05:40:41Z","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/2012.04626/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The parameters for a Markov Decision Process (MDP) often cannot be specified exactly. Uncertain MDPs (UMDPs) capture this model ambiguity by defining sets which the parameters belong to. Minimax regret has been proposed as an objective for planning in UMDPs to find robust policies which are not overly conservative. In this work, we focus on planning for Stochastic Shortest Path (SSP) UMDPs with uncertain cost and transition functions. We introduce a Bellman equation to compute the regret for a policy. We propose a dynamic programming algorithm that utilises the regret Bellman equation, and sho","authors_text":"Bruno Lacerda, Marc Rigter, Nick Hawes","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-12-08T18:48:14Z","title":"Minimax Regret Optimisation for Robust Planning in Uncertain Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.04626","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":"sha256:9e966688754cb5e1a270125497cdd2585ce559ddeca60a19818c19f241901298","target":"record","created_at":"2026-07-05T05:40:41Z","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":"3fc7e0c25867e64181c9465eb817ce0995834d88c4c3246a473ca51bfbdadc45","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-12-08T18:48:14Z","title_canon_sha256":"acb4bdee4dcead88f859d9bed06939fa7f6c6c1024cd68d7d513a8b4b1a331dc"},"schema_version":"1.0","source":{"id":"2012.04626","kind":"arxiv","version":2}},"canonical_sha256":"5a2a7b584a3777108c140331e2892060ded32e14d7ef4acaae2e60be8e88b114","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a2a7b584a3777108c140331e2892060ded32e14d7ef4acaae2e60be8e88b114","first_computed_at":"2026-07-05T05:40:41.869772Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:40:41.869772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DiJYh1dV0Mi1R+94t5dEkUjDgTzTzPHInNOIAgbfLqV+/8tr6x2kP/AAgewJuHlXZ3mf8zczKHqd0L6dHeZqDg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:40:41.870177Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.04626","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e966688754cb5e1a270125497cdd2585ce559ddeca60a19818c19f241901298","sha256:9518a85cf677ce61c79dfb80cce42ffbee3e0c4293a75e015d6922c02772a606"],"state_sha256":"5d24aaac3860924ee8319f18907f3d621ffd83dc0af808b7c0ed3fa92a07ecdb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S25Jhpjno81V/00Hm+MN93VeKxuxGI5IYEesX9zr9b+hMbfoyLAxHo1Ovy7GGkhLn/nzZGDKibbTzfuHXUBJCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T06:53:36.300986Z","bundle_sha256":"7d7d7d9b8c56430c508286435a301f7e648c96c151278a1443629033526dab98"}}