{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QF6U5AR7C25IWGTMDBXVEI3XZV","short_pith_number":"pith:QF6U5AR7","canonical_record":{"source":{"id":"2303.06654","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-12T13:03:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a0759d4399d759a84903b58a94ce52e803a7608e0c3125f72ec59c0377bd68e9","abstract_canon_sha256":"842ca3ffadb2b7892ce43f40d15cdb2e1dbf5186e860d60880a7ad96f14a20d5"},"schema_version":"1.0"},"canonical_sha256":"817d4e823f16ba8b1a6c186f522377cd5221014cdad16c3c1949d97293069506","source":{"kind":"arxiv","id":"2303.06654","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.06654","created_at":"2026-07-05T05:50:21Z"},{"alias_kind":"arxiv_version","alias_value":"2303.06654v1","created_at":"2026-07-05T05:50:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.06654","created_at":"2026-07-05T05:50:21Z"},{"alias_kind":"pith_short_12","alias_value":"QF6U5AR7C25I","created_at":"2026-07-05T05:50:21Z"},{"alias_kind":"pith_short_16","alias_value":"QF6U5AR7C25IWGTM","created_at":"2026-07-05T05:50:21Z"},{"alias_kind":"pith_short_8","alias_value":"QF6U5AR7","created_at":"2026-07-05T05:50:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QF6U5AR7C25IWGTMDBXVEI3XZV","target":"record","payload":{"canonical_record":{"source":{"id":"2303.06654","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-12T13:03:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a0759d4399d759a84903b58a94ce52e803a7608e0c3125f72ec59c0377bd68e9","abstract_canon_sha256":"842ca3ffadb2b7892ce43f40d15cdb2e1dbf5186e860d60880a7ad96f14a20d5"},"schema_version":"1.0"},"canonical_sha256":"817d4e823f16ba8b1a6c186f522377cd5221014cdad16c3c1949d97293069506","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:50:21.538540Z","signature_b64":"1C28rIagK5kPgFcSHz/tftqNvQvdp2T3hvLFk9NLDoEgjPe/JhnT+nBzwIbdXIn7c0ZpiiqsvCuB974Dt3p8Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"817d4e823f16ba8b1a6c186f522377cd5221014cdad16c3c1949d97293069506","last_reissued_at":"2026-07-05T05:50:21.538186Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:50:21.538186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.06654","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":"2026-07-05T05:50:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fslbxpW6qRfnHyCh5A5y3KM64qkQOuZnVyAv9Xnu1BnjILXHQ4/EDewlOukfR2PqZJYyjvYGuOoSAWtBwtvIAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T01:42:04.833072Z"},"content_sha256":"75ebedab85049bc87d38c0c03019f74d910a302d842c8d1adadbe0cec0b8b10f","schema_version":"1.0","event_id":"sha256:75ebedab85049bc87d38c0c03019f74d910a302d842c8d1adadbe0cec0b8b10f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QF6U5AR7C25IWGTMDBXVEI3XZV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Twice Regularized Markov Decision Processes: The Equivalence between Robustness and Regularization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Esther Derman, Matthieu Geist, Shie Mannor, Yevgeniy Men","submitted_at":"2023-03-12T13:03:28Z","abstract_excerpt":"Robust Markov decision processes (MDPs) aim to handle changing or partially known system dynamics. To solve them, one typically resorts to robust optimization methods. However, this significantly increases computational complexity and limits scalability in both learning and planning. On the other hand, regularized MDPs show more stability in policy learning without impairing time complexity. Yet, they generally do not encompass uncertainty in the model dynamics. In this work, we aim to learn robust MDPs using regularization. We first show that regularized MDPs are a particular instance of robu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.06654","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/2303.06654/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":"2026-07-05T05:50:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tRB/k6BeJbRqxMJARKZvaOvTQb06xsqDMKQZlU1tnm8DHNMrWd4aEmgXagRZiCjVADjVGn102R5ISUVldj+pDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T01:42:04.833581Z"},"content_sha256":"9d86f0509cb04524c866a9cdb7a4f61bddbcddfb82e092cfc0809512ba714478","schema_version":"1.0","event_id":"sha256:9d86f0509cb04524c866a9cdb7a4f61bddbcddfb82e092cfc0809512ba714478"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QF6U5AR7C25IWGTMDBXVEI3XZV/bundle.json","state_url":"https://pith.science/pith/QF6U5AR7C25IWGTMDBXVEI3XZV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QF6U5AR7C25IWGTMDBXVEI3XZV/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":"2026-08-09T01:42:04Z","links":{"resolver":"https://pith.science/pith/QF6U5AR7C25IWGTMDBXVEI3XZV","bundle":"https://pith.science/pith/QF6U5AR7C25IWGTMDBXVEI3XZV/bundle.json","state":"https://pith.science/pith/QF6U5AR7C25IWGTMDBXVEI3XZV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QF6U5AR7C25IWGTMDBXVEI3XZV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QF6U5AR7C25IWGTMDBXVEI3XZV","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":"842ca3ffadb2b7892ce43f40d15cdb2e1dbf5186e860d60880a7ad96f14a20d5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-12T13:03:28Z","title_canon_sha256":"a0759d4399d759a84903b58a94ce52e803a7608e0c3125f72ec59c0377bd68e9"},"schema_version":"1.0","source":{"id":"2303.06654","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.06654","created_at":"2026-07-05T05:50:21Z"},{"alias_kind":"arxiv_version","alias_value":"2303.06654v1","created_at":"2026-07-05T05:50:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.06654","created_at":"2026-07-05T05:50:21Z"},{"alias_kind":"pith_short_12","alias_value":"QF6U5AR7C25I","created_at":"2026-07-05T05:50:21Z"},{"alias_kind":"pith_short_16","alias_value":"QF6U5AR7C25IWGTM","created_at":"2026-07-05T05:50:21Z"},{"alias_kind":"pith_short_8","alias_value":"QF6U5AR7","created_at":"2026-07-05T05:50:21Z"}],"graph_snapshots":[{"event_id":"sha256:9d86f0509cb04524c866a9cdb7a4f61bddbcddfb82e092cfc0809512ba714478","target":"graph","created_at":"2026-07-05T05:50:21Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2303.06654/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Robust Markov decision processes (MDPs) aim to handle changing or partially known system dynamics. To solve them, one typically resorts to robust optimization methods. However, this significantly increases computational complexity and limits scalability in both learning and planning. On the other hand, regularized MDPs show more stability in policy learning without impairing time complexity. Yet, they generally do not encompass uncertainty in the model dynamics. In this work, we aim to learn robust MDPs using regularization. We first show that regularized MDPs are a particular instance of robu","authors_text":"Esther Derman, Matthieu Geist, Shie Mannor, Yevgeniy Men","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-12T13:03:28Z","title":"Twice Regularized Markov Decision Processes: The Equivalence between Robustness and Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.06654","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":"sha256:75ebedab85049bc87d38c0c03019f74d910a302d842c8d1adadbe0cec0b8b10f","target":"record","created_at":"2026-07-05T05:50:21Z","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":"842ca3ffadb2b7892ce43f40d15cdb2e1dbf5186e860d60880a7ad96f14a20d5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-12T13:03:28Z","title_canon_sha256":"a0759d4399d759a84903b58a94ce52e803a7608e0c3125f72ec59c0377bd68e9"},"schema_version":"1.0","source":{"id":"2303.06654","kind":"arxiv","version":1}},"canonical_sha256":"817d4e823f16ba8b1a6c186f522377cd5221014cdad16c3c1949d97293069506","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"817d4e823f16ba8b1a6c186f522377cd5221014cdad16c3c1949d97293069506","first_computed_at":"2026-07-05T05:50:21.538186Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:50:21.538186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1C28rIagK5kPgFcSHz/tftqNvQvdp2T3hvLFk9NLDoEgjPe/JhnT+nBzwIbdXIn7c0ZpiiqsvCuB974Dt3p8Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:50:21.538540Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.06654","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75ebedab85049bc87d38c0c03019f74d910a302d842c8d1adadbe0cec0b8b10f","sha256:9d86f0509cb04524c866a9cdb7a4f61bddbcddfb82e092cfc0809512ba714478"],"state_sha256":"e443f6a8a3c5332da667b9fddce7a0baabeb91d2fd851293d703621fbaf96374"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3rW3US/gmOrEIhR2svoDPmJwmm+RCYXsWZC9N+cYNS+9bQhzWWzBrtrrjQN1DZaUzKFznTfA3YgwH90f3S3VBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T01:42:04.839600Z","bundle_sha256":"6e6ae292f412acf8596fccf531048ec249064d3ca3a540e270f99df069e79130"}}