{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:EHJYBSQNRHOVD4Y5PLQ7O6TD3B","short_pith_number":"pith:EHJYBSQN","canonical_record":{"source":{"id":"2302.01248","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-02-02T17:29:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"492d9f3fe2148e1ca3fcb2f33f34bc32f9b7f0b333c6786ce4d63ff4a815579e","abstract_canon_sha256":"96e461458ffb5c3fd4e0ee2e938c492f12f85ed78790a702bb8ecb3918aa902e"},"schema_version":"1.0"},"canonical_sha256":"21d380ca0d89dd51f31d7ae1f77a63d872bd1bb190213e8400e70849efc0fb75","source":{"kind":"arxiv","id":"2302.01248","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.01248","created_at":"2026-07-05T06:49:58Z"},{"alias_kind":"arxiv_version","alias_value":"2302.01248v2","created_at":"2026-07-05T06:49:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.01248","created_at":"2026-07-05T06:49:58Z"},{"alias_kind":"pith_short_12","alias_value":"EHJYBSQNRHOV","created_at":"2026-07-05T06:49:58Z"},{"alias_kind":"pith_short_16","alias_value":"EHJYBSQNRHOVD4Y5","created_at":"2026-07-05T06:49:58Z"},{"alias_kind":"pith_short_8","alias_value":"EHJYBSQN","created_at":"2026-07-05T06:49:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:EHJYBSQNRHOVD4Y5PLQ7O6TD3B","target":"record","payload":{"canonical_record":{"source":{"id":"2302.01248","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-02-02T17:29:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"492d9f3fe2148e1ca3fcb2f33f34bc32f9b7f0b333c6786ce4d63ff4a815579e","abstract_canon_sha256":"96e461458ffb5c3fd4e0ee2e938c492f12f85ed78790a702bb8ecb3918aa902e"},"schema_version":"1.0"},"canonical_sha256":"21d380ca0d89dd51f31d7ae1f77a63d872bd1bb190213e8400e70849efc0fb75","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:49:58.930926Z","signature_b64":"xAQ+svnGYq/uJuIcjNTjiERV5L07ej0nAucIvuo8oxtMMOA52zySkWBLHj4nHNE5b2LhnEojw1hPRadELQwnAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21d380ca0d89dd51f31d7ae1f77a63d872bd1bb190213e8400e70849efc0fb75","last_reissued_at":"2026-07-05T06:49:58.930445Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:49:58.930445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.01248","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":"2026-07-05T06:49:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XXc8wb2QuOLiLY7CEbjX1lwOz0N+jCiw7VBaz4kYYtZX9hnXRrNJ3Id7M81oZc3VEW9xmp88Nxgp6lNfoTp5Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T23:49:44.254871Z"},"content_sha256":"69d7b48aa0fe4696b5d0bff0dd10799f81003ffaed88404cfbe0d9d2c135796d","schema_version":"1.0","event_id":"sha256:69d7b48aa0fe4696b5d0bff0dd10799f81003ffaed88404cfbe0d9d2c135796d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:EHJYBSQNRHOVD4Y5PLQ7O6TD3B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Markov Decision Processes without Model Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Han Wang, Scott M. Jordan, Tadashi Kozuno, Wenhao Yang, Zhihua Zhang","submitted_at":"2023-02-02T17:29:10Z","abstract_excerpt":"Robust Markov Decision Processes (MDPs) are receiving much attention in learning a robust policy which is less sensitive to environment changes. There are an increasing number of works analyzing sample-efficiency of robust MDPs. However, there are two major barriers to applying robust MDPs in practice. First, most works study robust MDPs in a model-based regime, where the transition probability needs to be estimated and requires a large amount of memories $\\mathcal{O}(|\\mathcal{S}|^2|\\mathcal{A}|)$. Second, prior work typically assumes a strong oracle to obtain the optimal solution as an inter"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.01248","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/2302.01248/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":"2026-07-05T06:49:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9QjM+SkIrxdDyqFFKBhTGt2pilOZ/pNlPK87BKUzEI49TncKckDNbH8B5URTq5+US/uUm+NdOroarRyRHsVxDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T23:49:44.255399Z"},"content_sha256":"d95880028d882ed46abf06b16f06419772d3236441379a4e07e8827155f1a1ee","schema_version":"1.0","event_id":"sha256:d95880028d882ed46abf06b16f06419772d3236441379a4e07e8827155f1a1ee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EHJYBSQNRHOVD4Y5PLQ7O6TD3B/bundle.json","state_url":"https://pith.science/pith/EHJYBSQNRHOVD4Y5PLQ7O6TD3B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EHJYBSQNRHOVD4Y5PLQ7O6TD3B/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":"2026-08-18T23:49:44Z","links":{"resolver":"https://pith.science/pith/EHJYBSQNRHOVD4Y5PLQ7O6TD3B","bundle":"https://pith.science/pith/EHJYBSQNRHOVD4Y5PLQ7O6TD3B/bundle.json","state":"https://pith.science/pith/EHJYBSQNRHOVD4Y5PLQ7O6TD3B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EHJYBSQNRHOVD4Y5PLQ7O6TD3B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EHJYBSQNRHOVD4Y5PLQ7O6TD3B","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":"96e461458ffb5c3fd4e0ee2e938c492f12f85ed78790a702bb8ecb3918aa902e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-02-02T17:29:10Z","title_canon_sha256":"492d9f3fe2148e1ca3fcb2f33f34bc32f9b7f0b333c6786ce4d63ff4a815579e"},"schema_version":"1.0","source":{"id":"2302.01248","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.01248","created_at":"2026-07-05T06:49:58Z"},{"alias_kind":"arxiv_version","alias_value":"2302.01248v2","created_at":"2026-07-05T06:49:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.01248","created_at":"2026-07-05T06:49:58Z"},{"alias_kind":"pith_short_12","alias_value":"EHJYBSQNRHOV","created_at":"2026-07-05T06:49:58Z"},{"alias_kind":"pith_short_16","alias_value":"EHJYBSQNRHOVD4Y5","created_at":"2026-07-05T06:49:58Z"},{"alias_kind":"pith_short_8","alias_value":"EHJYBSQN","created_at":"2026-07-05T06:49:58Z"}],"graph_snapshots":[{"event_id":"sha256:d95880028d882ed46abf06b16f06419772d3236441379a4e07e8827155f1a1ee","target":"graph","created_at":"2026-07-05T06:49:58Z","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/2302.01248/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Robust Markov Decision Processes (MDPs) are receiving much attention in learning a robust policy which is less sensitive to environment changes. There are an increasing number of works analyzing sample-efficiency of robust MDPs. However, there are two major barriers to applying robust MDPs in practice. First, most works study robust MDPs in a model-based regime, where the transition probability needs to be estimated and requires a large amount of memories $\\mathcal{O}(|\\mathcal{S}|^2|\\mathcal{A}|)$. Second, prior work typically assumes a strong oracle to obtain the optimal solution as an inter","authors_text":"Han Wang, Scott M. Jordan, Tadashi Kozuno, Wenhao Yang, Zhihua Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-02-02T17:29:10Z","title":"Robust Markov Decision Processes without Model Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.01248","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":"sha256:69d7b48aa0fe4696b5d0bff0dd10799f81003ffaed88404cfbe0d9d2c135796d","target":"record","created_at":"2026-07-05T06:49:58Z","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":"96e461458ffb5c3fd4e0ee2e938c492f12f85ed78790a702bb8ecb3918aa902e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-02-02T17:29:10Z","title_canon_sha256":"492d9f3fe2148e1ca3fcb2f33f34bc32f9b7f0b333c6786ce4d63ff4a815579e"},"schema_version":"1.0","source":{"id":"2302.01248","kind":"arxiv","version":2}},"canonical_sha256":"21d380ca0d89dd51f31d7ae1f77a63d872bd1bb190213e8400e70849efc0fb75","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"21d380ca0d89dd51f31d7ae1f77a63d872bd1bb190213e8400e70849efc0fb75","first_computed_at":"2026-07-05T06:49:58.930445Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:49:58.930445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xAQ+svnGYq/uJuIcjNTjiERV5L07ej0nAucIvuo8oxtMMOA52zySkWBLHj4nHNE5b2LhnEojw1hPRadELQwnAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:49:58.930926Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.01248","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:69d7b48aa0fe4696b5d0bff0dd10799f81003ffaed88404cfbe0d9d2c135796d","sha256:d95880028d882ed46abf06b16f06419772d3236441379a4e07e8827155f1a1ee"],"state_sha256":"fdb0fef682e8487b1afa2c5c7d616f45d32125e9d9a4cd0603ff1426f48579c5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0VcXY5uVKSP3wdJM6Rs+LS//NOJMODTgiKdkOGnBtH3aGyVAUTRvJCY7VhW1AGEL+MQ2I+dMYB+be6hBdF34Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T23:49:44.260858Z","bundle_sha256":"08d29475cea4fc4d63a5a41147a03bf786da6fb05f0907747bbb8526f87ad435"}}