{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:H7VNZEODLCU245HUSFC2PK3CNA","short_pith_number":"pith:H7VNZEOD","canonical_record":{"source":{"id":"2505.19058","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-25T09:22:06Z","cross_cats_sorted":["math.OC","q-fin.PM","stat.ML"],"title_canon_sha256":"05a90620a18ef27cac2a12fefe607424a5e79fcc029404012ab975f1026a7c6f","abstract_canon_sha256":"28a13b6557b1b1d4b3be46c581f29a1fee84131fd1785840300e01bd4fa505ca"},"schema_version":"1.0"},"canonical_sha256":"3feadc91c358a9ae74f49145a7ab62683068bd07337a9612e51cc5d24373b866","source":{"kind":"arxiv","id":"2505.19058","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19058","created_at":"2026-07-05T11:09:24Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19058v1","created_at":"2026-07-05T11:09:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19058","created_at":"2026-07-05T11:09:24Z"},{"alias_kind":"pith_short_12","alias_value":"H7VNZEODLCU2","created_at":"2026-07-05T11:09:24Z"},{"alias_kind":"pith_short_16","alias_value":"H7VNZEODLCU245HU","created_at":"2026-07-05T11:09:24Z"},{"alias_kind":"pith_short_8","alias_value":"H7VNZEOD","created_at":"2026-07-05T11:09:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:H7VNZEODLCU245HUSFC2PK3CNA","target":"record","payload":{"canonical_record":{"source":{"id":"2505.19058","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-25T09:22:06Z","cross_cats_sorted":["math.OC","q-fin.PM","stat.ML"],"title_canon_sha256":"05a90620a18ef27cac2a12fefe607424a5e79fcc029404012ab975f1026a7c6f","abstract_canon_sha256":"28a13b6557b1b1d4b3be46c581f29a1fee84131fd1785840300e01bd4fa505ca"},"schema_version":"1.0"},"canonical_sha256":"3feadc91c358a9ae74f49145a7ab62683068bd07337a9612e51cc5d24373b866","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:24.240615Z","signature_b64":"k7MT+XkVPYBQCTpsAtHwlX/O1btPPQyR3uI0FWSMlrrA2DDe/aaIKk/C+yN2d/yXiWBScPQ9IpUHrO72T5ldDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3feadc91c358a9ae74f49145a7ab62683068bd07337a9612e51cc5d24373b866","last_reissued_at":"2026-07-05T11:09:24.240116Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:24.240116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.19058","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":"2026-07-05T11:09:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"StLdxW2o0sJCfouLr4j3uwRqNpsE8/cpZlM59p0tA7b2+EIfhospMyaVBGysqilokrBiuLLRFRtK0UdSQEMkDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:58:16.329179Z"},"content_sha256":"1017457b036a982068eaeb0fcfdf34f2713ca9167362d7141317f52155748641","schema_version":"1.0","event_id":"sha256:1017457b036a982068eaeb0fcfdf34f2713ca9167362d7141317f52155748641"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:H7VNZEODLCU245HUSFC2PK3CNA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distributionally Robust Deep Q-Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","q-fin.PM","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aijia Zhang, Chung I Lu, Julian Sester","submitted_at":"2025-05-25T09:22:06Z","abstract_excerpt":"We propose a novel distributionally robust $Q$-learning algorithm for the non-tabular case accounting for continuous state spaces where the state transition of the underlying Markov decision process is subject to model uncertainty. The uncertainty is taken into account by considering the worst-case transition from a ball around a reference probability measure. To determine the optimal policy under the worst-case state transition, we solve the associated non-linear Bellman equation by dualising and regularising the Bellman operator with the Sinkhorn distance, which is then parameterized with de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19058","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/2505.19058/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":"2026-07-05T11:09:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M0YJ5Zgccpiqz3mOToSWp+XDzoxhkB+LHNWhAFykHxrVJnl3Z/2v5Zdkq06JOBEWbQ5QXo6GlyKjV9ZXYOTgAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:58:16.329712Z"},"content_sha256":"3a160f160a198b90fd19e55407bf725abf980706b5da2b8affa44f17e323635b","schema_version":"1.0","event_id":"sha256:3a160f160a198b90fd19e55407bf725abf980706b5da2b8affa44f17e323635b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H7VNZEODLCU245HUSFC2PK3CNA/bundle.json","state_url":"https://pith.science/pith/H7VNZEODLCU245HUSFC2PK3CNA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H7VNZEODLCU245HUSFC2PK3CNA/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":"2026-08-08T22:58:16Z","links":{"resolver":"https://pith.science/pith/H7VNZEODLCU245HUSFC2PK3CNA","bundle":"https://pith.science/pith/H7VNZEODLCU245HUSFC2PK3CNA/bundle.json","state":"https://pith.science/pith/H7VNZEODLCU245HUSFC2PK3CNA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H7VNZEODLCU245HUSFC2PK3CNA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:H7VNZEODLCU245HUSFC2PK3CNA","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":"28a13b6557b1b1d4b3be46c581f29a1fee84131fd1785840300e01bd4fa505ca","cross_cats_sorted":["math.OC","q-fin.PM","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-25T09:22:06Z","title_canon_sha256":"05a90620a18ef27cac2a12fefe607424a5e79fcc029404012ab975f1026a7c6f"},"schema_version":"1.0","source":{"id":"2505.19058","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19058","created_at":"2026-07-05T11:09:24Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19058v1","created_at":"2026-07-05T11:09:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19058","created_at":"2026-07-05T11:09:24Z"},{"alias_kind":"pith_short_12","alias_value":"H7VNZEODLCU2","created_at":"2026-07-05T11:09:24Z"},{"alias_kind":"pith_short_16","alias_value":"H7VNZEODLCU245HU","created_at":"2026-07-05T11:09:24Z"},{"alias_kind":"pith_short_8","alias_value":"H7VNZEOD","created_at":"2026-07-05T11:09:24Z"}],"graph_snapshots":[{"event_id":"sha256:3a160f160a198b90fd19e55407bf725abf980706b5da2b8affa44f17e323635b","target":"graph","created_at":"2026-07-05T11:09:24Z","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/2505.19058/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a novel distributionally robust $Q$-learning algorithm for the non-tabular case accounting for continuous state spaces where the state transition of the underlying Markov decision process is subject to model uncertainty. The uncertainty is taken into account by considering the worst-case transition from a ball around a reference probability measure. To determine the optimal policy under the worst-case state transition, we solve the associated non-linear Bellman equation by dualising and regularising the Bellman operator with the Sinkhorn distance, which is then parameterized with de","authors_text":"Aijia Zhang, Chung I Lu, Julian Sester","cross_cats":["math.OC","q-fin.PM","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-25T09:22:06Z","title":"Distributionally Robust Deep Q-Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19058","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":"sha256:1017457b036a982068eaeb0fcfdf34f2713ca9167362d7141317f52155748641","target":"record","created_at":"2026-07-05T11:09:24Z","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":"28a13b6557b1b1d4b3be46c581f29a1fee84131fd1785840300e01bd4fa505ca","cross_cats_sorted":["math.OC","q-fin.PM","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-25T09:22:06Z","title_canon_sha256":"05a90620a18ef27cac2a12fefe607424a5e79fcc029404012ab975f1026a7c6f"},"schema_version":"1.0","source":{"id":"2505.19058","kind":"arxiv","version":1}},"canonical_sha256":"3feadc91c358a9ae74f49145a7ab62683068bd07337a9612e51cc5d24373b866","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3feadc91c358a9ae74f49145a7ab62683068bd07337a9612e51cc5d24373b866","first_computed_at":"2026-07-05T11:09:24.240116Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:24.240116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k7MT+XkVPYBQCTpsAtHwlX/O1btPPQyR3uI0FWSMlrrA2DDe/aaIKk/C+yN2d/yXiWBScPQ9IpUHrO72T5ldDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:24.240615Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19058","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1017457b036a982068eaeb0fcfdf34f2713ca9167362d7141317f52155748641","sha256:3a160f160a198b90fd19e55407bf725abf980706b5da2b8affa44f17e323635b"],"state_sha256":"d665e9f3b5efbb9da3d9c5f194781f6bb59d64c96327e3cf2515c32092209338"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OmyCKGSZKg/h/q+K0NpIGQAVDYjW7cPx8uXh5pH7zn6X8P6yC44MjBtizAU+tePSPsx9YHpmN9ouBw2GIv/KBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:58:16.334344Z","bundle_sha256":"1835028f958845d8842ac96e1d1cc44d3823a2228ed22f927357a35967862edf"}}