{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:W5NNJFCXPXTFER5TD54SQD5DRA","short_pith_number":"pith:W5NNJFCX","canonical_record":{"source":{"id":"2304.14326","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-27T16:58:29Z","cross_cats_sorted":[],"title_canon_sha256":"12d919e218120a123fa6404a5024891d805c0071d61b33ee6db07df3654cd81e","abstract_canon_sha256":"e97e03e217599b68b5873c716abb3442bf67d95d864a73660f6ddb7a2c2653c0"},"schema_version":"1.0"},"canonical_sha256":"b75ad494577de65247b31f79280fa38836fd7a657e765ec19d60510da5abcbb4","source":{"kind":"arxiv","id":"2304.14326","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.14326","created_at":"2026-07-05T09:00:20Z"},{"alias_kind":"arxiv_version","alias_value":"2304.14326v2","created_at":"2026-07-05T09:00:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14326","created_at":"2026-07-05T09:00:20Z"},{"alias_kind":"pith_short_12","alias_value":"W5NNJFCXPXTF","created_at":"2026-07-05T09:00:20Z"},{"alias_kind":"pith_short_16","alias_value":"W5NNJFCXPXTFER5T","created_at":"2026-07-05T09:00:20Z"},{"alias_kind":"pith_short_8","alias_value":"W5NNJFCX","created_at":"2026-07-05T09:00:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:W5NNJFCXPXTFER5TD54SQD5DRA","target":"record","payload":{"canonical_record":{"source":{"id":"2304.14326","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-27T16:58:29Z","cross_cats_sorted":[],"title_canon_sha256":"12d919e218120a123fa6404a5024891d805c0071d61b33ee6db07df3654cd81e","abstract_canon_sha256":"e97e03e217599b68b5873c716abb3442bf67d95d864a73660f6ddb7a2c2653c0"},"schema_version":"1.0"},"canonical_sha256":"b75ad494577de65247b31f79280fa38836fd7a657e765ec19d60510da5abcbb4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:00:20.977362Z","signature_b64":"ygc/g4oSqYxUGpQRCD+wshVNdnfSwpo8LhxwbD8ZcBfSI2LShm5aGJZ3tIjggALOObCZZAALdQ16S0wTym7XCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b75ad494577de65247b31f79280fa38836fd7a657e765ec19d60510da5abcbb4","last_reissued_at":"2026-07-05T09:00:20.976848Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:00:20.976848Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.14326","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":"2026-07-05T09:00:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LNKodKMTitSJWHESlf8Iw1xfx+BtP6nCJ6kF/V2wr72EnB4Rpz3AiYQ+H6r0o6sYLjxrjs6OHTALEV4v6Mw8Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T09:00:52.051050Z"},"content_sha256":"26741cfbf975b848872839bc6208154c849658bce9d17a4506646d24784eff77","schema_version":"1.0","event_id":"sha256:26741cfbf975b848872839bc6208154c849658bce9d17a4506646d24784eff77"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:W5NNJFCXPXTFER5TD54SQD5DRA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Best-of-Both-Worlds Algorithm for Constrained MDPs with Long-Term Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alberto Marchesi, Francesco Emanuele Stradi, Gianmarco Genalti, Jacopo Germano, Matteo Castiglioni, Nicola Gatti","submitted_at":"2023-04-27T16:58:29Z","abstract_excerpt":"We study online learning in episodic constrained Markov decision processes (CMDPs), where the learner aims at collecting as much reward as possible over the episodes, while satisfying some long-term constraints during the learning process. Rewards and constraints can be selected either stochastically or adversarially, and the transition function is not known to the learner. While online learning in classical (unconstrained) MDPs has received considerable attention over the last years, the setting of CMDPs is still largely unexplored. This is surprising, since in real-world applications, such a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14326","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/2304.14326/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":"2026-07-05T09:00:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6QiW8Hj7a2ELMupDSQF0mNzJzw4n3C7QyhGA2Wu5DRG0O7ba6fWKhE2o7SZsVh9Q7V5/HDsYe24x0eoMEW4EDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T09:00:52.051691Z"},"content_sha256":"7d0ed88be368bee3109c13abca86a47421bc7ada925c21e3eb0897fe2db45fdc","schema_version":"1.0","event_id":"sha256:7d0ed88be368bee3109c13abca86a47421bc7ada925c21e3eb0897fe2db45fdc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W5NNJFCXPXTFER5TD54SQD5DRA/bundle.json","state_url":"https://pith.science/pith/W5NNJFCXPXTFER5TD54SQD5DRA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W5NNJFCXPXTFER5TD54SQD5DRA/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":"2026-08-19T09:00:52Z","links":{"resolver":"https://pith.science/pith/W5NNJFCXPXTFER5TD54SQD5DRA","bundle":"https://pith.science/pith/W5NNJFCXPXTFER5TD54SQD5DRA/bundle.json","state":"https://pith.science/pith/W5NNJFCXPXTFER5TD54SQD5DRA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W5NNJFCXPXTFER5TD54SQD5DRA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:W5NNJFCXPXTFER5TD54SQD5DRA","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":"e97e03e217599b68b5873c716abb3442bf67d95d864a73660f6ddb7a2c2653c0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-27T16:58:29Z","title_canon_sha256":"12d919e218120a123fa6404a5024891d805c0071d61b33ee6db07df3654cd81e"},"schema_version":"1.0","source":{"id":"2304.14326","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.14326","created_at":"2026-07-05T09:00:20Z"},{"alias_kind":"arxiv_version","alias_value":"2304.14326v2","created_at":"2026-07-05T09:00:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14326","created_at":"2026-07-05T09:00:20Z"},{"alias_kind":"pith_short_12","alias_value":"W5NNJFCXPXTF","created_at":"2026-07-05T09:00:20Z"},{"alias_kind":"pith_short_16","alias_value":"W5NNJFCXPXTFER5T","created_at":"2026-07-05T09:00:20Z"},{"alias_kind":"pith_short_8","alias_value":"W5NNJFCX","created_at":"2026-07-05T09:00:20Z"}],"graph_snapshots":[{"event_id":"sha256:7d0ed88be368bee3109c13abca86a47421bc7ada925c21e3eb0897fe2db45fdc","target":"graph","created_at":"2026-07-05T09:00:20Z","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/2304.14326/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study online learning in episodic constrained Markov decision processes (CMDPs), where the learner aims at collecting as much reward as possible over the episodes, while satisfying some long-term constraints during the learning process. Rewards and constraints can be selected either stochastically or adversarially, and the transition function is not known to the learner. While online learning in classical (unconstrained) MDPs has received considerable attention over the last years, the setting of CMDPs is still largely unexplored. This is surprising, since in real-world applications, such a","authors_text":"Alberto Marchesi, Francesco Emanuele Stradi, Gianmarco Genalti, Jacopo Germano, Matteo Castiglioni, Nicola Gatti","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-27T16:58:29Z","title":"A Best-of-Both-Worlds Algorithm for Constrained MDPs with Long-Term Constraints"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14326","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":"sha256:26741cfbf975b848872839bc6208154c849658bce9d17a4506646d24784eff77","target":"record","created_at":"2026-07-05T09:00:20Z","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":"e97e03e217599b68b5873c716abb3442bf67d95d864a73660f6ddb7a2c2653c0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-27T16:58:29Z","title_canon_sha256":"12d919e218120a123fa6404a5024891d805c0071d61b33ee6db07df3654cd81e"},"schema_version":"1.0","source":{"id":"2304.14326","kind":"arxiv","version":2}},"canonical_sha256":"b75ad494577de65247b31f79280fa38836fd7a657e765ec19d60510da5abcbb4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b75ad494577de65247b31f79280fa38836fd7a657e765ec19d60510da5abcbb4","first_computed_at":"2026-07-05T09:00:20.976848Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:00:20.976848Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ygc/g4oSqYxUGpQRCD+wshVNdnfSwpo8LhxwbD8ZcBfSI2LShm5aGJZ3tIjggALOObCZZAALdQ16S0wTym7XCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:00:20.977362Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.14326","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26741cfbf975b848872839bc6208154c849658bce9d17a4506646d24784eff77","sha256:7d0ed88be368bee3109c13abca86a47421bc7ada925c21e3eb0897fe2db45fdc"],"state_sha256":"228468d8a97383e75753278e8b128b558e77ca9e9285ec788abbed426ff3e42f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZeoEHc1OzklrLjj1OetFAY6MD+CqRAFF1oH3OCZ54lEvXcDrDhRR7qemfoPyyOui9UX5VMKJ3SbYYQ3b0RJuDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T09:00:52.056569Z","bundle_sha256":"416cf475efa0bb74c73388c191de64c539dd59e6480b4385d9f7b92fe5c9be31"}}