{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:L27LVQ2CFEWQW2JBLM3M2C26E5","short_pith_number":"pith:L27LVQ2C","canonical_record":{"source":{"id":"2410.02275","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-03T07:54:04Z","cross_cats_sorted":[],"title_canon_sha256":"659886da069053307c99ad6bc200f37a5299dc3367611f800bcf2378ec05e0fb","abstract_canon_sha256":"5dd217ed067a6584bee1beea570234174f4c3cf11afc98f46280e60e1b893227"},"schema_version":"1.0"},"canonical_sha256":"5ebebac342292d0b69215b36cd0b5e27755ff67552cc303a84dddea79b0f06c9","source":{"kind":"arxiv","id":"2410.02275","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.02275","created_at":"2026-07-05T09:15:18Z"},{"alias_kind":"arxiv_version","alias_value":"2410.02275v1","created_at":"2026-07-05T09:15:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02275","created_at":"2026-07-05T09:15:18Z"},{"alias_kind":"pith_short_12","alias_value":"L27LVQ2CFEWQ","created_at":"2026-07-05T09:15:18Z"},{"alias_kind":"pith_short_16","alias_value":"L27LVQ2CFEWQW2JB","created_at":"2026-07-05T09:15:18Z"},{"alias_kind":"pith_short_8","alias_value":"L27LVQ2C","created_at":"2026-07-05T09:15:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:L27LVQ2CFEWQW2JBLM3M2C26E5","target":"record","payload":{"canonical_record":{"source":{"id":"2410.02275","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-03T07:54:04Z","cross_cats_sorted":[],"title_canon_sha256":"659886da069053307c99ad6bc200f37a5299dc3367611f800bcf2378ec05e0fb","abstract_canon_sha256":"5dd217ed067a6584bee1beea570234174f4c3cf11afc98f46280e60e1b893227"},"schema_version":"1.0"},"canonical_sha256":"5ebebac342292d0b69215b36cd0b5e27755ff67552cc303a84dddea79b0f06c9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:18.636813Z","signature_b64":"XEkP0M1caPYHMzWvkjTUacaYKIYebqlxTt9pEXZXJ8SD8eFd9wp030oRwZQVC3FLtEzPYwts5wa4czrp583vBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ebebac342292d0b69215b36cd0b5e27755ff67552cc303a84dddea79b0f06c9","last_reissued_at":"2026-07-05T09:15:18.636371Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:18.636371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.02275","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":"2026-07-05T09:15:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gnsFkFp215iSGUyzNpKG81/qy8FRtk4WSsUFH52UbcD2v1nYm2/sozL/T+AyzpSxN258rXn/T02kmBNLs55lDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:45:19.537284Z"},"content_sha256":"c1b7f770c33988505a8ed5d38083722c4f427c8f019b2e4a405de014d7972b25","schema_version":"1.0","event_id":"sha256:c1b7f770c33988505a8ed5d38083722c4f427c8f019b2e4a405de014d7972b25"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:L27LVQ2CFEWQW2JBLM3M2C26E5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimal Strong Regret and Violation in Constrained MDPs via Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alberto Marchesi, Francesco Emanuele Stradi, Matteo Castiglioni, Nicola Gatti","submitted_at":"2024-10-03T07:54:04Z","abstract_excerpt":"We study online learning in \\emph{constrained MDPs} (CMDPs), focusing on the goal of attaining sublinear strong regret and strong cumulative constraint violation. Differently from their standard (weak) counterparts, these metrics do not allow negative terms to compensate positive ones, raising considerable additional challenges. Efroni et al. (2020) were the first to propose an algorithm with sublinear strong regret and strong violation, by exploiting linear programming. Thus, their algorithm is highly inefficient, leaving as an open problem achieving sublinear bounds by means of policy optimi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02275","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/2410.02275/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":"2026-07-05T09:15:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0sFa7Ch8y5cXz15X9FpSRkwl0FdLVhRDzkgeYm4AIPzVwzQ+OVifflqmwLIkD7z5j151Guad/7DQ16C8fAGGBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:45:19.537820Z"},"content_sha256":"efabb65bd7a93ce7a07814f18095dcac07402e18d010cb8460bbffed112352b3","schema_version":"1.0","event_id":"sha256:efabb65bd7a93ce7a07814f18095dcac07402e18d010cb8460bbffed112352b3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L27LVQ2CFEWQW2JBLM3M2C26E5/bundle.json","state_url":"https://pith.science/pith/L27LVQ2CFEWQW2JBLM3M2C26E5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L27LVQ2CFEWQW2JBLM3M2C26E5/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":"2026-08-08T21:45:19Z","links":{"resolver":"https://pith.science/pith/L27LVQ2CFEWQW2JBLM3M2C26E5","bundle":"https://pith.science/pith/L27LVQ2CFEWQW2JBLM3M2C26E5/bundle.json","state":"https://pith.science/pith/L27LVQ2CFEWQW2JBLM3M2C26E5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L27LVQ2CFEWQW2JBLM3M2C26E5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:L27LVQ2CFEWQW2JBLM3M2C26E5","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":"5dd217ed067a6584bee1beea570234174f4c3cf11afc98f46280e60e1b893227","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-03T07:54:04Z","title_canon_sha256":"659886da069053307c99ad6bc200f37a5299dc3367611f800bcf2378ec05e0fb"},"schema_version":"1.0","source":{"id":"2410.02275","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.02275","created_at":"2026-07-05T09:15:18Z"},{"alias_kind":"arxiv_version","alias_value":"2410.02275v1","created_at":"2026-07-05T09:15:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02275","created_at":"2026-07-05T09:15:18Z"},{"alias_kind":"pith_short_12","alias_value":"L27LVQ2CFEWQ","created_at":"2026-07-05T09:15:18Z"},{"alias_kind":"pith_short_16","alias_value":"L27LVQ2CFEWQW2JB","created_at":"2026-07-05T09:15:18Z"},{"alias_kind":"pith_short_8","alias_value":"L27LVQ2C","created_at":"2026-07-05T09:15:18Z"}],"graph_snapshots":[{"event_id":"sha256:efabb65bd7a93ce7a07814f18095dcac07402e18d010cb8460bbffed112352b3","target":"graph","created_at":"2026-07-05T09:15:18Z","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/2410.02275/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study online learning in \\emph{constrained MDPs} (CMDPs), focusing on the goal of attaining sublinear strong regret and strong cumulative constraint violation. Differently from their standard (weak) counterparts, these metrics do not allow negative terms to compensate positive ones, raising considerable additional challenges. Efroni et al. (2020) were the first to propose an algorithm with sublinear strong regret and strong violation, by exploiting linear programming. Thus, their algorithm is highly inefficient, leaving as an open problem achieving sublinear bounds by means of policy optimi","authors_text":"Alberto Marchesi, Francesco Emanuele Stradi, Matteo Castiglioni, Nicola Gatti","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-03T07:54:04Z","title":"Optimal Strong Regret and Violation in Constrained MDPs via Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02275","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:c1b7f770c33988505a8ed5d38083722c4f427c8f019b2e4a405de014d7972b25","target":"record","created_at":"2026-07-05T09:15:18Z","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":"5dd217ed067a6584bee1beea570234174f4c3cf11afc98f46280e60e1b893227","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-03T07:54:04Z","title_canon_sha256":"659886da069053307c99ad6bc200f37a5299dc3367611f800bcf2378ec05e0fb"},"schema_version":"1.0","source":{"id":"2410.02275","kind":"arxiv","version":1}},"canonical_sha256":"5ebebac342292d0b69215b36cd0b5e27755ff67552cc303a84dddea79b0f06c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ebebac342292d0b69215b36cd0b5e27755ff67552cc303a84dddea79b0f06c9","first_computed_at":"2026-07-05T09:15:18.636371Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:15:18.636371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XEkP0M1caPYHMzWvkjTUacaYKIYebqlxTt9pEXZXJ8SD8eFd9wp030oRwZQVC3FLtEzPYwts5wa4czrp583vBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:15:18.636813Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.02275","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c1b7f770c33988505a8ed5d38083722c4f427c8f019b2e4a405de014d7972b25","sha256:efabb65bd7a93ce7a07814f18095dcac07402e18d010cb8460bbffed112352b3"],"state_sha256":"4dc310f6260308922229597ac072341594a3ccfb39856f4d2ab3c3bbfa5c880c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bR5jDFbhTgIrSD99+x28Xrvmx1z9D3EtRykxBCAbm6SxxTbaqpE7GIAUi/UqwneZe0B691rz+EfXk3bUYjA8CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T21:45:19.543379Z","bundle_sha256":"b646e619802de37f4b92fe36d5f5c3dc070141f38e2431be6e285e82b329d79c"}}