{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:V6ENV2UNLZMKSKSOYJXX3QGP2V","short_pith_number":"pith:V6ENV2UN","canonical_record":{"source":{"id":"2501.13013","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-22T16:56:42Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"574be3a1cee121486c506e52708d7bf86750a46dc57f207049e0e547fd27c8ed","abstract_canon_sha256":"623d0c1e23a9c39fd9a07d7f077499f290a541f473668177f73f43866a87d073"},"schema_version":"1.0"},"canonical_sha256":"af88daea8d5e58a92a4ec26f7dc0cfd5512d8c4b8de309e7d336c1aabce31ddd","source":{"kind":"arxiv","id":"2501.13013","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.13013","created_at":"2026-07-05T10:04:01Z"},{"alias_kind":"arxiv_version","alias_value":"2501.13013v1","created_at":"2026-07-05T10:04:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13013","created_at":"2026-07-05T10:04:01Z"},{"alias_kind":"pith_short_12","alias_value":"V6ENV2UNLZMK","created_at":"2026-07-05T10:04:01Z"},{"alias_kind":"pith_short_16","alias_value":"V6ENV2UNLZMKSKSO","created_at":"2026-07-05T10:04:01Z"},{"alias_kind":"pith_short_8","alias_value":"V6ENV2UN","created_at":"2026-07-05T10:04:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:V6ENV2UNLZMKSKSOYJXX3QGP2V","target":"record","payload":{"canonical_record":{"source":{"id":"2501.13013","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-22T16:56:42Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"574be3a1cee121486c506e52708d7bf86750a46dc57f207049e0e547fd27c8ed","abstract_canon_sha256":"623d0c1e23a9c39fd9a07d7f077499f290a541f473668177f73f43866a87d073"},"schema_version":"1.0"},"canonical_sha256":"af88daea8d5e58a92a4ec26f7dc0cfd5512d8c4b8de309e7d336c1aabce31ddd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:01.776450Z","signature_b64":"4PcfAsSd5TaMWfIz9vnP9bBe+hfO+C5J9fq++Au/IkRd6wC2RMpYfxLwVJcFwlWn0WuNRxRUTNaVmc3V7WQ6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af88daea8d5e58a92a4ec26f7dc0cfd5512d8c4b8de309e7d336c1aabce31ddd","last_reissued_at":"2026-07-05T10:04:01.775971Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:01.775971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.13013","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":"2026-07-05T10:04:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m7m2P17q6xz4jCiVpqNbBFuchy1D4S3i8gedqWohFBdUD1vAo6k0Oe3gq238xF7LeEA6NeafIMrRfPBHZyS1DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T16:03:12.836229Z"},"content_sha256":"f04d9428a9a6489eaa7425da9a9fc406e6e166dfccd1e6db9d38223b0d0e3ab8","schema_version":"1.0","event_id":"sha256:f04d9428a9a6489eaa7425da9a9fc406e6e166dfccd1e6db9d38223b0d0e3ab8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:V6ENV2UNLZMKSKSOYJXX3QGP2V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The regret lower bound for communicating Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Odalric-Ambrym Maillard, Victor Boone","submitted_at":"2025-01-22T16:56:42Z","abstract_excerpt":"This paper is devoted to the extension of the regret lower bound beyond ergodic Markov decision processes (MDPs) in the problem dependent setting. While the regret lower bound for ergodic MDPs is well-known and reached by tractable algorithms, we prove that the regret lower bound becomes significatively more complex in communicating MDPs. Our lower bound revisits the necessary explorative behavior of consistent learning agents and further explains that all optimal regions of the environment must be overvisited compared to sub-optimal ones, a phenomenon that we refer to as co-exploration. In ta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13013","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/2501.13013/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":"2026-07-05T10:04:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V8VS2/8d/eMnFa38FSTr5MhIfpFG+PFzVSMmkmTWPV0aoCOtGGhz2s9WOqoo1LmzULMpBvxFbhXVRGJv09BoDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T16:03:12.836797Z"},"content_sha256":"64819f31037bdd150cf317a2b487e6fc6a32916573f8032685c83396ec3b1653","schema_version":"1.0","event_id":"sha256:64819f31037bdd150cf317a2b487e6fc6a32916573f8032685c83396ec3b1653"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V6ENV2UNLZMKSKSOYJXX3QGP2V/bundle.json","state_url":"https://pith.science/pith/V6ENV2UNLZMKSKSOYJXX3QGP2V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V6ENV2UNLZMKSKSOYJXX3QGP2V/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":"2026-08-05T16:03:12Z","links":{"resolver":"https://pith.science/pith/V6ENV2UNLZMKSKSOYJXX3QGP2V","bundle":"https://pith.science/pith/V6ENV2UNLZMKSKSOYJXX3QGP2V/bundle.json","state":"https://pith.science/pith/V6ENV2UNLZMKSKSOYJXX3QGP2V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V6ENV2UNLZMKSKSOYJXX3QGP2V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:V6ENV2UNLZMKSKSOYJXX3QGP2V","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":"623d0c1e23a9c39fd9a07d7f077499f290a541f473668177f73f43866a87d073","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-22T16:56:42Z","title_canon_sha256":"574be3a1cee121486c506e52708d7bf86750a46dc57f207049e0e547fd27c8ed"},"schema_version":"1.0","source":{"id":"2501.13013","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.13013","created_at":"2026-07-05T10:04:01Z"},{"alias_kind":"arxiv_version","alias_value":"2501.13013v1","created_at":"2026-07-05T10:04:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13013","created_at":"2026-07-05T10:04:01Z"},{"alias_kind":"pith_short_12","alias_value":"V6ENV2UNLZMK","created_at":"2026-07-05T10:04:01Z"},{"alias_kind":"pith_short_16","alias_value":"V6ENV2UNLZMKSKSO","created_at":"2026-07-05T10:04:01Z"},{"alias_kind":"pith_short_8","alias_value":"V6ENV2UN","created_at":"2026-07-05T10:04:01Z"}],"graph_snapshots":[{"event_id":"sha256:64819f31037bdd150cf317a2b487e6fc6a32916573f8032685c83396ec3b1653","target":"graph","created_at":"2026-07-05T10:04:01Z","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/2501.13013/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper is devoted to the extension of the regret lower bound beyond ergodic Markov decision processes (MDPs) in the problem dependent setting. While the regret lower bound for ergodic MDPs is well-known and reached by tractable algorithms, we prove that the regret lower bound becomes significatively more complex in communicating MDPs. Our lower bound revisits the necessary explorative behavior of consistent learning agents and further explains that all optimal regions of the environment must be overvisited compared to sub-optimal ones, a phenomenon that we refer to as co-exploration. In ta","authors_text":"Odalric-Ambrym Maillard, Victor Boone","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-22T16:56:42Z","title":"The regret lower bound for communicating Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13013","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:f04d9428a9a6489eaa7425da9a9fc406e6e166dfccd1e6db9d38223b0d0e3ab8","target":"record","created_at":"2026-07-05T10:04:01Z","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":"623d0c1e23a9c39fd9a07d7f077499f290a541f473668177f73f43866a87d073","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-22T16:56:42Z","title_canon_sha256":"574be3a1cee121486c506e52708d7bf86750a46dc57f207049e0e547fd27c8ed"},"schema_version":"1.0","source":{"id":"2501.13013","kind":"arxiv","version":1}},"canonical_sha256":"af88daea8d5e58a92a4ec26f7dc0cfd5512d8c4b8de309e7d336c1aabce31ddd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af88daea8d5e58a92a4ec26f7dc0cfd5512d8c4b8de309e7d336c1aabce31ddd","first_computed_at":"2026-07-05T10:04:01.775971Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:04:01.775971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4PcfAsSd5TaMWfIz9vnP9bBe+hfO+C5J9fq++Au/IkRd6wC2RMpYfxLwVJcFwlWn0WuNRxRUTNaVmc3V7WQ6CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:04:01.776450Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.13013","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f04d9428a9a6489eaa7425da9a9fc406e6e166dfccd1e6db9d38223b0d0e3ab8","sha256:64819f31037bdd150cf317a2b487e6fc6a32916573f8032685c83396ec3b1653"],"state_sha256":"4cc5bb59d7da369e00b0f3695c32b9e8137f327423ad590b9c90cdde01de01ed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S35/4zkppqYTJe97bJEC0TeR4j/ZFTqjVKlTKn9o48LyGNHh2gd7FQqIkpU0AQ5robFS5gYrw/8Igsv8Vv2VAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T16:03:12.840486Z","bundle_sha256":"c067389ee5a5848cbb0d4679e1f24d5503fb64d0a2bd9cfc598ff6fcaaf683d0"}}