{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:V2A3R5RSXXATHB3UKQF72Q6VUV","short_pith_number":"pith:V2A3R5RS","canonical_record":{"source":{"id":"2111.02702","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-11-04T09:26:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"41ede2d8d9d1c345298b4e0246f0580220b924b310f65e79723daa851753c239","abstract_canon_sha256":"fda2edf06e9e8b78c5bc59e098195d053f95a0ca4989e3e96649b7d93fb4321c"},"schema_version":"1.0"},"canonical_sha256":"ae81b8f632bdc1338774540bfd43d5a55c8a0e3f4b864b75fef776f1fe6aaab7","source":{"kind":"arxiv","id":"2111.02702","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.02702","created_at":"2026-07-05T05:02:55Z"},{"alias_kind":"arxiv_version","alias_value":"2111.02702v3","created_at":"2026-07-05T05:02:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.02702","created_at":"2026-07-05T05:02:55Z"},{"alias_kind":"pith_short_12","alias_value":"V2A3R5RSXXAT","created_at":"2026-07-05T05:02:55Z"},{"alias_kind":"pith_short_16","alias_value":"V2A3R5RSXXATHB3U","created_at":"2026-07-05T05:02:55Z"},{"alias_kind":"pith_short_8","alias_value":"V2A3R5RS","created_at":"2026-07-05T05:02:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:V2A3R5RSXXATHB3UKQF72Q6VUV","target":"record","payload":{"canonical_record":{"source":{"id":"2111.02702","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-11-04T09:26:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"41ede2d8d9d1c345298b4e0246f0580220b924b310f65e79723daa851753c239","abstract_canon_sha256":"fda2edf06e9e8b78c5bc59e098195d053f95a0ca4989e3e96649b7d93fb4321c"},"schema_version":"1.0"},"canonical_sha256":"ae81b8f632bdc1338774540bfd43d5a55c8a0e3f4b864b75fef776f1fe6aaab7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:02:55.610260Z","signature_b64":"gqDhki3q9wtCJQ5VS00BDfxFo3SjamMAvid2B9cVP7nMz9+tN7XS4XnUZKmFRiI7AomXE8Bj5/PEx55IS10eCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae81b8f632bdc1338774540bfd43d5a55c8a0e3f4b864b75fef776f1fe6aaab7","last_reissued_at":"2026-07-05T05:02:55.609773Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:02:55.609773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.02702","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:02:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eyEGOekWqmg7zC6IPS/TstwfDZcV+ATnkdIDoZBMRCWuWIdAZDmcyVr9ZUelj4CIgx7xaQo4I9wAice1clgLCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T07:59:48.783851Z"},"content_sha256":"f1228ca0fb964a75210dba876e1c49cafe33771d7687e3a4fcb773ad892a86d4","schema_version":"1.0","event_id":"sha256:f1228ca0fb964a75210dba876e1c49cafe33771d7687e3a4fcb773ad892a86d4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:V2A3R5RSXXATHB3UKQF72Q6VUV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Local-Global MCMC kernels: the best of both worlds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alain Durmus, Alexey Naumov, Eric Moulines, Evgeny Lagutin, Marylou Gabri\\'e, Sergey Samsonov","submitted_at":"2021-11-04T09:26:38Z","abstract_excerpt":"Recent works leveraging learning to enhance sampling have shown promising results, in particular by designing effective non-local moves and global proposals. However, learning accuracy is inevitably limited in regions where little data is available such as in the tails of distributions as well as in high-dimensional problems. In the present paper we study an Explore-Exploit Markov chain Monte Carlo strategy ($Ex^2MCMC$) that combines local and global samplers showing that it enjoys the advantages of both approaches. We prove $V$-uniform geometric ergodicity of $Ex^2MCMC$ without requiring a un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.02702","kind":"arxiv","version":3},"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/2111.02702/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":"2026-07-05T05:02:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q1rELmhcUGXL9q6m0OA2/SxJTNnGn98H9c+iAHiVyph2O6cu4qXUdmOkPeWGqk6J5ZkKe9ofcLKeQp6bl6ueBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T07:59:48.784352Z"},"content_sha256":"e39d8df2a8e8b222e6a5303ae0ab9d7ca45431d7b832eef39f3b151548e76a83","schema_version":"1.0","event_id":"sha256:e39d8df2a8e8b222e6a5303ae0ab9d7ca45431d7b832eef39f3b151548e76a83"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V2A3R5RSXXATHB3UKQF72Q6VUV/bundle.json","state_url":"https://pith.science/pith/V2A3R5RSXXATHB3UKQF72Q6VUV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V2A3R5RSXXATHB3UKQF72Q6VUV/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":"2026-08-17T07:59:48Z","links":{"resolver":"https://pith.science/pith/V2A3R5RSXXATHB3UKQF72Q6VUV","bundle":"https://pith.science/pith/V2A3R5RSXXATHB3UKQF72Q6VUV/bundle.json","state":"https://pith.science/pith/V2A3R5RSXXATHB3UKQF72Q6VUV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V2A3R5RSXXATHB3UKQF72Q6VUV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:V2A3R5RSXXATHB3UKQF72Q6VUV","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":"fda2edf06e9e8b78c5bc59e098195d053f95a0ca4989e3e96649b7d93fb4321c","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-11-04T09:26:38Z","title_canon_sha256":"41ede2d8d9d1c345298b4e0246f0580220b924b310f65e79723daa851753c239"},"schema_version":"1.0","source":{"id":"2111.02702","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.02702","created_at":"2026-07-05T05:02:55Z"},{"alias_kind":"arxiv_version","alias_value":"2111.02702v3","created_at":"2026-07-05T05:02:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.02702","created_at":"2026-07-05T05:02:55Z"},{"alias_kind":"pith_short_12","alias_value":"V2A3R5RSXXAT","created_at":"2026-07-05T05:02:55Z"},{"alias_kind":"pith_short_16","alias_value":"V2A3R5RSXXATHB3U","created_at":"2026-07-05T05:02:55Z"},{"alias_kind":"pith_short_8","alias_value":"V2A3R5RS","created_at":"2026-07-05T05:02:55Z"}],"graph_snapshots":[{"event_id":"sha256:e39d8df2a8e8b222e6a5303ae0ab9d7ca45431d7b832eef39f3b151548e76a83","target":"graph","created_at":"2026-07-05T05:02:55Z","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/2111.02702/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent works leveraging learning to enhance sampling have shown promising results, in particular by designing effective non-local moves and global proposals. However, learning accuracy is inevitably limited in regions where little data is available such as in the tails of distributions as well as in high-dimensional problems. In the present paper we study an Explore-Exploit Markov chain Monte Carlo strategy ($Ex^2MCMC$) that combines local and global samplers showing that it enjoys the advantages of both approaches. We prove $V$-uniform geometric ergodicity of $Ex^2MCMC$ without requiring a un","authors_text":"Alain Durmus, Alexey Naumov, Eric Moulines, Evgeny Lagutin, Marylou Gabri\\'e, Sergey Samsonov","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-11-04T09:26:38Z","title":"Local-Global MCMC kernels: the best of both worlds"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.02702","kind":"arxiv","version":3},"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:f1228ca0fb964a75210dba876e1c49cafe33771d7687e3a4fcb773ad892a86d4","target":"record","created_at":"2026-07-05T05:02:55Z","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":"fda2edf06e9e8b78c5bc59e098195d053f95a0ca4989e3e96649b7d93fb4321c","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-11-04T09:26:38Z","title_canon_sha256":"41ede2d8d9d1c345298b4e0246f0580220b924b310f65e79723daa851753c239"},"schema_version":"1.0","source":{"id":"2111.02702","kind":"arxiv","version":3}},"canonical_sha256":"ae81b8f632bdc1338774540bfd43d5a55c8a0e3f4b864b75fef776f1fe6aaab7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae81b8f632bdc1338774540bfd43d5a55c8a0e3f4b864b75fef776f1fe6aaab7","first_computed_at":"2026-07-05T05:02:55.609773Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:02:55.609773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gqDhki3q9wtCJQ5VS00BDfxFo3SjamMAvid2B9cVP7nMz9+tN7XS4XnUZKmFRiI7AomXE8Bj5/PEx55IS10eCA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:02:55.610260Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.02702","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f1228ca0fb964a75210dba876e1c49cafe33771d7687e3a4fcb773ad892a86d4","sha256:e39d8df2a8e8b222e6a5303ae0ab9d7ca45431d7b832eef39f3b151548e76a83"],"state_sha256":"97428b2c44f4f627fa764e6315c8cfc5961a337885c617ea25926346c07d1cb0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mESoci2KyMKv8XHEFmjQim09fPqmJfeox4XCvxe7TirgKJMUz2XdYPTQPNPpfCX4qPdIzobtNYcLpNs9wKluCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T07:59:48.789270Z","bundle_sha256":"3601a81a8428ff51e5c463d0cdd73e96e56d18f32df882af580471e177b7f9ca"}}