{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EZ6WMP4NOTHO6SLBHPIU4N2FYZ","short_pith_number":"pith:EZ6WMP4N","schema_version":"1.0","canonical_sha256":"267d663f8d74ceef49613bd14e3745c67c89e74172e7ed11ae8280e2f5027723","source":{"kind":"arxiv","id":"2606.27564","version":1},"attestation_state":"computed","paper":{"title":"Fast-Mixing Markov Chains without Gradients","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.CO","stat.TH"],"primary_cat":"math.ST","authors_text":"Robert Kutri, Robert Scheichl","submitted_at":"2026-06-25T21:43:50Z","abstract_excerpt":"Most approaches for accelerating Markov chain mixing either rely on incorporating expensive geometric information in the proposals, or reduce the per-step cost of sampling via surrogate densities. We propose a localisation principle that allows a surrogate-based Metropolis-Hastings proposal to exploit gradient-level geometric information of the target density, without evaluating either the target gradient or the surrogate gradient. The construction relies on regularisation and tempering of the proposal measure. We show that the expected proposal displacement coincides with the Langevin drift u"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.27564","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2026-06-25T21:43:50Z","cross_cats_sorted":["stat.CO","stat.TH"],"title_canon_sha256":"dc114b0cf1a113ea936a9a07a6da4e832eb81429822400b7a9da1a8b51a9ddcb","abstract_canon_sha256":"ee10a31706ff1175e9e2947403208f826b5cfe9e96ebe6a39cb0adf76076361f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T00:14:10.111223Z","signature_b64":"CWUccyXEQZmhLmdpHBJSqACbJh9SY1Uz88LQFx5VX3dIZo99rUR2n11ZtnpQLZaQnr2cUJVaVh69wgRRbaG0DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"267d663f8d74ceef49613bd14e3745c67c89e74172e7ed11ae8280e2f5027723","last_reissued_at":"2026-06-29T00:14:10.110815Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T00:14:10.110815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast-Mixing Markov Chains without Gradients","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.CO","stat.TH"],"primary_cat":"math.ST","authors_text":"Robert Kutri, Robert Scheichl","submitted_at":"2026-06-25T21:43:50Z","abstract_excerpt":"Most approaches for accelerating Markov chain mixing either rely on incorporating expensive geometric information in the proposals, or reduce the per-step cost of sampling via surrogate densities. We propose a localisation principle that allows a surrogate-based Metropolis-Hastings proposal to exploit gradient-level geometric information of the target density, without evaluating either the target gradient or the surrogate gradient. The construction relies on regularisation and tempering of the proposal measure. We show that the expected proposal displacement coincides with the Langevin drift u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27564","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/2606.27564/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.27564","created_at":"2026-06-29T00:14:10.110874+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.27564v1","created_at":"2026-06-29T00:14:10.110874+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27564","created_at":"2026-06-29T00:14:10.110874+00:00"},{"alias_kind":"pith_short_12","alias_value":"EZ6WMP4NOTHO","created_at":"2026-06-29T00:14:10.110874+00:00"},{"alias_kind":"pith_short_16","alias_value":"EZ6WMP4NOTHO6SLB","created_at":"2026-06-29T00:14:10.110874+00:00"},{"alias_kind":"pith_short_8","alias_value":"EZ6WMP4N","created_at":"2026-06-29T00:14:10.110874+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07519","citing_title":"Gradient-free Riemannian Langevin Sampler","ref_index":73,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EZ6WMP4NOTHO6SLBHPIU4N2FYZ","json":"https://pith.science/pith/EZ6WMP4NOTHO6SLBHPIU4N2FYZ.json","graph_json":"https://pith.science/api/pith-number/EZ6WMP4NOTHO6SLBHPIU4N2FYZ/graph.json","events_json":"https://pith.science/api/pith-number/EZ6WMP4NOTHO6SLBHPIU4N2FYZ/events.json","paper":"https://pith.science/paper/EZ6WMP4N"},"agent_actions":{"view_html":"https://pith.science/pith/EZ6WMP4NOTHO6SLBHPIU4N2FYZ","download_json":"https://pith.science/pith/EZ6WMP4NOTHO6SLBHPIU4N2FYZ.json","view_paper":"https://pith.science/paper/EZ6WMP4N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.27564&json=true","fetch_graph":"https://pith.science/api/pith-number/EZ6WMP4NOTHO6SLBHPIU4N2FYZ/graph.json","fetch_events":"https://pith.science/api/pith-number/EZ6WMP4NOTHO6SLBHPIU4N2FYZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EZ6WMP4NOTHO6SLBHPIU4N2FYZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EZ6WMP4NOTHO6SLBHPIU4N2FYZ/action/storage_attestation","attest_author":"https://pith.science/pith/EZ6WMP4NOTHO6SLBHPIU4N2FYZ/action/author_attestation","sign_citation":"https://pith.science/pith/EZ6WMP4NOTHO6SLBHPIU4N2FYZ/action/citation_signature","submit_replication":"https://pith.science/pith/EZ6WMP4NOTHO6SLBHPIU4N2FYZ/action/replication_record"}},"created_at":"2026-06-29T00:14:10.110874+00:00","updated_at":"2026-06-29T00:14:10.110874+00:00"}