{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CHEZPBPDL4AWVHDBUP4MAOX76K","short_pith_number":"pith:CHEZPBPD","schema_version":"1.0","canonical_sha256":"11c99785e35f016a9c61a3f8c03afff28957ed29b7d9e0b7dcabdba0a83a3853","source":{"kind":"arxiv","id":"2602.01449","version":2},"attestation_state":"computed","paper":{"title":"Dimension-Free Multimodal Sampling via Preconditioned Annealed Langevin Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.PR","stat.ML"],"primary_cat":"math.NA","authors_text":"Josselin Garnier, Knut Solna, Lorenzo Baldassari, Maarten V. de Hoop","submitted_at":"2026-02-01T21:37:33Z","abstract_excerpt":"Designing sampling algorithms for multimodal targets that remain stable under refinement of the finite-dimensional approximation of an underlying function-space problem is a central challenge. Annealed Langevin dynamics (ALD) is a natural alternative to classical Langevin in this context, since it is often observed to improve exploration across modes. Yet a gap remains between its empirical success and existing theory: under which conditions can ALD be guaranteed to remain stable across dimensions? In this paper, we bridge this gap by providing a uniform-in-dimension analysis of continuous-tim"},"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":"2602.01449","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2026-02-01T21:37:33Z","cross_cats_sorted":["cs.NA","math.PR","stat.ML"],"title_canon_sha256":"de199b2d9ecb1bb504c6bf39d57a81d3a45e79a2e3b298ed8369600186fba917","abstract_canon_sha256":"60b0e69740aaff0c42f9ac691e3c17b24be9042bf226caf3a46bb8bb7b055850"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:13.983139Z","signature_b64":"uXCFCFezbJQeEPyUokmphegX+hD1MgkENYqHb6J2VW0aH4D783gEE3Sleyv14yOIIb0lc3EZKExmtww4389RDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11c99785e35f016a9c61a3f8c03afff28957ed29b7d9e0b7dcabdba0a83a3853","last_reissued_at":"2026-05-25T02:01:13.982224Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:13.982224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dimension-Free Multimodal Sampling via Preconditioned Annealed Langevin Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.PR","stat.ML"],"primary_cat":"math.NA","authors_text":"Josselin Garnier, Knut Solna, Lorenzo Baldassari, Maarten V. de Hoop","submitted_at":"2026-02-01T21:37:33Z","abstract_excerpt":"Designing sampling algorithms for multimodal targets that remain stable under refinement of the finite-dimensional approximation of an underlying function-space problem is a central challenge. Annealed Langevin dynamics (ALD) is a natural alternative to classical Langevin in this context, since it is often observed to improve exploration across modes. Yet a gap remains between its empirical success and existing theory: under which conditions can ALD be guaranteed to remain stable across dimensions? In this paper, we bridge this gap by providing a uniform-in-dimension analysis of continuous-tim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.01449","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/2602.01449/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":"2602.01449","created_at":"2026-05-25T02:01:13.982373+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.01449v2","created_at":"2026-05-25T02:01:13.982373+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.01449","created_at":"2026-05-25T02:01:13.982373+00:00"},{"alias_kind":"pith_short_12","alias_value":"CHEZPBPDL4AW","created_at":"2026-05-25T02:01:13.982373+00:00"},{"alias_kind":"pith_short_16","alias_value":"CHEZPBPDL4AWVHDB","created_at":"2026-05-25T02:01:13.982373+00:00"},{"alias_kind":"pith_short_8","alias_value":"CHEZPBPD","created_at":"2026-05-25T02:01:13.982373+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.16473","citing_title":"Dimension-Uniform Discretization Analysis of Preconditioned Annealed Langevin Dynamics for Multimodal Gaussian Mixtures","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06091","citing_title":"Time-Inhomogeneous Preconditioned Langevin Dynamics","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07950","citing_title":"Slowly Annealed Langevin Dynamics: Theory and Applications to Training-Free Guided Generation","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CHEZPBPDL4AWVHDBUP4MAOX76K","json":"https://pith.science/pith/CHEZPBPDL4AWVHDBUP4MAOX76K.json","graph_json":"https://pith.science/api/pith-number/CHEZPBPDL4AWVHDBUP4MAOX76K/graph.json","events_json":"https://pith.science/api/pith-number/CHEZPBPDL4AWVHDBUP4MAOX76K/events.json","paper":"https://pith.science/paper/CHEZPBPD"},"agent_actions":{"view_html":"https://pith.science/pith/CHEZPBPDL4AWVHDBUP4MAOX76K","download_json":"https://pith.science/pith/CHEZPBPDL4AWVHDBUP4MAOX76K.json","view_paper":"https://pith.science/paper/CHEZPBPD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.01449&json=true","fetch_graph":"https://pith.science/api/pith-number/CHEZPBPDL4AWVHDBUP4MAOX76K/graph.json","fetch_events":"https://pith.science/api/pith-number/CHEZPBPDL4AWVHDBUP4MAOX76K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CHEZPBPDL4AWVHDBUP4MAOX76K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CHEZPBPDL4AWVHDBUP4MAOX76K/action/storage_attestation","attest_author":"https://pith.science/pith/CHEZPBPDL4AWVHDBUP4MAOX76K/action/author_attestation","sign_citation":"https://pith.science/pith/CHEZPBPDL4AWVHDBUP4MAOX76K/action/citation_signature","submit_replication":"https://pith.science/pith/CHEZPBPDL4AWVHDBUP4MAOX76K/action/replication_record"}},"created_at":"2026-05-25T02:01:13.982373+00:00","updated_at":"2026-05-25T02:01:13.982373+00:00"}