{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:W72YVII5LWAAIOQIEABHPRSEYX","short_pith_number":"pith:W72YVII5","schema_version":"1.0","canonical_sha256":"b7f58aa11d5d80043a08200277c644c5f7e50f3d9ac0ab0629aa9afe273660b3","source":{"kind":"arxiv","id":"2412.07081","version":2},"attestation_state":"computed","paper":{"title":"Sequential Controlled Langevin Diffusions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Anima Anandkumar, Denis Blessing, Gerhard Neumann, Julius Berner, Junhua Chen, Lorenz Richter","submitted_at":"2024-12-10T00:47:10Z","abstract_excerpt":"An effective approach for sampling from unnormalized densities is based on the idea of gradually transporting samples from an easy prior to the complicated target distribution. Two popular methods are (1) Sequential Monte Carlo (SMC), where the transport is performed through successive annealed densities via prescribed Markov chains and resampling steps, and (2) recently developed diffusion-based sampling methods, where a learned dynamical transport is used. Despite the common goal, both approaches have different, often complementary, advantages and drawbacks. The resampling steps in SMC allow"},"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":"2412.07081","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-12-10T00:47:10Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0b2bee68427adaf18cad2821cd36c20f9915673537c229fedbdf2c89c55475a4","abstract_canon_sha256":"73e356172e554ddd085ed074af3591f34fc6d002dcd9d7b2bed1fb92d9f2ffc9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:03.828974Z","signature_b64":"+WstecsTOK6L5rBgi2SC1eFnDWbyBb2x0y4GtgZwTPj7x3xVUYi5eTY1MLnmkJEUIQGSPPJ5cLFK3bezXdy3BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7f58aa11d5d80043a08200277c644c5f7e50f3d9ac0ab0629aa9afe273660b3","last_reissued_at":"2026-07-05T12:06:03.828476Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:03.828476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sequential Controlled Langevin Diffusions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Anima Anandkumar, Denis Blessing, Gerhard Neumann, Julius Berner, Junhua Chen, Lorenz Richter","submitted_at":"2024-12-10T00:47:10Z","abstract_excerpt":"An effective approach for sampling from unnormalized densities is based on the idea of gradually transporting samples from an easy prior to the complicated target distribution. Two popular methods are (1) Sequential Monte Carlo (SMC), where the transport is performed through successive annealed densities via prescribed Markov chains and resampling steps, and (2) recently developed diffusion-based sampling methods, where a learned dynamical transport is used. Despite the common goal, both approaches have different, often complementary, advantages and drawbacks. The resampling steps in SMC allow"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07081","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/2412.07081/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":"2412.07081","created_at":"2026-07-05T12:06:03.828537+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.07081v2","created_at":"2026-07-05T12:06:03.828537+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07081","created_at":"2026-07-05T12:06:03.828537+00:00"},{"alias_kind":"pith_short_12","alias_value":"W72YVII5LWAA","created_at":"2026-07-05T12:06:03.828537+00:00"},{"alias_kind":"pith_short_16","alias_value":"W72YVII5LWAAIOQI","created_at":"2026-07-05T12:06:03.828537+00:00"},{"alias_kind":"pith_short_8","alias_value":"W72YVII5","created_at":"2026-07-05T12:06:03.828537+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06841","citing_title":"Tensor Train Diffusion: Leveraging Low-Rank Structures for High-Dimensional Score-Based Sampling","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2602.20549","citing_title":"Sample-efficient evidence estimation of score based priors for model selection","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00337","citing_title":"FES-FM: Free Energy Surface Sampling via Reduced Flow Matching","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W72YVII5LWAAIOQIEABHPRSEYX","json":"https://pith.science/pith/W72YVII5LWAAIOQIEABHPRSEYX.json","graph_json":"https://pith.science/api/pith-number/W72YVII5LWAAIOQIEABHPRSEYX/graph.json","events_json":"https://pith.science/api/pith-number/W72YVII5LWAAIOQIEABHPRSEYX/events.json","paper":"https://pith.science/paper/W72YVII5"},"agent_actions":{"view_html":"https://pith.science/pith/W72YVII5LWAAIOQIEABHPRSEYX","download_json":"https://pith.science/pith/W72YVII5LWAAIOQIEABHPRSEYX.json","view_paper":"https://pith.science/paper/W72YVII5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.07081&json=true","fetch_graph":"https://pith.science/api/pith-number/W72YVII5LWAAIOQIEABHPRSEYX/graph.json","fetch_events":"https://pith.science/api/pith-number/W72YVII5LWAAIOQIEABHPRSEYX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W72YVII5LWAAIOQIEABHPRSEYX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W72YVII5LWAAIOQIEABHPRSEYX/action/storage_attestation","attest_author":"https://pith.science/pith/W72YVII5LWAAIOQIEABHPRSEYX/action/author_attestation","sign_citation":"https://pith.science/pith/W72YVII5LWAAIOQIEABHPRSEYX/action/citation_signature","submit_replication":"https://pith.science/pith/W72YVII5LWAAIOQIEABHPRSEYX/action/replication_record"}},"created_at":"2026-07-05T12:06:03.828537+00:00","updated_at":"2026-07-05T12:06:03.828537+00:00"}