{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FDMKUMDCRNPR7JBU25J26VHJ64","short_pith_number":"pith:FDMKUMDC","schema_version":"1.0","canonical_sha256":"28d8aa30628b5f1fa434d753af54e9f73fe70dd1542e640b9d46466a029c8271","source":{"kind":"arxiv","id":"2410.02711","version":3},"attestation_state":"computed","paper":{"title":"NETS: A Non-Equilibrium Transport Sampler","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.stat-mech","hep-lat"],"primary_cat":"cs.LG","authors_text":"Eric Vanden-Eijnden, Michael S. Albergo","submitted_at":"2024-10-03T17:35:38Z","abstract_excerpt":"We propose an algorithm, termed the Non-Equilibrium Transport Sampler (NETS), to sample from unnormalized probability distributions. NETS can be viewed as a variant of annealed importance sampling (AIS) based on Jarzynski's equality, in which the stochastic differential equation used to perform the non-equilibrium sampling is augmented with an additional learned drift term that lowers the impact of the unbiasing weights used in AIS. We show that this drift is the minimizer of a variety of objective functions, which can all be estimated in an unbiased fashion without backpropagating through sol"},"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":"2410.02711","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-03T17:35:38Z","cross_cats_sorted":["cond-mat.stat-mech","hep-lat"],"title_canon_sha256":"d0944ac9697dd331d0fa0cbe1737853bc3dd6ba8b3eeb066fb45258eb4cf8fb4","abstract_canon_sha256":"712cf35db049429d18c4104cd371dd6088ba03aa05b7b075601ba42dd903dce3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:53.227476Z","signature_b64":"M+/D+aq7fEMo/ZJQl9Ac8W+gZK/OLd24rKOXw5q1Nfdlmb/ZHN1eqxSxRCK2jZlYUfTAu5fAtVXoxkXWUbkMDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28d8aa30628b5f1fa434d753af54e9f73fe70dd1542e640b9d46466a029c8271","last_reissued_at":"2026-07-05T09:59:53.227042Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:53.227042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NETS: A Non-Equilibrium Transport Sampler","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.stat-mech","hep-lat"],"primary_cat":"cs.LG","authors_text":"Eric Vanden-Eijnden, Michael S. Albergo","submitted_at":"2024-10-03T17:35:38Z","abstract_excerpt":"We propose an algorithm, termed the Non-Equilibrium Transport Sampler (NETS), to sample from unnormalized probability distributions. NETS can be viewed as a variant of annealed importance sampling (AIS) based on Jarzynski's equality, in which the stochastic differential equation used to perform the non-equilibrium sampling is augmented with an additional learned drift term that lowers the impact of the unbiasing weights used in AIS. We show that this drift is the minimizer of a variety of objective functions, which can all be estimated in an unbiased fashion without backpropagating through sol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02711","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/2410.02711/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":"2410.02711","created_at":"2026-07-05T09:59:53.227098+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.02711v3","created_at":"2026-07-05T09:59:53.227098+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02711","created_at":"2026-07-05T09:59:53.227098+00:00"},{"alias_kind":"pith_short_12","alias_value":"FDMKUMDCRNPR","created_at":"2026-07-05T09:59:53.227098+00:00"},{"alias_kind":"pith_short_16","alias_value":"FDMKUMDCRNPR7JBU","created_at":"2026-07-05T09:59:53.227098+00:00"},{"alias_kind":"pith_short_8","alias_value":"FDMKUMDC","created_at":"2026-07-05T09:59:53.227098+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.06841","citing_title":"Tensor Train Diffusion: Leveraging Low-Rank Structures for High-Dimensional Score-Based Sampling","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2607.08160","citing_title":"Weak Poincar\\'e Inequalities via Approximate Stochastic Localization: Application to Sampling the Sherrington-Kirkpatrick Model","ref_index":185,"is_internal_anchor":true},{"citing_arxiv_id":"2605.31063","citing_title":"Free energy Estimation on Any State Space","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31498","citing_title":"Scalable Inference-Time Annealing with Surrogate Likelihood Estimators","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18745","citing_title":"SURGE: Approximation and Training Free Particle Filter for Diffusion Surrogate","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00295","citing_title":"Adaptive Order Policies for Masked Diffusion","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2308.08615","citing_title":"Improvement of Heatbath Algorithm in LFT using Generative models","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03718","citing_title":"Potential Hessian Ascent III: Sampling the Sherrington--Kirkpatrick Model at Beta < 1/2","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17808","citing_title":"A Unified Framework for Data-Free One-Step Sampling via Wasserstein Gradient Flows","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18745","citing_title":"SURGE: Approximation and Training Free Particle Filter for Diffusion Surrogate","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17850","citing_title":"Simple Approximation and Derivative Free Inference-Time Scaling for Diffusion Models via Sequential Monte Carlo on Path Measures","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2509.03726","citing_title":"Energy-Weighted Flow Matching: Unlocking Continuous Normalizing Flows for Efficient and Scalable Boltzmann Sampling","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2510.25704","citing_title":"Scaling flow-based approaches for topology sampling in $\\mathrm{SU}(3)$ gauge theory","ref_index":103,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03718","citing_title":"Potential Hessian Ascent III: Sampling the Sherrington--Kirkpatrick Model at Beta < 1/2","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20301","citing_title":"Properties and limitations of geometric tempering for gradient flow dynamics","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FDMKUMDCRNPR7JBU25J26VHJ64","json":"https://pith.science/pith/FDMKUMDCRNPR7JBU25J26VHJ64.json","graph_json":"https://pith.science/api/pith-number/FDMKUMDCRNPR7JBU25J26VHJ64/graph.json","events_json":"https://pith.science/api/pith-number/FDMKUMDCRNPR7JBU25J26VHJ64/events.json","paper":"https://pith.science/paper/FDMKUMDC"},"agent_actions":{"view_html":"https://pith.science/pith/FDMKUMDCRNPR7JBU25J26VHJ64","download_json":"https://pith.science/pith/FDMKUMDCRNPR7JBU25J26VHJ64.json","view_paper":"https://pith.science/paper/FDMKUMDC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.02711&json=true","fetch_graph":"https://pith.science/api/pith-number/FDMKUMDCRNPR7JBU25J26VHJ64/graph.json","fetch_events":"https://pith.science/api/pith-number/FDMKUMDCRNPR7JBU25J26VHJ64/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FDMKUMDCRNPR7JBU25J26VHJ64/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FDMKUMDCRNPR7JBU25J26VHJ64/action/storage_attestation","attest_author":"https://pith.science/pith/FDMKUMDCRNPR7JBU25J26VHJ64/action/author_attestation","sign_citation":"https://pith.science/pith/FDMKUMDCRNPR7JBU25J26VHJ64/action/citation_signature","submit_replication":"https://pith.science/pith/FDMKUMDCRNPR7JBU25J26VHJ64/action/replication_record"}},"created_at":"2026-07-05T09:59:53.227098+00:00","updated_at":"2026-07-05T09:59:53.227098+00:00"}