{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CUCHDONYFQ45ZKOBHSQRE5FRB4","short_pith_number":"pith:CUCHDONY","schema_version":"1.0","canonical_sha256":"150471b9b82c39dca9c13ca11274b10f1393823014a0bbd844780169c091c717","source":{"kind":"arxiv","id":"2307.01198","version":2},"attestation_state":"computed","paper":{"title":"Improved sampling via learned diffusions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","math.PR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Julius Berner, Lorenz Richter","submitted_at":"2023-07-03T17:58:26Z","abstract_excerpt":"Recently, a series of papers proposed deep learning-based approaches to sample from target distributions using controlled diffusion processes, being trained only on the unnormalized target densities without access to samples. Building on previous work, we identify these approaches as special cases of a generalized Schr\\\"odinger bridge problem, seeking a stochastic evolution between a given prior distribution and the specified target. We further generalize this framework by introducing a variational formulation based on divergences between path space measures of time-reversed diffusion processe"},"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":"2307.01198","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-03T17:58:26Z","cross_cats_sorted":["math.OC","math.PR","stat.ML"],"title_canon_sha256":"e80840fb1d9dde58fa3809603df99acc6fe8a08302e6931abec7ca01171fcbcc","abstract_canon_sha256":"e3c51182c0204d984805f7815bffd6a021ea413e575ab0bf9eaaeac6887d8cd9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:20.630011Z","signature_b64":"hxtpbgVVY1hCI9HHQ4fXeTtbZ6e8LW7rtd/z2lO1r9QdDd9HNpwLkq/6ZUYNJrNO3D79teqDe5DZ36u40HjvDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"150471b9b82c39dca9c13ca11274b10f1393823014a0bbd844780169c091c717","last_reissued_at":"2026-07-05T08:22:20.629503Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:20.629503Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved sampling via learned diffusions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","math.PR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Julius Berner, Lorenz Richter","submitted_at":"2023-07-03T17:58:26Z","abstract_excerpt":"Recently, a series of papers proposed deep learning-based approaches to sample from target distributions using controlled diffusion processes, being trained only on the unnormalized target densities without access to samples. Building on previous work, we identify these approaches as special cases of a generalized Schr\\\"odinger bridge problem, seeking a stochastic evolution between a given prior distribution and the specified target. We further generalize this framework by introducing a variational formulation based on divergences between path space measures of time-reversed diffusion processe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.01198","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/2307.01198/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":"2307.01198","created_at":"2026-07-05T08:22:20.629575+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.01198v2","created_at":"2026-07-05T08:22:20.629575+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.01198","created_at":"2026-07-05T08:22:20.629575+00:00"},{"alias_kind":"pith_short_12","alias_value":"CUCHDONYFQ45","created_at":"2026-07-05T08:22:20.629575+00:00"},{"alias_kind":"pith_short_16","alias_value":"CUCHDONYFQ45ZKOB","created_at":"2026-07-05T08:22:20.629575+00:00"},{"alias_kind":"pith_short_8","alias_value":"CUCHDONY","created_at":"2026-07-05T08:22:20.629575+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31498","citing_title":"Scalable Inference-Time Annealing with Surrogate Likelihood Estimators","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CUCHDONYFQ45ZKOBHSQRE5FRB4","json":"https://pith.science/pith/CUCHDONYFQ45ZKOBHSQRE5FRB4.json","graph_json":"https://pith.science/api/pith-number/CUCHDONYFQ45ZKOBHSQRE5FRB4/graph.json","events_json":"https://pith.science/api/pith-number/CUCHDONYFQ45ZKOBHSQRE5FRB4/events.json","paper":"https://pith.science/paper/CUCHDONY"},"agent_actions":{"view_html":"https://pith.science/pith/CUCHDONYFQ45ZKOBHSQRE5FRB4","download_json":"https://pith.science/pith/CUCHDONYFQ45ZKOBHSQRE5FRB4.json","view_paper":"https://pith.science/paper/CUCHDONY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.01198&json=true","fetch_graph":"https://pith.science/api/pith-number/CUCHDONYFQ45ZKOBHSQRE5FRB4/graph.json","fetch_events":"https://pith.science/api/pith-number/CUCHDONYFQ45ZKOBHSQRE5FRB4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CUCHDONYFQ45ZKOBHSQRE5FRB4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CUCHDONYFQ45ZKOBHSQRE5FRB4/action/storage_attestation","attest_author":"https://pith.science/pith/CUCHDONYFQ45ZKOBHSQRE5FRB4/action/author_attestation","sign_citation":"https://pith.science/pith/CUCHDONYFQ45ZKOBHSQRE5FRB4/action/citation_signature","submit_replication":"https://pith.science/pith/CUCHDONYFQ45ZKOBHSQRE5FRB4/action/replication_record"}},"created_at":"2026-07-05T08:22:20.629575+00:00","updated_at":"2026-07-05T08:22:20.629575+00:00"}