{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:S4I4CLK4YYVFUZQ574OBQPFTAJ","short_pith_number":"pith:S4I4CLK4","schema_version":"1.0","canonical_sha256":"9711c12d5cc62a5a661dff1c183cb302484922e0bbae8b4e8af6adc9186c85b8","source":{"kind":"arxiv","id":"2401.04372","version":3},"attestation_state":"computed","paper":{"title":"Stable generative modeling using Schr\\\"odinger bridges","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA","stat.CO"],"primary_cat":"stat.ML","authors_text":"Fengyi Li, Georg A. Gottwald, Sebastian Reich, Youssef Marzouk","submitted_at":"2024-01-09T06:15:45Z","abstract_excerpt":"We consider the problem of sampling from an unknown distribution for which only a sufficiently large number of training samples are available. Such settings have recently drawn considerable interest in the context of generative modelling and Bayesian inference. In this paper, we propose a generative model combining Schr\\\"odinger bridges and Langevin dynamics. Schr\\\"odinger bridges over an appropriate reversible reference process are used to approximate the conditional transition probability from the available training samples, which is then implemented in a discrete-time reversible Langevin sa"},"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":"2401.04372","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-01-09T06:15:45Z","cross_cats_sorted":["cs.LG","cs.NA","math.NA","stat.CO"],"title_canon_sha256":"e7beadb138ab940bd700cf728be025ff524ab23b36c918696652815f69f3f8df","abstract_canon_sha256":"4d7701017c44054d908112fd065b02c7661a219ec58a1d88b7ec13b3c5e4f2f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:32.176879Z","signature_b64":"ChUHG22Nn68t0Xrba5ErnDVHhtEgsXGouIrIBKufFGUFnyhQyuZEuzcQr0mxGJ1Wzzz6h9yoH6mDCxdS/03mAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9711c12d5cc62a5a661dff1c183cb302484922e0bbae8b4e8af6adc9186c85b8","last_reissued_at":"2026-07-05T09:24:32.176373Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:32.176373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stable generative modeling using Schr\\\"odinger bridges","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA","stat.CO"],"primary_cat":"stat.ML","authors_text":"Fengyi Li, Georg A. Gottwald, Sebastian Reich, Youssef Marzouk","submitted_at":"2024-01-09T06:15:45Z","abstract_excerpt":"We consider the problem of sampling from an unknown distribution for which only a sufficiently large number of training samples are available. Such settings have recently drawn considerable interest in the context of generative modelling and Bayesian inference. In this paper, we propose a generative model combining Schr\\\"odinger bridges and Langevin dynamics. Schr\\\"odinger bridges over an appropriate reversible reference process are used to approximate the conditional transition probability from the available training samples, which is then implemented in a discrete-time reversible Langevin sa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.04372","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/2401.04372/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":"2401.04372","created_at":"2026-07-05T09:24:32.176438+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.04372v3","created_at":"2026-07-05T09:24:32.176438+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.04372","created_at":"2026-07-05T09:24:32.176438+00:00"},{"alias_kind":"pith_short_12","alias_value":"S4I4CLK4YYVF","created_at":"2026-07-05T09:24:32.176438+00:00"},{"alias_kind":"pith_short_16","alias_value":"S4I4CLK4YYVFUZQ5","created_at":"2026-07-05T09:24:32.176438+00:00"},{"alias_kind":"pith_short_8","alias_value":"S4I4CLK4","created_at":"2026-07-05T09:24:32.176438+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08794","citing_title":"Deterministic Decomposition of Stochastic Generative Dynamics","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08794","citing_title":"Deterministic Decomposition of Stochastic Generative Dynamics","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S4I4CLK4YYVFUZQ574OBQPFTAJ","json":"https://pith.science/pith/S4I4CLK4YYVFUZQ574OBQPFTAJ.json","graph_json":"https://pith.science/api/pith-number/S4I4CLK4YYVFUZQ574OBQPFTAJ/graph.json","events_json":"https://pith.science/api/pith-number/S4I4CLK4YYVFUZQ574OBQPFTAJ/events.json","paper":"https://pith.science/paper/S4I4CLK4"},"agent_actions":{"view_html":"https://pith.science/pith/S4I4CLK4YYVFUZQ574OBQPFTAJ","download_json":"https://pith.science/pith/S4I4CLK4YYVFUZQ574OBQPFTAJ.json","view_paper":"https://pith.science/paper/S4I4CLK4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.04372&json=true","fetch_graph":"https://pith.science/api/pith-number/S4I4CLK4YYVFUZQ574OBQPFTAJ/graph.json","fetch_events":"https://pith.science/api/pith-number/S4I4CLK4YYVFUZQ574OBQPFTAJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S4I4CLK4YYVFUZQ574OBQPFTAJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S4I4CLK4YYVFUZQ574OBQPFTAJ/action/storage_attestation","attest_author":"https://pith.science/pith/S4I4CLK4YYVFUZQ574OBQPFTAJ/action/author_attestation","sign_citation":"https://pith.science/pith/S4I4CLK4YYVFUZQ574OBQPFTAJ/action/citation_signature","submit_replication":"https://pith.science/pith/S4I4CLK4YYVFUZQ574OBQPFTAJ/action/replication_record"}},"created_at":"2026-07-05T09:24:32.176438+00:00","updated_at":"2026-07-05T09:24:32.176438+00:00"}