{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QWPLF6VDOQPXANRRZL62UUO4BI","short_pith_number":"pith:QWPLF6VD","schema_version":"1.0","canonical_sha256":"859eb2faa3741f703631cafdaa51dc0a1b75ceb5f9ec22790505954848ed7b61","source":{"kind":"arxiv","id":"2402.15285","version":1},"attestation_state":"computed","paper":{"title":"Generative Modelling with Tensor Train approximations of Hamilton--Jacobi--Bellman equations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Claudia Schillings, David Sommer, Martin Eigel, Max Kirstein, Robert Gruhlke","submitted_at":"2024-02-23T12:30:20Z","abstract_excerpt":"Sampling from probability densities is a common challenge in fields such as Uncertainty Quantification (UQ) and Generative Modelling (GM). In GM in particular, the use of reverse-time diffusion processes depending on the log-densities of Ornstein-Uhlenbeck forward processes are a popular sampling tool. In Berner et al. [2022] the authors point out that these log-densities can be obtained by solution of a \\textit{Hamilton-Jacobi-Bellman} (HJB) equation known from stochastic optimal control. While this HJB equation is usually treated with indirect methods such as policy iteration and unsupervise"},"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":"2402.15285","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-02-23T12:30:20Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"c2d1240879feb4a692d5d4c40be6e4af9eec44aecd461cdddecaac6c81f06cea","abstract_canon_sha256":"7ddf7162aef9d5056782134a84005a9ae6fd30623c43ca9bef908cfc0500b6a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:38.705048Z","signature_b64":"uvIXnTUNe3gJfRBhy23OrViQRRGwdv9tQqCIrPQW3MYns8ItDzgILaQ/gjrLyfT8DkmpccgmgV4oYZbzmZVoCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"859eb2faa3741f703631cafdaa51dc0a1b75ceb5f9ec22790505954848ed7b61","last_reissued_at":"2026-07-05T07:48:38.704598Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:38.704598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Modelling with Tensor Train approximations of Hamilton--Jacobi--Bellman equations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Claudia Schillings, David Sommer, Martin Eigel, Max Kirstein, Robert Gruhlke","submitted_at":"2024-02-23T12:30:20Z","abstract_excerpt":"Sampling from probability densities is a common challenge in fields such as Uncertainty Quantification (UQ) and Generative Modelling (GM). In GM in particular, the use of reverse-time diffusion processes depending on the log-densities of Ornstein-Uhlenbeck forward processes are a popular sampling tool. In Berner et al. [2022] the authors point out that these log-densities can be obtained by solution of a \\textit{Hamilton-Jacobi-Bellman} (HJB) equation known from stochastic optimal control. While this HJB equation is usually treated with indirect methods such as policy iteration and unsupervise"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15285","kind":"arxiv","version":1},"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/2402.15285/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":"2402.15285","created_at":"2026-07-05T07:48:38.704659+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.15285v1","created_at":"2026-07-05T07:48:38.704659+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15285","created_at":"2026-07-05T07:48:38.704659+00:00"},{"alias_kind":"pith_short_12","alias_value":"QWPLF6VDOQPX","created_at":"2026-07-05T07:48:38.704659+00:00"},{"alias_kind":"pith_short_16","alias_value":"QWPLF6VDOQPXANRR","created_at":"2026-07-05T07:48:38.704659+00:00"},{"alias_kind":"pith_short_8","alias_value":"QWPLF6VD","created_at":"2026-07-05T07:48:38.704659+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.07762","citing_title":"Generative optimal transport via forward-backward HJB matching","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QWPLF6VDOQPXANRRZL62UUO4BI","json":"https://pith.science/pith/QWPLF6VDOQPXANRRZL62UUO4BI.json","graph_json":"https://pith.science/api/pith-number/QWPLF6VDOQPXANRRZL62UUO4BI/graph.json","events_json":"https://pith.science/api/pith-number/QWPLF6VDOQPXANRRZL62UUO4BI/events.json","paper":"https://pith.science/paper/QWPLF6VD"},"agent_actions":{"view_html":"https://pith.science/pith/QWPLF6VDOQPXANRRZL62UUO4BI","download_json":"https://pith.science/pith/QWPLF6VDOQPXANRRZL62UUO4BI.json","view_paper":"https://pith.science/paper/QWPLF6VD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.15285&json=true","fetch_graph":"https://pith.science/api/pith-number/QWPLF6VDOQPXANRRZL62UUO4BI/graph.json","fetch_events":"https://pith.science/api/pith-number/QWPLF6VDOQPXANRRZL62UUO4BI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QWPLF6VDOQPXANRRZL62UUO4BI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QWPLF6VDOQPXANRRZL62UUO4BI/action/storage_attestation","attest_author":"https://pith.science/pith/QWPLF6VDOQPXANRRZL62UUO4BI/action/author_attestation","sign_citation":"https://pith.science/pith/QWPLF6VDOQPXANRRZL62UUO4BI/action/citation_signature","submit_replication":"https://pith.science/pith/QWPLF6VDOQPXANRRZL62UUO4BI/action/replication_record"}},"created_at":"2026-07-05T07:48:38.704659+00:00","updated_at":"2026-07-05T07:48:38.704659+00:00"}