{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WEDNS5PUKNXJIUQSYYWK7TDOCR","short_pith_number":"pith:WEDNS5PU","schema_version":"1.0","canonical_sha256":"b106d975f4536e945212c62cafcc6e14431e55255d0b280c0ee7e316f253288a","source":{"kind":"arxiv","id":"2504.18911","version":2},"attestation_state":"computed","paper":{"title":"A Langevin sampling algorithm inspired by the Adam optimizer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"stat.CO","authors_text":"Benedict Leimkuhler, Peter Whalley, Ren\\'e Lohmann","submitted_at":"2025-04-26T12:57:57Z","abstract_excerpt":"We present a framework for adaptive-stepsize MCMC sampling based on time-rescaled Langevin dynamics, in which the stepsize variation is dynamically driven by an additional degree of freedom. Our approach augments the phase space by an additional variable which in turn defines a time reparameterization. The use of an auxiliary relaxation equation allows accumulation of a moving average of a local monitor function and provides for precise control of the timestep while circumventing the need to modify the drift term in the physical system. Our algorithm is straightforward to implement and can be "},"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":"2504.18911","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2025-04-26T12:57:57Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"fd7a395eb3dd712132b26103e3c86e66e3a75a0dd13cb6ad6f89352e1e2ca55d","abstract_canon_sha256":"7c5f1558a9c8dbf0260a566dd719a54456f1775815ab88e5da5132abda5b69c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:46.636651Z","signature_b64":"t0VD0B0D9JtEbmIwWzOWJIqJjeTW4s3senTOl2Db7MqZaJLaTY8rX8CQmylaFlSqoXIurwkLVqI3eoAepBvbBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b106d975f4536e945212c62cafcc6e14431e55255d0b280c0ee7e316f253288a","last_reissued_at":"2026-07-05T11:09:46.636211Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:46.636211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Langevin sampling algorithm inspired by the Adam optimizer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"stat.CO","authors_text":"Benedict Leimkuhler, Peter Whalley, Ren\\'e Lohmann","submitted_at":"2025-04-26T12:57:57Z","abstract_excerpt":"We present a framework for adaptive-stepsize MCMC sampling based on time-rescaled Langevin dynamics, in which the stepsize variation is dynamically driven by an additional degree of freedom. Our approach augments the phase space by an additional variable which in turn defines a time reparameterization. The use of an auxiliary relaxation equation allows accumulation of a moving average of a local monitor function and provides for precise control of the timestep while circumventing the need to modify the drift term in the physical system. Our algorithm is straightforward to implement and can be "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.18911","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/2504.18911/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":"2504.18911","created_at":"2026-07-05T11:09:46.636274+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.18911v2","created_at":"2026-07-05T11:09:46.636274+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.18911","created_at":"2026-07-05T11:09:46.636274+00:00"},{"alias_kind":"pith_short_12","alias_value":"WEDNS5PUKNXJ","created_at":"2026-07-05T11:09:46.636274+00:00"},{"alias_kind":"pith_short_16","alias_value":"WEDNS5PUKNXJIUQS","created_at":"2026-07-05T11:09:46.636274+00:00"},{"alias_kind":"pith_short_8","alias_value":"WEDNS5PU","created_at":"2026-07-05T11:09:46.636274+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.21765","citing_title":"Position: The Time for Sampling Is Now! Charting a New Course for Bayesian Deep Learning","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WEDNS5PUKNXJIUQSYYWK7TDOCR","json":"https://pith.science/pith/WEDNS5PUKNXJIUQSYYWK7TDOCR.json","graph_json":"https://pith.science/api/pith-number/WEDNS5PUKNXJIUQSYYWK7TDOCR/graph.json","events_json":"https://pith.science/api/pith-number/WEDNS5PUKNXJIUQSYYWK7TDOCR/events.json","paper":"https://pith.science/paper/WEDNS5PU"},"agent_actions":{"view_html":"https://pith.science/pith/WEDNS5PUKNXJIUQSYYWK7TDOCR","download_json":"https://pith.science/pith/WEDNS5PUKNXJIUQSYYWK7TDOCR.json","view_paper":"https://pith.science/paper/WEDNS5PU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.18911&json=true","fetch_graph":"https://pith.science/api/pith-number/WEDNS5PUKNXJIUQSYYWK7TDOCR/graph.json","fetch_events":"https://pith.science/api/pith-number/WEDNS5PUKNXJIUQSYYWK7TDOCR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WEDNS5PUKNXJIUQSYYWK7TDOCR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WEDNS5PUKNXJIUQSYYWK7TDOCR/action/storage_attestation","attest_author":"https://pith.science/pith/WEDNS5PUKNXJIUQSYYWK7TDOCR/action/author_attestation","sign_citation":"https://pith.science/pith/WEDNS5PUKNXJIUQSYYWK7TDOCR/action/citation_signature","submit_replication":"https://pith.science/pith/WEDNS5PUKNXJIUQSYYWK7TDOCR/action/replication_record"}},"created_at":"2026-07-05T11:09:46.636274+00:00","updated_at":"2026-07-05T11:09:46.636274+00:00"}