{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GVTM6IZCVA6RHDZR6BHYBXDUUX","short_pith_number":"pith:GVTM6IZC","schema_version":"1.0","canonical_sha256":"3566cf2322a83d138f31f04f80dc74a5f0185ff7555eca432f06a370acb5ddd8","source":{"kind":"arxiv","id":"2312.14027","version":3},"attestation_state":"computed","paper":{"title":"AdamMCMC: Combining Metropolis Adjusted Langevin with Momentum-based Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","hep-ph","stat.CO"],"primary_cat":"stat.ML","authors_text":"Gregor Kasieczka, Mathias Trabs, Maximilian F. Steffen, Sebastian Bieringer","submitted_at":"2023-12-21T16:58:49Z","abstract_excerpt":"Uncertainty estimation is a key issue when considering the application of deep neural network methods in science and engineering. In this work, we introduce a novel algorithm that quantifies epistemic uncertainty via Monte Carlo sampling from a tempered posterior distribution. It combines the well established Metropolis Adjusted Langevin Algorithm (MALA) with momentum-based optimization using Adam and leverages a prolate proposal distribution, to efficiently draw from the posterior. We prove that the constructed chain admits the Gibbs posterior as invariant distribution and approximates this p"},"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":"2312.14027","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-12-21T16:58:49Z","cross_cats_sorted":["cs.LG","hep-ph","stat.CO"],"title_canon_sha256":"a54626db8fa34fa05cd42517d34a8cbc473e809caa3ef0410a009cb2a656d7f5","abstract_canon_sha256":"0fa593ddf8374051623c840ab7dccfbe85598d2dd864eed2869bd62b23174812"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:49.181053Z","signature_b64":"euaqGV+XWAyyc1pKvp0KHq7aglmVmbW/PXwTd9/l0igj+Bfwo5VPs9sEYyp8SjAkbcf1l9DUhwe80RCuyNnvAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3566cf2322a83d138f31f04f80dc74a5f0185ff7555eca432f06a370acb5ddd8","last_reissued_at":"2026-07-05T09:44:49.180563Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:49.180563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AdamMCMC: Combining Metropolis Adjusted Langevin with Momentum-based Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","hep-ph","stat.CO"],"primary_cat":"stat.ML","authors_text":"Gregor Kasieczka, Mathias Trabs, Maximilian F. Steffen, Sebastian Bieringer","submitted_at":"2023-12-21T16:58:49Z","abstract_excerpt":"Uncertainty estimation is a key issue when considering the application of deep neural network methods in science and engineering. In this work, we introduce a novel algorithm that quantifies epistemic uncertainty via Monte Carlo sampling from a tempered posterior distribution. It combines the well established Metropolis Adjusted Langevin Algorithm (MALA) with momentum-based optimization using Adam and leverages a prolate proposal distribution, to efficiently draw from the posterior. We prove that the constructed chain admits the Gibbs posterior as invariant distribution and approximates this p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.14027","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/2312.14027/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":"2312.14027","created_at":"2026-07-05T09:44:49.180621+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.14027v3","created_at":"2026-07-05T09:44:49.180621+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14027","created_at":"2026-07-05T09:44:49.180621+00:00"},{"alias_kind":"pith_short_12","alias_value":"GVTM6IZCVA6R","created_at":"2026-07-05T09:44:49.180621+00:00"},{"alias_kind":"pith_short_16","alias_value":"GVTM6IZCVA6RHDZR","created_at":"2026-07-05T09:44:49.180621+00:00"},{"alias_kind":"pith_short_8","alias_value":"GVTM6IZC","created_at":"2026-07-05T09:44:49.180621+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11170","citing_title":"Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data","ref_index":123,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GVTM6IZCVA6RHDZR6BHYBXDUUX","json":"https://pith.science/pith/GVTM6IZCVA6RHDZR6BHYBXDUUX.json","graph_json":"https://pith.science/api/pith-number/GVTM6IZCVA6RHDZR6BHYBXDUUX/graph.json","events_json":"https://pith.science/api/pith-number/GVTM6IZCVA6RHDZR6BHYBXDUUX/events.json","paper":"https://pith.science/paper/GVTM6IZC"},"agent_actions":{"view_html":"https://pith.science/pith/GVTM6IZCVA6RHDZR6BHYBXDUUX","download_json":"https://pith.science/pith/GVTM6IZCVA6RHDZR6BHYBXDUUX.json","view_paper":"https://pith.science/paper/GVTM6IZC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.14027&json=true","fetch_graph":"https://pith.science/api/pith-number/GVTM6IZCVA6RHDZR6BHYBXDUUX/graph.json","fetch_events":"https://pith.science/api/pith-number/GVTM6IZCVA6RHDZR6BHYBXDUUX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GVTM6IZCVA6RHDZR6BHYBXDUUX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GVTM6IZCVA6RHDZR6BHYBXDUUX/action/storage_attestation","attest_author":"https://pith.science/pith/GVTM6IZCVA6RHDZR6BHYBXDUUX/action/author_attestation","sign_citation":"https://pith.science/pith/GVTM6IZCVA6RHDZR6BHYBXDUUX/action/citation_signature","submit_replication":"https://pith.science/pith/GVTM6IZCVA6RHDZR6BHYBXDUUX/action/replication_record"}},"created_at":"2026-07-05T09:44:49.180621+00:00","updated_at":"2026-07-05T09:44:49.180621+00:00"}