{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:V4LBBSO46BL2AENC45CU5B5CIV","short_pith_number":"pith:V4LBBSO4","schema_version":"1.0","canonical_sha256":"af1610c9dcf057a011a2e7454e87a2456dc20445f61053771b500bc18391c17f","source":{"kind":"arxiv","id":"2602.06500","version":2},"attestation_state":"computed","paper":{"title":"Can Microcanonical Langevin Dynamics Leverage Mini-Batch Gradient Noise?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"David R\\\"ugamer, Emanuel Sommer, Jakob Robnik, Kangning Diao, Uros Seljak","submitted_at":"2026-02-06T08:52:19Z","abstract_excerpt":"Scaling inference methods such as Markov chain Monte Carlo to high-dimensional models remains a central challenge in Bayesian deep learning. A promising recent proposal, microcanonical Langevin Monte Carlo, has shown state-of-the-art performance across a wide range of problems. However, its reliance on full-dataset gradients makes it prohibitively expensive for large-scale problems. This paper addresses a fundamental question: Can microcanonical dynamics effectively leverage mini-batch gradient noise? We provide the first systematic study of this problem, establishing a novel continuous-time t"},"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":"2602.06500","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-06T08:52:19Z","cross_cats_sorted":[],"title_canon_sha256":"fefc4b4c5709aa3ddea54127f68d769b544b872eb4f5f1f0193631f38191c1ae","abstract_canon_sha256":"c41cd9cc3216e461035cc233b73a69f43604cdedaaa46b6d7892a2a43eb56a04"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:22.364631Z","signature_b64":"4gvVgy35nm+5EdFBoqXnuaoPtKL8fJlWofGYQ10XqLOiMw7M5lRI+uyYa0mv8dNzlvqi8vroEi9eBW85McoZBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af1610c9dcf057a011a2e7454e87a2456dc20445f61053771b500bc18391c17f","last_reissued_at":"2026-05-21T01:04:22.363713Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:22.363713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Microcanonical Langevin Dynamics Leverage Mini-Batch Gradient Noise?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"David R\\\"ugamer, Emanuel Sommer, Jakob Robnik, Kangning Diao, Uros Seljak","submitted_at":"2026-02-06T08:52:19Z","abstract_excerpt":"Scaling inference methods such as Markov chain Monte Carlo to high-dimensional models remains a central challenge in Bayesian deep learning. A promising recent proposal, microcanonical Langevin Monte Carlo, has shown state-of-the-art performance across a wide range of problems. However, its reliance on full-dataset gradients makes it prohibitively expensive for large-scale problems. This paper addresses a fundamental question: Can microcanonical dynamics effectively leverage mini-batch gradient noise? We provide the first systematic study of this problem, establishing a novel continuous-time t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.06500","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/2602.06500/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":"2602.06500","created_at":"2026-05-21T01:04:22.363832+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.06500v2","created_at":"2026-05-21T01:04:22.363832+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.06500","created_at":"2026-05-21T01:04:22.363832+00:00"},{"alias_kind":"pith_short_12","alias_value":"V4LBBSO46BL2","created_at":"2026-05-21T01:04:22.363832+00:00"},{"alias_kind":"pith_short_16","alias_value":"V4LBBSO46BL2AENC","created_at":"2026-05-21T01:04:22.363832+00:00"},{"alias_kind":"pith_short_8","alias_value":"V4LBBSO4","created_at":"2026-05-21T01:04:22.363832+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V4LBBSO46BL2AENC45CU5B5CIV","json":"https://pith.science/pith/V4LBBSO46BL2AENC45CU5B5CIV.json","graph_json":"https://pith.science/api/pith-number/V4LBBSO46BL2AENC45CU5B5CIV/graph.json","events_json":"https://pith.science/api/pith-number/V4LBBSO46BL2AENC45CU5B5CIV/events.json","paper":"https://pith.science/paper/V4LBBSO4"},"agent_actions":{"view_html":"https://pith.science/pith/V4LBBSO46BL2AENC45CU5B5CIV","download_json":"https://pith.science/pith/V4LBBSO46BL2AENC45CU5B5CIV.json","view_paper":"https://pith.science/paper/V4LBBSO4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.06500&json=true","fetch_graph":"https://pith.science/api/pith-number/V4LBBSO46BL2AENC45CU5B5CIV/graph.json","fetch_events":"https://pith.science/api/pith-number/V4LBBSO46BL2AENC45CU5B5CIV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V4LBBSO46BL2AENC45CU5B5CIV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V4LBBSO46BL2AENC45CU5B5CIV/action/storage_attestation","attest_author":"https://pith.science/pith/V4LBBSO46BL2AENC45CU5B5CIV/action/author_attestation","sign_citation":"https://pith.science/pith/V4LBBSO46BL2AENC45CU5B5CIV/action/citation_signature","submit_replication":"https://pith.science/pith/V4LBBSO46BL2AENC45CU5B5CIV/action/replication_record"}},"created_at":"2026-05-21T01:04:22.363832+00:00","updated_at":"2026-05-21T01:04:22.363832+00:00"}