{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:V4LBBSO46BL2AENC45CU5B5CIV","short_pith_number":"pith:V4LBBSO4","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"},"canonical_sha256":"af1610c9dcf057a011a2e7454e87a2456dc20445f61053771b500bc18391c17f","source":{"kind":"arxiv","id":"2602.06500","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.06500","created_at":"2026-05-21T01:04:22Z"},{"alias_kind":"arxiv_version","alias_value":"2602.06500v2","created_at":"2026-05-21T01:04:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.06500","created_at":"2026-05-21T01:04:22Z"},{"alias_kind":"pith_short_12","alias_value":"V4LBBSO46BL2","created_at":"2026-05-21T01:04:22Z"},{"alias_kind":"pith_short_16","alias_value":"V4LBBSO46BL2AENC","created_at":"2026-05-21T01:04:22Z"},{"alias_kind":"pith_short_8","alias_value":"V4LBBSO4","created_at":"2026-05-21T01:04:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:V4LBBSO46BL2AENC45CU5B5CIV","target":"record","payload":{"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"},"canonical_sha256":"af1610c9dcf057a011a2e7454e87a2456dc20445f61053771b500bc18391c17f","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"},"source_kind":"arxiv","source_id":"2602.06500","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T01:04:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TrXh9meNOURuRTSilpBH0eIZcOzx4tO6eF1rKrClllsOIo0MZlhU2//0UX8PHtr/Qhb4vx2o8RKvfTpRMsWdDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T17:21:07.814620Z"},"content_sha256":"1b4f06dcd5822f24082d2c375ef0cf193c884071b09b8417278ab35dfc56e7fd","schema_version":"1.0","event_id":"sha256:1b4f06dcd5822f24082d2c375ef0cf193c884071b09b8417278ab35dfc56e7fd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:V4LBBSO46BL2AENC45CU5B5CIV","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T01:04:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nDFactdBfhHm8jWzWhHiN2HkapOSxmOZzBWoR40SAhg1WJOYDrgpt4Sxo6kYXbj8iVrOmoy/AD5h/CGpRvOpBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T17:21:07.814992Z"},"content_sha256":"0025bc17177aa2b692b685a7a8312eb590e4bf07c612ea8b2cabaf201fbd93e8","schema_version":"1.0","event_id":"sha256:0025bc17177aa2b692b685a7a8312eb590e4bf07c612ea8b2cabaf201fbd93e8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V4LBBSO46BL2AENC45CU5B5CIV/bundle.json","state_url":"https://pith.science/pith/V4LBBSO46BL2AENC45CU5B5CIV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V4LBBSO46BL2AENC45CU5B5CIV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-30T17:21:07Z","links":{"resolver":"https://pith.science/pith/V4LBBSO46BL2AENC45CU5B5CIV","bundle":"https://pith.science/pith/V4LBBSO46BL2AENC45CU5B5CIV/bundle.json","state":"https://pith.science/pith/V4LBBSO46BL2AENC45CU5B5CIV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V4LBBSO46BL2AENC45CU5B5CIV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:V4LBBSO46BL2AENC45CU5B5CIV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c41cd9cc3216e461035cc233b73a69f43604cdedaaa46b6d7892a2a43eb56a04","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-06T08:52:19Z","title_canon_sha256":"fefc4b4c5709aa3ddea54127f68d769b544b872eb4f5f1f0193631f38191c1ae"},"schema_version":"1.0","source":{"id":"2602.06500","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.06500","created_at":"2026-05-21T01:04:22Z"},{"alias_kind":"arxiv_version","alias_value":"2602.06500v2","created_at":"2026-05-21T01:04:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.06500","created_at":"2026-05-21T01:04:22Z"},{"alias_kind":"pith_short_12","alias_value":"V4LBBSO46BL2","created_at":"2026-05-21T01:04:22Z"},{"alias_kind":"pith_short_16","alias_value":"V4LBBSO46BL2AENC","created_at":"2026-05-21T01:04:22Z"},{"alias_kind":"pith_short_8","alias_value":"V4LBBSO4","created_at":"2026-05-21T01:04:22Z"}],"graph_snapshots":[{"event_id":"sha256:0025bc17177aa2b692b685a7a8312eb590e4bf07c612ea8b2cabaf201fbd93e8","target":"graph","created_at":"2026-05-21T01:04:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2602.06500/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"David R\\\"ugamer, Emanuel Sommer, Jakob Robnik, Kangning Diao, Uros Seljak","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-06T08:52:19Z","title":"Can Microcanonical Langevin Dynamics Leverage Mini-Batch Gradient Noise?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.06500","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1b4f06dcd5822f24082d2c375ef0cf193c884071b09b8417278ab35dfc56e7fd","target":"record","created_at":"2026-05-21T01:04:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c41cd9cc3216e461035cc233b73a69f43604cdedaaa46b6d7892a2a43eb56a04","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-06T08:52:19Z","title_canon_sha256":"fefc4b4c5709aa3ddea54127f68d769b544b872eb4f5f1f0193631f38191c1ae"},"schema_version":"1.0","source":{"id":"2602.06500","kind":"arxiv","version":2}},"canonical_sha256":"af1610c9dcf057a011a2e7454e87a2456dc20445f61053771b500bc18391c17f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af1610c9dcf057a011a2e7454e87a2456dc20445f61053771b500bc18391c17f","first_computed_at":"2026-05-21T01:04:22.363713Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:22.363713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4gvVgy35nm+5EdFBoqXnuaoPtKL8fJlWofGYQ10XqLOiMw7M5lRI+uyYa0mv8dNzlvqi8vroEi9eBW85McoZBw==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:22.364631Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.06500","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1b4f06dcd5822f24082d2c375ef0cf193c884071b09b8417278ab35dfc56e7fd","sha256:0025bc17177aa2b692b685a7a8312eb590e4bf07c612ea8b2cabaf201fbd93e8"],"state_sha256":"0dc22c98e02addfa326abc93fd9df8f9939caa356698ed4e0a18292ba2764d4b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vSicJ4CcQfe+O6GtzN7PBQ6Z9vFM5p8Vr/CQP1l/fAsI4trQasniy6ewmos6HPlfZmGb7xsnKox5ClTJMjywCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T17:21:07.817239Z","bundle_sha256":"4fae5096584bb82b633439108d7997f059733bb60adc357d18fdf0c663cf827e"}}