{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SQGDUD6AD2HRE347EFSFNFE7BZ","short_pith_number":"pith:SQGDUD6A","canonical_record":{"source":{"id":"2503.00699","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-02T02:42:50Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"67adc4dc7621e7e05ec9b4208c1bbc627af6ea0f23331bd31488875376bf1ad9","abstract_canon_sha256":"8c3c2a1195b34b4499727c0c09ca4470595f1fe62a3dadab6642d0c40e5971b6"},"schema_version":"1.0"},"canonical_sha256":"940c3a0fc01e8f126f9f216456949f0e46d62b39b2ba1b146e151cfa3e120577","source":{"kind":"arxiv","id":"2503.00699","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.00699","created_at":"2026-07-05T10:22:27Z"},{"alias_kind":"arxiv_version","alias_value":"2503.00699v1","created_at":"2026-07-05T10:22:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00699","created_at":"2026-07-05T10:22:27Z"},{"alias_kind":"pith_short_12","alias_value":"SQGDUD6AD2HR","created_at":"2026-07-05T10:22:27Z"},{"alias_kind":"pith_short_16","alias_value":"SQGDUD6AD2HRE347","created_at":"2026-07-05T10:22:27Z"},{"alias_kind":"pith_short_8","alias_value":"SQGDUD6A","created_at":"2026-07-05T10:22:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SQGDUD6AD2HRE347EFSFNFE7BZ","target":"record","payload":{"canonical_record":{"source":{"id":"2503.00699","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-02T02:42:50Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"67adc4dc7621e7e05ec9b4208c1bbc627af6ea0f23331bd31488875376bf1ad9","abstract_canon_sha256":"8c3c2a1195b34b4499727c0c09ca4470595f1fe62a3dadab6642d0c40e5971b6"},"schema_version":"1.0"},"canonical_sha256":"940c3a0fc01e8f126f9f216456949f0e46d62b39b2ba1b146e151cfa3e120577","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:27.668994Z","signature_b64":"98pRTbq7uycMl3WVoW4z4Taz98qnt9nqM8dpUuN6ccjxYldOexypZlRT1LKK+cx3A0yFgMcj8mUEDr9U0/jkCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"940c3a0fc01e8f126f9f216456949f0e46d62b39b2ba1b146e151cfa3e120577","last_reissued_at":"2026-07-05T10:22:27.668567Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:27.668567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.00699","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:22:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"niBthR6q+armDH7XUD/uSG01jExpyYo+cHdJrmCT4U0C0htUlwHdsKED+MNBz6Ek55WbI5/jPkFPK7537rFTDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T23:49:09.616696Z"},"content_sha256":"3112be9ba89267a3d9984e8dccea6b0237fa5ac73bf2b48f535e8ccd152368e9","schema_version":"1.0","event_id":"sha256:3112be9ba89267a3d9984e8dccea6b0237fa5ac73bf2b48f535e8ccd152368e9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SQGDUD6AD2HRE347EFSFNFE7BZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Parameter Expanded Stochastic Gradient Markov Chain Monte Carlo","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chulhee Yun, Giung Nam, Hongseok Yang, Hyunsu Kim, Juho Lee","submitted_at":"2025-03-02T02:42:50Z","abstract_excerpt":"Bayesian Neural Networks (BNNs) provide a promising framework for modeling predictive uncertainty and enhancing out-of-distribution robustness (OOD) by estimating the posterior distribution of network parameters. Stochastic Gradient Markov Chain Monte Carlo (SGMCMC) is one of the most powerful methods for scalable posterior sampling in BNNs, achieving efficiency by combining stochastic gradient descent with second-order Langevin dynamics. However, SGMCMC often suffers from limited sample diversity in practice, which affects uncertainty estimation and model performance. We propose a simple yet "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00699","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/2503.00699/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":"2026-07-05T10:22:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GvKo0kZzrkCqaFgr4zUBmlvGwr9Hd3bNYzGXmWK5LN/0f3IT1z0w/205n5blJkaQpbUEvJzfyBz6BD0hcw5UDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T23:49:09.617265Z"},"content_sha256":"3b01943d0a956940be190bb872840c3d76bbb2ae456e97c52c080c5245b613cd","schema_version":"1.0","event_id":"sha256:3b01943d0a956940be190bb872840c3d76bbb2ae456e97c52c080c5245b613cd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SQGDUD6AD2HRE347EFSFNFE7BZ/bundle.json","state_url":"https://pith.science/pith/SQGDUD6AD2HRE347EFSFNFE7BZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SQGDUD6AD2HRE347EFSFNFE7BZ/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":"2026-08-06T23:49:09Z","links":{"resolver":"https://pith.science/pith/SQGDUD6AD2HRE347EFSFNFE7BZ","bundle":"https://pith.science/pith/SQGDUD6AD2HRE347EFSFNFE7BZ/bundle.json","state":"https://pith.science/pith/SQGDUD6AD2HRE347EFSFNFE7BZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SQGDUD6AD2HRE347EFSFNFE7BZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SQGDUD6AD2HRE347EFSFNFE7BZ","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":"8c3c2a1195b34b4499727c0c09ca4470595f1fe62a3dadab6642d0c40e5971b6","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-02T02:42:50Z","title_canon_sha256":"67adc4dc7621e7e05ec9b4208c1bbc627af6ea0f23331bd31488875376bf1ad9"},"schema_version":"1.0","source":{"id":"2503.00699","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.00699","created_at":"2026-07-05T10:22:27Z"},{"alias_kind":"arxiv_version","alias_value":"2503.00699v1","created_at":"2026-07-05T10:22:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00699","created_at":"2026-07-05T10:22:27Z"},{"alias_kind":"pith_short_12","alias_value":"SQGDUD6AD2HR","created_at":"2026-07-05T10:22:27Z"},{"alias_kind":"pith_short_16","alias_value":"SQGDUD6AD2HRE347","created_at":"2026-07-05T10:22:27Z"},{"alias_kind":"pith_short_8","alias_value":"SQGDUD6A","created_at":"2026-07-05T10:22:27Z"}],"graph_snapshots":[{"event_id":"sha256:3b01943d0a956940be190bb872840c3d76bbb2ae456e97c52c080c5245b613cd","target":"graph","created_at":"2026-07-05T10:22:27Z","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/2503.00699/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Bayesian Neural Networks (BNNs) provide a promising framework for modeling predictive uncertainty and enhancing out-of-distribution robustness (OOD) by estimating the posterior distribution of network parameters. Stochastic Gradient Markov Chain Monte Carlo (SGMCMC) is one of the most powerful methods for scalable posterior sampling in BNNs, achieving efficiency by combining stochastic gradient descent with second-order Langevin dynamics. However, SGMCMC often suffers from limited sample diversity in practice, which affects uncertainty estimation and model performance. We propose a simple yet ","authors_text":"Chulhee Yun, Giung Nam, Hongseok Yang, Hyunsu Kim, Juho Lee","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-02T02:42:50Z","title":"Parameter Expanded Stochastic Gradient Markov Chain Monte Carlo"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00699","kind":"arxiv","version":1},"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":"sha256:3112be9ba89267a3d9984e8dccea6b0237fa5ac73bf2b48f535e8ccd152368e9","target":"record","created_at":"2026-07-05T10:22:27Z","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":"8c3c2a1195b34b4499727c0c09ca4470595f1fe62a3dadab6642d0c40e5971b6","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-02T02:42:50Z","title_canon_sha256":"67adc4dc7621e7e05ec9b4208c1bbc627af6ea0f23331bd31488875376bf1ad9"},"schema_version":"1.0","source":{"id":"2503.00699","kind":"arxiv","version":1}},"canonical_sha256":"940c3a0fc01e8f126f9f216456949f0e46d62b39b2ba1b146e151cfa3e120577","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"940c3a0fc01e8f126f9f216456949f0e46d62b39b2ba1b146e151cfa3e120577","first_computed_at":"2026-07-05T10:22:27.668567Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:22:27.668567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"98pRTbq7uycMl3WVoW4z4Taz98qnt9nqM8dpUuN6ccjxYldOexypZlRT1LKK+cx3A0yFgMcj8mUEDr9U0/jkCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:22:27.668994Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.00699","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3112be9ba89267a3d9984e8dccea6b0237fa5ac73bf2b48f535e8ccd152368e9","sha256:3b01943d0a956940be190bb872840c3d76bbb2ae456e97c52c080c5245b613cd"],"state_sha256":"0e39672ba93ea22e402d0459173359ff7e1c8f538df44e009097934b761d9202"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9/9xfKxc3vGrEtoaGsmQyuEJ6umrCaQq/aidiy5ygwd22AfnMM4PQxT+/Mo1/lzwVqVelsHifY+QyBFKiKPRBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T23:49:09.620807Z","bundle_sha256":"a196fcb836cccad9cbcdf24b8bfb2ec7b68ba86571cb50a4d4ba343a1c3a2791"}}