{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:APHP5P62B5H4AKWIWYL6LXOE66","short_pith_number":"pith:APHP5P62","schema_version":"1.0","canonical_sha256":"03cefebfda0f4fc02ac8b617e5ddc4f79766812173a3ef61c0fb35a769ee80ba","source":{"kind":"arxiv","id":"2009.09535","version":1},"attestation_state":"computed","paper":{"title":"Stochastic Gradient Langevin Dynamics Algorithms with Adaptive Drifts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Faming Liang, Qifan Song, Sehwan Kim","submitted_at":"2020-09-20T22:03:39Z","abstract_excerpt":"Bayesian deep learning offers a principled way to address many issues concerning safety of artificial intelligence (AI), such as model uncertainty,model interpretability, and prediction bias. However, due to the lack of efficient Monte Carlo algorithms for sampling from the posterior of deep neural networks (DNNs), Bayesian deep learning has not yet powered our AI system. We propose a class of adaptive stochastic gradient Markov chain Monte Carlo (SGMCMC) algorithms, where the drift function is biased to enhance escape from saddle points and the bias is adaptively adjusted according to the gra"},"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":"2009.09535","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-09-20T22:03:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b5bb13fa521a8655acf41c6fe07139c248f7b7e39e673088ca10ee7d9a924234","abstract_canon_sha256":"f4445c466e064668e24622b74652b9143f0b0990c8e5e6614e8eabf784ddfe14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:36:41.623526Z","signature_b64":"cARrGOVlvlrTi3dOjTlN7+Xm9XJ9ojJ4Ux+DZkdNTamIPNQNprWACK3+FjIQfgOlP3VCVpJH+BF4Jh+TogJTCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03cefebfda0f4fc02ac8b617e5ddc4f79766812173a3ef61c0fb35a769ee80ba","last_reissued_at":"2026-07-05T01:36:41.623116Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:36:41.623116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Gradient Langevin Dynamics Algorithms with Adaptive Drifts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Faming Liang, Qifan Song, Sehwan Kim","submitted_at":"2020-09-20T22:03:39Z","abstract_excerpt":"Bayesian deep learning offers a principled way to address many issues concerning safety of artificial intelligence (AI), such as model uncertainty,model interpretability, and prediction bias. However, due to the lack of efficient Monte Carlo algorithms for sampling from the posterior of deep neural networks (DNNs), Bayesian deep learning has not yet powered our AI system. We propose a class of adaptive stochastic gradient Markov chain Monte Carlo (SGMCMC) algorithms, where the drift function is biased to enhance escape from saddle points and the bias is adaptively adjusted according to the gra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.09535","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/2009.09535/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":"2009.09535","created_at":"2026-07-05T01:36:41.623177+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.09535v1","created_at":"2026-07-05T01:36:41.623177+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.09535","created_at":"2026-07-05T01:36:41.623177+00:00"},{"alias_kind":"pith_short_12","alias_value":"APHP5P62B5H4","created_at":"2026-07-05T01:36:41.623177+00:00"},{"alias_kind":"pith_short_16","alias_value":"APHP5P62B5H4AKWI","created_at":"2026-07-05T01:36:41.623177+00:00"},{"alias_kind":"pith_short_8","alias_value":"APHP5P62","created_at":"2026-07-05T01:36:41.623177+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23477","citing_title":"Sublinearly Structured Deep Neural Networks Achieve Feature Learning Consistency for Compositional Functions","ref_index":268,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14880","citing_title":"Denoising-GS: Gaussian Splatting with Spatial-aware Denoising","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/APHP5P62B5H4AKWIWYL6LXOE66","json":"https://pith.science/pith/APHP5P62B5H4AKWIWYL6LXOE66.json","graph_json":"https://pith.science/api/pith-number/APHP5P62B5H4AKWIWYL6LXOE66/graph.json","events_json":"https://pith.science/api/pith-number/APHP5P62B5H4AKWIWYL6LXOE66/events.json","paper":"https://pith.science/paper/APHP5P62"},"agent_actions":{"view_html":"https://pith.science/pith/APHP5P62B5H4AKWIWYL6LXOE66","download_json":"https://pith.science/pith/APHP5P62B5H4AKWIWYL6LXOE66.json","view_paper":"https://pith.science/paper/APHP5P62","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.09535&json=true","fetch_graph":"https://pith.science/api/pith-number/APHP5P62B5H4AKWIWYL6LXOE66/graph.json","fetch_events":"https://pith.science/api/pith-number/APHP5P62B5H4AKWIWYL6LXOE66/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/APHP5P62B5H4AKWIWYL6LXOE66/action/timestamp_anchor","attest_storage":"https://pith.science/pith/APHP5P62B5H4AKWIWYL6LXOE66/action/storage_attestation","attest_author":"https://pith.science/pith/APHP5P62B5H4AKWIWYL6LXOE66/action/author_attestation","sign_citation":"https://pith.science/pith/APHP5P62B5H4AKWIWYL6LXOE66/action/citation_signature","submit_replication":"https://pith.science/pith/APHP5P62B5H4AKWIWYL6LXOE66/action/replication_record"}},"created_at":"2026-07-05T01:36:41.623177+00:00","updated_at":"2026-07-05T01:36:41.623177+00:00"}