{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WEVAL5HS5L4DXXZY4EH2T7P6FT","short_pith_number":"pith:WEVAL5HS","schema_version":"1.0","canonical_sha256":"b12a05f4f2eaf83bdf38e10fa9fdfe2cde3489a364118c02093d759c98f7270d","source":{"kind":"arxiv","id":"2606.00293","version":1},"attestation_state":"computed","paper":{"title":"Accurate Large-sample Uncertainty Quantification using Stochastic Gradient Markov Chain Monte Carlo","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ME","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jie Ding, Jonathan H. Huggins, Yu Wang","submitted_at":"2026-05-29T19:24:38Z","abstract_excerpt":"Tuning algorithms such as stochastic gradient descent (SGD) and stochastic gradient Langevin dynamics (SGLD) for approximate sampling and uncertainty quantification remains challenging, particularly in the practically relevant settings when the batch size is large or the model is misspecified. Existing theory that provides tuning guidance relies on continuous-time limits or strong statistical assumptions, which can become quantitatively inaccurate in these regimes. We address these shortcomings by proposing new discrete-time approximations to SG(L)D with and without momentum, which enables acc"},"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":"2606.00293","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T19:24:38Z","cross_cats_sorted":["stat.ME","stat.ML"],"title_canon_sha256":"c8d2a5a3b26d754fe563bf8abb03ffc4dccd327e45aee2d336fae061a4d0688c","abstract_canon_sha256":"1172645c6cf03f97f0a9cdcf208eaed3f2b0b66511e4d2d7603e490c72faf822"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:50.867046Z","signature_b64":"ipZ9qWEHXPUNboBEoCYzfGraT8vdcBoZHCJlZsrEiLo1IdsUKQvkkeO4NKMCQCh2mX60/cdYUglCRX2Hg9ZCBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b12a05f4f2eaf83bdf38e10fa9fdfe2cde3489a364118c02093d759c98f7270d","last_reissued_at":"2026-06-02T01:03:50.866614Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:50.866614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accurate Large-sample Uncertainty Quantification using Stochastic Gradient Markov Chain Monte Carlo","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ME","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jie Ding, Jonathan H. Huggins, Yu Wang","submitted_at":"2026-05-29T19:24:38Z","abstract_excerpt":"Tuning algorithms such as stochastic gradient descent (SGD) and stochastic gradient Langevin dynamics (SGLD) for approximate sampling and uncertainty quantification remains challenging, particularly in the practically relevant settings when the batch size is large or the model is misspecified. Existing theory that provides tuning guidance relies on continuous-time limits or strong statistical assumptions, which can become quantitatively inaccurate in these regimes. We address these shortcomings by proposing new discrete-time approximations to SG(L)D with and without momentum, which enables acc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00293","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/2606.00293/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":"2606.00293","created_at":"2026-06-02T01:03:50.866668+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00293v1","created_at":"2026-06-02T01:03:50.866668+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00293","created_at":"2026-06-02T01:03:50.866668+00:00"},{"alias_kind":"pith_short_12","alias_value":"WEVAL5HS5L4D","created_at":"2026-06-02T01:03:50.866668+00:00"},{"alias_kind":"pith_short_16","alias_value":"WEVAL5HS5L4DXXZY","created_at":"2026-06-02T01:03:50.866668+00:00"},{"alias_kind":"pith_short_8","alias_value":"WEVAL5HS","created_at":"2026-06-02T01:03:50.866668+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/WEVAL5HS5L4DXXZY4EH2T7P6FT","json":"https://pith.science/pith/WEVAL5HS5L4DXXZY4EH2T7P6FT.json","graph_json":"https://pith.science/api/pith-number/WEVAL5HS5L4DXXZY4EH2T7P6FT/graph.json","events_json":"https://pith.science/api/pith-number/WEVAL5HS5L4DXXZY4EH2T7P6FT/events.json","paper":"https://pith.science/paper/WEVAL5HS"},"agent_actions":{"view_html":"https://pith.science/pith/WEVAL5HS5L4DXXZY4EH2T7P6FT","download_json":"https://pith.science/pith/WEVAL5HS5L4DXXZY4EH2T7P6FT.json","view_paper":"https://pith.science/paper/WEVAL5HS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00293&json=true","fetch_graph":"https://pith.science/api/pith-number/WEVAL5HS5L4DXXZY4EH2T7P6FT/graph.json","fetch_events":"https://pith.science/api/pith-number/WEVAL5HS5L4DXXZY4EH2T7P6FT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WEVAL5HS5L4DXXZY4EH2T7P6FT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WEVAL5HS5L4DXXZY4EH2T7P6FT/action/storage_attestation","attest_author":"https://pith.science/pith/WEVAL5HS5L4DXXZY4EH2T7P6FT/action/author_attestation","sign_citation":"https://pith.science/pith/WEVAL5HS5L4DXXZY4EH2T7P6FT/action/citation_signature","submit_replication":"https://pith.science/pith/WEVAL5HS5L4DXXZY4EH2T7P6FT/action/replication_record"}},"created_at":"2026-06-02T01:03:50.866668+00:00","updated_at":"2026-06-02T01:03:50.866668+00:00"}