{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:X3GOQIQTUBVTU2BV4EBLKTK5I3","short_pith_number":"pith:X3GOQIQT","schema_version":"1.0","canonical_sha256":"becce82213a06b3a6835e102b54d5d46e1c0e9c2ec6bcce1427b26a74791329f","source":{"kind":"arxiv","id":"1712.09097","version":1},"attestation_state":"computed","paper":{"title":"On Connecting Stochastic Gradient MCMC and Differential Privacy","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Bai Li, Changyou Chen, Hao Liu, Lawrence Carin","submitted_at":"2017-12-25T16:29:44Z","abstract_excerpt":"Significant success has been realized recently on applying machine learning to real-world applications. There have also been corresponding concerns on the privacy of training data, which relates to data security and confidentiality issues. Differential privacy provides a principled and rigorous privacy guarantee on machine learning models. While it is common to design a model satisfying a required differential-privacy property by injecting noise, it is generally hard to balance the trade-off between privacy and utility. We show that stochastic gradient Markov chain Monte Carlo (SG-MCMC) -- a c"},"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":"1712.09097","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"stat.ML","submitted_at":"2017-12-25T16:29:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3e28e177a6cd77f638fa8cc4b7e708016e9b5940c761875f6c00574a314b8f43","abstract_canon_sha256":"72f7c1a6c14bd14928087087e4e77718ef5556b15258f2b0d9c3ae19ca515fa1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:27:14.428033Z","signature_b64":"fEJRHZzGtJdnt8Y80scEx1mufreVboFDuwS9Dszk2ffadQ77BFggsZQNnvoqu+4/Vom0FkzYHlPKof6owvj9Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"becce82213a06b3a6835e102b54d5d46e1c0e9c2ec6bcce1427b26a74791329f","last_reissued_at":"2026-05-18T00:27:14.427641Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:27:14.427641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Connecting Stochastic Gradient MCMC and Differential Privacy","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Bai Li, Changyou Chen, Hao Liu, Lawrence Carin","submitted_at":"2017-12-25T16:29:44Z","abstract_excerpt":"Significant success has been realized recently on applying machine learning to real-world applications. There have also been corresponding concerns on the privacy of training data, which relates to data security and confidentiality issues. Differential privacy provides a principled and rigorous privacy guarantee on machine learning models. While it is common to design a model satisfying a required differential-privacy property by injecting noise, it is generally hard to balance the trade-off between privacy and utility. We show that stochastic gradient Markov chain Monte Carlo (SG-MCMC) -- a c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.09097","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":""},"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":"1712.09097","created_at":"2026-05-18T00:27:14.427703+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.09097v1","created_at":"2026-05-18T00:27:14.427703+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.09097","created_at":"2026-05-18T00:27:14.427703+00:00"},{"alias_kind":"pith_short_12","alias_value":"X3GOQIQTUBVT","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_16","alias_value":"X3GOQIQTUBVTU2BV","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_8","alias_value":"X3GOQIQT","created_at":"2026-05-18T12:31:53.515858+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/X3GOQIQTUBVTU2BV4EBLKTK5I3","json":"https://pith.science/pith/X3GOQIQTUBVTU2BV4EBLKTK5I3.json","graph_json":"https://pith.science/api/pith-number/X3GOQIQTUBVTU2BV4EBLKTK5I3/graph.json","events_json":"https://pith.science/api/pith-number/X3GOQIQTUBVTU2BV4EBLKTK5I3/events.json","paper":"https://pith.science/paper/X3GOQIQT"},"agent_actions":{"view_html":"https://pith.science/pith/X3GOQIQTUBVTU2BV4EBLKTK5I3","download_json":"https://pith.science/pith/X3GOQIQTUBVTU2BV4EBLKTK5I3.json","view_paper":"https://pith.science/paper/X3GOQIQT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.09097&json=true","fetch_graph":"https://pith.science/api/pith-number/X3GOQIQTUBVTU2BV4EBLKTK5I3/graph.json","fetch_events":"https://pith.science/api/pith-number/X3GOQIQTUBVTU2BV4EBLKTK5I3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X3GOQIQTUBVTU2BV4EBLKTK5I3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X3GOQIQTUBVTU2BV4EBLKTK5I3/action/storage_attestation","attest_author":"https://pith.science/pith/X3GOQIQTUBVTU2BV4EBLKTK5I3/action/author_attestation","sign_citation":"https://pith.science/pith/X3GOQIQTUBVTU2BV4EBLKTK5I3/action/citation_signature","submit_replication":"https://pith.science/pith/X3GOQIQTUBVTU2BV4EBLKTK5I3/action/replication_record"}},"created_at":"2026-05-18T00:27:14.427703+00:00","updated_at":"2026-05-18T00:27:14.427703+00:00"}