{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:SBCKMUFPBRJHGBHZIVTTHACJZL","short_pith_number":"pith:SBCKMUFP","schema_version":"1.0","canonical_sha256":"9044a650af0c527304f94567338049cadaf0ba9d438ab4fee5c555644a819422","source":{"kind":"arxiv","id":"1505.02827","version":1},"attestation_state":"computed","paper":{"title":"On Markov chain Monte Carlo methods for tall data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.CO","stat.ML"],"primary_cat":"stat.ME","authors_text":"Arnaud Doucet, Chris Holmes, R\\'emi Bardenet","submitted_at":"2015-05-11T22:51:02Z","abstract_excerpt":"Markov chain Monte Carlo methods are often deemed too computationally intensive to be of any practical use for big data applications, and in particular for inference on datasets containing a large number $n$ of individual data points, also known as tall datasets. In scenarios where data are assumed independent, various approaches to scale up the Metropolis-Hastings algorithm in a Bayesian inference context have been recently proposed in machine learning and computational statistics. These approaches can be grouped into two categories: divide-and-conquer approaches and, subsampling-based algori"},"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":"1505.02827","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2015-05-11T22:51:02Z","cross_cats_sorted":["stat.CO","stat.ML"],"title_canon_sha256":"4fcf6fd582afe5e17da40cf2e5b24d330e4b2d140f9c721a7b9e0a679cdc2e3d","abstract_canon_sha256":"df6aeedc18562fad9057db68f313c9dc4d34e1881d921d816ea8632895bbf354"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:14:15.940469Z","signature_b64":"izUcCN0Tb+nBVcBNEkmKhuBVq3hHBIcoSDx+hGIxAv9OI8tRF0M/X/uxcIE3BxJTgNB8Gb4bqqbk6FTqoRlmAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9044a650af0c527304f94567338049cadaf0ba9d438ab4fee5c555644a819422","last_reissued_at":"2026-05-18T02:14:15.939757Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:14:15.939757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Markov chain Monte Carlo methods for tall data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.CO","stat.ML"],"primary_cat":"stat.ME","authors_text":"Arnaud Doucet, Chris Holmes, R\\'emi Bardenet","submitted_at":"2015-05-11T22:51:02Z","abstract_excerpt":"Markov chain Monte Carlo methods are often deemed too computationally intensive to be of any practical use for big data applications, and in particular for inference on datasets containing a large number $n$ of individual data points, also known as tall datasets. In scenarios where data are assumed independent, various approaches to scale up the Metropolis-Hastings algorithm in a Bayesian inference context have been recently proposed in machine learning and computational statistics. These approaches can be grouped into two categories: divide-and-conquer approaches and, subsampling-based algori"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1505.02827","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":"1505.02827","created_at":"2026-05-18T02:14:15.939880+00:00"},{"alias_kind":"arxiv_version","alias_value":"1505.02827v1","created_at":"2026-05-18T02:14:15.939880+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1505.02827","created_at":"2026-05-18T02:14:15.939880+00:00"},{"alias_kind":"pith_short_12","alias_value":"SBCKMUFPBRJH","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_16","alias_value":"SBCKMUFPBRJHGBHZ","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_8","alias_value":"SBCKMUFP","created_at":"2026-05-18T12:29:39.896362+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.13127","citing_title":"State-of-art minibatches via novel DPP kernels: discretization, wavelets, and rough objectives","ref_index":257,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SBCKMUFPBRJHGBHZIVTTHACJZL","json":"https://pith.science/pith/SBCKMUFPBRJHGBHZIVTTHACJZL.json","graph_json":"https://pith.science/api/pith-number/SBCKMUFPBRJHGBHZIVTTHACJZL/graph.json","events_json":"https://pith.science/api/pith-number/SBCKMUFPBRJHGBHZIVTTHACJZL/events.json","paper":"https://pith.science/paper/SBCKMUFP"},"agent_actions":{"view_html":"https://pith.science/pith/SBCKMUFPBRJHGBHZIVTTHACJZL","download_json":"https://pith.science/pith/SBCKMUFPBRJHGBHZIVTTHACJZL.json","view_paper":"https://pith.science/paper/SBCKMUFP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1505.02827&json=true","fetch_graph":"https://pith.science/api/pith-number/SBCKMUFPBRJHGBHZIVTTHACJZL/graph.json","fetch_events":"https://pith.science/api/pith-number/SBCKMUFPBRJHGBHZIVTTHACJZL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SBCKMUFPBRJHGBHZIVTTHACJZL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SBCKMUFPBRJHGBHZIVTTHACJZL/action/storage_attestation","attest_author":"https://pith.science/pith/SBCKMUFPBRJHGBHZIVTTHACJZL/action/author_attestation","sign_citation":"https://pith.science/pith/SBCKMUFPBRJHGBHZIVTTHACJZL/action/citation_signature","submit_replication":"https://pith.science/pith/SBCKMUFPBRJHGBHZIVTTHACJZL/action/replication_record"}},"created_at":"2026-05-18T02:14:15.939880+00:00","updated_at":"2026-05-18T02:14:15.939880+00:00"}