{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XSUHAEUNM652L2X3XWZBPHY3FH","short_pith_number":"pith:XSUHAEUN","schema_version":"1.0","canonical_sha256":"bca870128d67bba5eafbbdb2179f1b29d5d3c079babb7e623c39204a67ee24d9","source":{"kind":"arxiv","id":"2202.00977","version":5},"attestation_state":"computed","paper":{"title":"HMC and underdamped Langevin united in the unadjusted convex smooth case","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.TH"],"primary_cat":"math.PR","authors_text":"Adrien Majka, Nicola\\\"i Gouraud, Pierre Le Bris, Pierre Monmarch\\'e","submitted_at":"2022-02-02T11:43:05Z","abstract_excerpt":"We consider a family of unadjusted generalized HMC samplers, which includes standard position HMC samplers and discretizations of the underdamped Langevin process. A detailed analysis and optimization of the parameters is conducted in the Gaussian case, which shows an improvement from $1/\\kappa$ to $1/\\sqrt{\\kappa}$ for the convergence rate in terms of the condition number $\\kappa$ by using partial velocity refreshment, with respect to classical full refreshments. A similar effect is observed empirically for two related algorithms, namely Metropolis-adjusted gHMC and kinetic piecewise-determin"},"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":"2202.00977","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.PR","submitted_at":"2022-02-02T11:43:05Z","cross_cats_sorted":["math.ST","stat.TH"],"title_canon_sha256":"3a018fbe54e106750bf3875b0c672bfaeec83758fb6dd4bc71df0e2e174de431","abstract_canon_sha256":"fdad9613fe459b1e4cf9908ee2185906475cfaac2268443dc3626655daebc64a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:21:35.719837Z","signature_b64":"AAwOnwW5J+cyHgyY3dQc3R7Ifz1K3Dvur/JMoh2w+x7pWjp6l9Cn/tZqL2pUtJJzzr2yFMUC18Phs8M9I18JCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bca870128d67bba5eafbbdb2179f1b29d5d3c079babb7e623c39204a67ee24d9","last_reissued_at":"2026-07-05T08:21:35.719357Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:21:35.719357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HMC and underdamped Langevin united in the unadjusted convex smooth case","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.TH"],"primary_cat":"math.PR","authors_text":"Adrien Majka, Nicola\\\"i Gouraud, Pierre Le Bris, Pierre Monmarch\\'e","submitted_at":"2022-02-02T11:43:05Z","abstract_excerpt":"We consider a family of unadjusted generalized HMC samplers, which includes standard position HMC samplers and discretizations of the underdamped Langevin process. A detailed analysis and optimization of the parameters is conducted in the Gaussian case, which shows an improvement from $1/\\kappa$ to $1/\\sqrt{\\kappa}$ for the convergence rate in terms of the condition number $\\kappa$ by using partial velocity refreshment, with respect to classical full refreshments. A similar effect is observed empirically for two related algorithms, namely Metropolis-adjusted gHMC and kinetic piecewise-determin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.00977","kind":"arxiv","version":5},"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/2202.00977/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":"2202.00977","created_at":"2026-07-05T08:21:35.719423+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.00977v5","created_at":"2026-07-05T08:21:35.719423+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.00977","created_at":"2026-07-05T08:21:35.719423+00:00"},{"alias_kind":"pith_short_12","alias_value":"XSUHAEUNM652","created_at":"2026-07-05T08:21:35.719423+00:00"},{"alias_kind":"pith_short_16","alias_value":"XSUHAEUNM652L2X3","created_at":"2026-07-05T08:21:35.719423+00:00"},{"alias_kind":"pith_short_8","alias_value":"XSUHAEUN","created_at":"2026-07-05T08:21:35.719423+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.04082","citing_title":"Adaptive tuning of Hamiltonian Monte Carlo methods","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XSUHAEUNM652L2X3XWZBPHY3FH","json":"https://pith.science/pith/XSUHAEUNM652L2X3XWZBPHY3FH.json","graph_json":"https://pith.science/api/pith-number/XSUHAEUNM652L2X3XWZBPHY3FH/graph.json","events_json":"https://pith.science/api/pith-number/XSUHAEUNM652L2X3XWZBPHY3FH/events.json","paper":"https://pith.science/paper/XSUHAEUN"},"agent_actions":{"view_html":"https://pith.science/pith/XSUHAEUNM652L2X3XWZBPHY3FH","download_json":"https://pith.science/pith/XSUHAEUNM652L2X3XWZBPHY3FH.json","view_paper":"https://pith.science/paper/XSUHAEUN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.00977&json=true","fetch_graph":"https://pith.science/api/pith-number/XSUHAEUNM652L2X3XWZBPHY3FH/graph.json","fetch_events":"https://pith.science/api/pith-number/XSUHAEUNM652L2X3XWZBPHY3FH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XSUHAEUNM652L2X3XWZBPHY3FH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XSUHAEUNM652L2X3XWZBPHY3FH/action/storage_attestation","attest_author":"https://pith.science/pith/XSUHAEUNM652L2X3XWZBPHY3FH/action/author_attestation","sign_citation":"https://pith.science/pith/XSUHAEUNM652L2X3XWZBPHY3FH/action/citation_signature","submit_replication":"https://pith.science/pith/XSUHAEUNM652L2X3XWZBPHY3FH/action/replication_record"}},"created_at":"2026-07-05T08:21:35.719423+00:00","updated_at":"2026-07-05T08:21:35.719423+00:00"}