{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IWQETABZKTJUDODK6KXB36NHSL","short_pith_number":"pith:IWQETABZ","schema_version":"1.0","canonical_sha256":"45a049803954d341b86af2ae1df9a792cf22e16e32786e246e4b2188ba17a762","source":{"kind":"arxiv","id":"2608.05425","version":1},"attestation_state":"computed","paper":{"title":"From Continuous Dynamics to Practical Gradient-Based Samplers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ME"],"primary_cat":"stat.CO","authors_text":"James Chok","submitted_at":"2026-08-05T21:39:43Z","abstract_excerpt":"Gradient-based Markov chain Monte Carlo methods are often introduced as a catalog of algorithms: Hamiltonian Monte Carlo (HMC), the Metropolis-adjusted Langevin algorithm (MALA), the No-U-Turn Sampler (NUTS), and several underdamped variants. This presentation obscures the common structure of the methods and, more importantly, the reasons why a sampler that is correct in principle may be ineffective in practice. We develop a unified account, beginning with exact continuous-time dynamics that represent idealized sampling methods and for which Metropolis adjustments are not required. Numerical d"},"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":"2608.05425","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.CO","submitted_at":"2026-08-05T21:39:43Z","cross_cats_sorted":["stat.ME"],"title_canon_sha256":"9ea6e231382d2104d46f9f91a60f139c3e55f83583408844e43a23ff6826da19","abstract_canon_sha256":"6e378e7ba6ebcc79eef4c05764cd2b9fcec280581b2b300e2371ac73b113c41d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T00:47:50.611749Z","signature_b64":"izFYa9UeecKrPUxxrmKBW0xSbyTVy+tmaa4ndyGkfbBK3/7NerBU9ETYStSV3uO2Lwtt0roj1J93ppqy2bPnDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45a049803954d341b86af2ae1df9a792cf22e16e32786e246e4b2188ba17a762","last_reissued_at":"2026-08-07T00:47:50.610321Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T00:47:50.610321Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Continuous Dynamics to Practical Gradient-Based Samplers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ME"],"primary_cat":"stat.CO","authors_text":"James Chok","submitted_at":"2026-08-05T21:39:43Z","abstract_excerpt":"Gradient-based Markov chain Monte Carlo methods are often introduced as a catalog of algorithms: Hamiltonian Monte Carlo (HMC), the Metropolis-adjusted Langevin algorithm (MALA), the No-U-Turn Sampler (NUTS), and several underdamped variants. This presentation obscures the common structure of the methods and, more importantly, the reasons why a sampler that is correct in principle may be ineffective in practice. We develop a unified account, beginning with exact continuous-time dynamics that represent idealized sampling methods and for which Metropolis adjustments are not required. Numerical d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05425","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/2608.05425/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":"2608.05425","created_at":"2026-08-07T00:47:50.611693+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.05425v1","created_at":"2026-08-07T00:47:50.611693+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05425","created_at":"2026-08-07T00:47:50.611693+00:00"},{"alias_kind":"pith_short_12","alias_value":"IWQETABZKTJU","created_at":"2026-08-07T00:47:50.611693+00:00"},{"alias_kind":"pith_short_16","alias_value":"IWQETABZKTJUDODK","created_at":"2026-08-07T00:47:50.611693+00:00"},{"alias_kind":"pith_short_8","alias_value":"IWQETABZ","created_at":"2026-08-07T00:47:50.611693+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/IWQETABZKTJUDODK6KXB36NHSL","json":"https://pith.science/pith/IWQETABZKTJUDODK6KXB36NHSL.json","graph_json":"https://pith.science/api/pith-number/IWQETABZKTJUDODK6KXB36NHSL/graph.json","events_json":"https://pith.science/api/pith-number/IWQETABZKTJUDODK6KXB36NHSL/events.json","paper":"https://pith.science/paper/IWQETABZ"},"agent_actions":{"view_html":"https://pith.science/pith/IWQETABZKTJUDODK6KXB36NHSL","download_json":"https://pith.science/pith/IWQETABZKTJUDODK6KXB36NHSL.json","view_paper":"https://pith.science/paper/IWQETABZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.05425&json=true","fetch_graph":"https://pith.science/api/pith-number/IWQETABZKTJUDODK6KXB36NHSL/graph.json","fetch_events":"https://pith.science/api/pith-number/IWQETABZKTJUDODK6KXB36NHSL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IWQETABZKTJUDODK6KXB36NHSL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IWQETABZKTJUDODK6KXB36NHSL/action/storage_attestation","attest_author":"https://pith.science/pith/IWQETABZKTJUDODK6KXB36NHSL/action/author_attestation","sign_citation":"https://pith.science/pith/IWQETABZKTJUDODK6KXB36NHSL/action/citation_signature","submit_replication":"https://pith.science/pith/IWQETABZKTJUDODK6KXB36NHSL/action/replication_record"}},"created_at":"2026-08-07T00:47:50.611693+00:00","updated_at":"2026-08-07T00:47:50.611693+00:00"}