{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2NBNCJJLWSPHTEBN5IPQIMASNO","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8e17a02d519a3baa883e2afe602629654c1f4414847f3bd14d702eae9bfa873a","cross_cats_sorted":["cs.DS","math-ph","math.MP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.PR","submitted_at":"2026-05-05T13:06:26Z","title_canon_sha256":"19673e75fed137168a88d89d0b53272939e80aed2f258487ab61670f4b441da6"},"schema_version":"1.0","source":{"id":"2605.03718","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.03718","created_at":"2026-05-20T02:05:44Z"},{"alias_kind":"arxiv_version","alias_value":"2605.03718v2","created_at":"2026-05-20T02:05:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.03718","created_at":"2026-05-20T02:05:44Z"},{"alias_kind":"pith_short_12","alias_value":"2NBNCJJLWSPH","created_at":"2026-05-20T02:05:44Z"},{"alias_kind":"pith_short_16","alias_value":"2NBNCJJLWSPHTEBN","created_at":"2026-05-20T02:05:44Z"},{"alias_kind":"pith_short_8","alias_value":"2NBNCJJL","created_at":"2026-05-20T02:05:44Z"}],"graph_snapshots":[{"event_id":"sha256:c4f5639eb777751c4b52a67ce28538f702ce406140ee9455608456337ab09a8f","target":"graph","created_at":"2026-05-20T02:05:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We give a polynomial-time algorithm to sample from the Gibbs measure of the Sherrington--Kirkpatrick model with negligible total-variation distance (TVD) error up to inverse temperature β < 1/2."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The restricted log-Sobolev inequality holds on the time-T localized distribution and the free-probability argument controlling the diagonal sub-algebra of the Hessian yields an O(1) KL bound for the finite-time Hessian-ascent process at all β < 1/2."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A polynomial-time algorithm samples the SK model Gibbs measure with o(1) TVD error for β < 1/2 by combining potential Hessian ascent, stochastic localization, Jarzynski equality, and Glauber dynamics."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Polynomial-time algorithm samples the Sherrington-Kirkpatrick Gibbs measure with negligible TVD error for all β < 1/2."}],"snapshot_sha256":"0f232f803ea4f32f83dedea5d6f21eff3b55f12962bca7a8b1cd97e17dee8685"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-20T00:31:21.355617Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T15:04:57.235908Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.03718/integrity.json","findings":[],"snapshot_sha256":"7be0d9bfcc1ab339d33a25722cc1cfda313a0048d20301ab157554c2ac8e9ec6","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We give a polynomial-time algorithm to sample from the Gibbs measure of the Sherrington-Kirkpatrick model with negligible total-variation distance (TVD) error up to inverse temperature $\\beta < 1/2$. Prior work obtained TVD error guarantees only up to $\\beta\\approx 0.295$, while results covering the entire replica-symmetric regime $\\beta < 1$ gave guarantees only in Wasserstein distance.\n  Our approach demonstrates that the same potential Hessian ascent previously developed for optimization also functions as a sampling algorithm by implementing algorithmic stochastic localization at high tempe","authors_text":"Ewan Davies, Holden Lee, Jonathan Shi, Juspreet Singh Sandhu","cross_cats":["cs.DS","math-ph","math.MP"],"headline":"Polynomial-time algorithm samples the Sherrington-Kirkpatrick Gibbs measure with negligible TVD error for all β < 1/2.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.PR","submitted_at":"2026-05-05T13:06:26Z","title":"Potential Hessian Ascent III: Sampling the Sherrington--Kirkpatrick Model at Beta < 1/2"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.03718","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-07T14:10:25.930237Z","id":"5dcc564b-2485-40f8-8594-4c767d8cee96","model_set":{"reader":"grok-4.3"},"one_line_summary":"A polynomial-time algorithm samples the SK model Gibbs measure with o(1) TVD error for β < 1/2 by combining potential Hessian ascent, stochastic localization, Jarzynski equality, and Glauber dynamics.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Polynomial-time algorithm samples the Sherrington-Kirkpatrick Gibbs measure with negligible TVD error for all β < 1/2.","strongest_claim":"We give a polynomial-time algorithm to sample from the Gibbs measure of the Sherrington--Kirkpatrick model with negligible total-variation distance (TVD) error up to inverse temperature β < 1/2.","weakest_assumption":"The restricted log-Sobolev inequality holds on the time-T localized distribution and the free-probability argument controlling the diagonal sub-algebra of the Hessian yields an O(1) KL bound for the finite-time Hessian-ascent process at all β < 1/2."}},"verdict_id":"5dcc564b-2485-40f8-8594-4c767d8cee96"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0bdcbc0336d7caae59e02c63882a5ab43fee077ddcabb15ff928a1639cd9359b","target":"record","created_at":"2026-05-20T02:05:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8e17a02d519a3baa883e2afe602629654c1f4414847f3bd14d702eae9bfa873a","cross_cats_sorted":["cs.DS","math-ph","math.MP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.PR","submitted_at":"2026-05-05T13:06:26Z","title_canon_sha256":"19673e75fed137168a88d89d0b53272939e80aed2f258487ab61670f4b441da6"},"schema_version":"1.0","source":{"id":"2605.03718","kind":"arxiv","version":2}},"canonical_sha256":"d342d1252bb49e79902dea1f0430126bb9edf14fb52bd7fdf915e7366c291764","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d342d1252bb49e79902dea1f0430126bb9edf14fb52bd7fdf915e7366c291764","first_computed_at":"2026-05-20T02:05:44.253416Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T02:05:44.253416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VQEqt/ivyj7ykAkMXZbnlV/C/Jm8Fnuk5TmRqufzBkTHaWidgoGbxvxS5Tq+/tr160aKOExPiYt4jWUced0MCw==","signature_status":"signed_v1","signed_at":"2026-05-20T02:05:44.254246Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.03718","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0bdcbc0336d7caae59e02c63882a5ab43fee077ddcabb15ff928a1639cd9359b","sha256:c4f5639eb777751c4b52a67ce28538f702ce406140ee9455608456337ab09a8f"],"state_sha256":"22252fe01048e0f249c7cb4609eca197beca5f04ff76d26c0e295382931ba99b"}