{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GYEIGM3EKIBFVYX4V3LV6EIQFZ","short_pith_number":"pith:GYEIGM3E","schema_version":"1.0","canonical_sha256":"360883336452025ae2fcaed75f11102e4a14fe4d63426dc02973bd71069515f4","source":{"kind":"arxiv","id":"2411.11174","version":1},"attestation_state":"computed","paper":{"title":"Learning the Sherrington-Kirkpatrick Model Even at Low Temperature","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Adam Klivans, Gautam Chandrasekaran","submitted_at":"2024-11-17T21:02:12Z","abstract_excerpt":"We consider the fundamental problem of learning the parameters of an undirected graphical model or Markov Random Field (MRF) in the setting where the edge weights are chosen at random. For Ising models, we show that a multiplicative-weight update algorithm due to Klivans and Meka learns the parameters in polynomial time for any inverse temperature $\\beta \\leq \\sqrt{\\log n}$.\n  This immediately yields an algorithm for learning the Sherrington-Kirkpatrick (SK) model beyond the high-temperature regime of $\\beta < 1$. Prior work breaks down at $\\beta = 1$ and requires heavy machinery from statisti"},"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":"2411.11174","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-17T21:02:12Z","cross_cats_sorted":["cs.DS","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"e6efc5c00c6c1eac2221074fbf28c127f983e9f6c7c86ae6a08d9c67da4a6db3","abstract_canon_sha256":"cec0bf78a465306e34c786858cc8532aa8cfa8e17886decaae730a5bab14c928"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:52.502055Z","signature_b64":"1e7jSQ+Xlx5DmA+XS1FDaKPKEqbBDVu2BGiWlesXCJXJsK21pzzaQCjtWdX1opSEAXi52WJSLpTJ4abN9L+yCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"360883336452025ae2fcaed75f11102e4a14fe4d63426dc02973bd71069515f4","last_reissued_at":"2026-07-05T09:36:52.501536Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:52.501536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning the Sherrington-Kirkpatrick Model Even at Low Temperature","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Adam Klivans, Gautam Chandrasekaran","submitted_at":"2024-11-17T21:02:12Z","abstract_excerpt":"We consider the fundamental problem of learning the parameters of an undirected graphical model or Markov Random Field (MRF) in the setting where the edge weights are chosen at random. For Ising models, we show that a multiplicative-weight update algorithm due to Klivans and Meka learns the parameters in polynomial time for any inverse temperature $\\beta \\leq \\sqrt{\\log n}$.\n  This immediately yields an algorithm for learning the Sherrington-Kirkpatrick (SK) model beyond the high-temperature regime of $\\beta < 1$. Prior work breaks down at $\\beta = 1$ and requires heavy machinery from statisti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11174","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/2411.11174/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":"2411.11174","created_at":"2026-07-05T09:36:52.501588+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.11174v1","created_at":"2026-07-05T09:36:52.501588+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11174","created_at":"2026-07-05T09:36:52.501588+00:00"},{"alias_kind":"pith_short_12","alias_value":"GYEIGM3EKIBF","created_at":"2026-07-05T09:36:52.501588+00:00"},{"alias_kind":"pith_short_16","alias_value":"GYEIGM3EKIBFVYX4","created_at":"2026-07-05T09:36:52.501588+00:00"},{"alias_kind":"pith_short_8","alias_value":"GYEIGM3E","created_at":"2026-07-05T09:36:52.501588+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.00764","citing_title":"Learning Juntas under Markov Random Fields","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GYEIGM3EKIBFVYX4V3LV6EIQFZ","json":"https://pith.science/pith/GYEIGM3EKIBFVYX4V3LV6EIQFZ.json","graph_json":"https://pith.science/api/pith-number/GYEIGM3EKIBFVYX4V3LV6EIQFZ/graph.json","events_json":"https://pith.science/api/pith-number/GYEIGM3EKIBFVYX4V3LV6EIQFZ/events.json","paper":"https://pith.science/paper/GYEIGM3E"},"agent_actions":{"view_html":"https://pith.science/pith/GYEIGM3EKIBFVYX4V3LV6EIQFZ","download_json":"https://pith.science/pith/GYEIGM3EKIBFVYX4V3LV6EIQFZ.json","view_paper":"https://pith.science/paper/GYEIGM3E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.11174&json=true","fetch_graph":"https://pith.science/api/pith-number/GYEIGM3EKIBFVYX4V3LV6EIQFZ/graph.json","fetch_events":"https://pith.science/api/pith-number/GYEIGM3EKIBFVYX4V3LV6EIQFZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GYEIGM3EKIBFVYX4V3LV6EIQFZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GYEIGM3EKIBFVYX4V3LV6EIQFZ/action/storage_attestation","attest_author":"https://pith.science/pith/GYEIGM3EKIBFVYX4V3LV6EIQFZ/action/author_attestation","sign_citation":"https://pith.science/pith/GYEIGM3EKIBFVYX4V3LV6EIQFZ/action/citation_signature","submit_replication":"https://pith.science/pith/GYEIGM3EKIBFVYX4V3LV6EIQFZ/action/replication_record"}},"created_at":"2026-07-05T09:36:52.501588+00:00","updated_at":"2026-07-05T09:36:52.501588+00:00"}