{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HPCAG6O3WRPM7FZXNVHB5HYXKH","short_pith_number":"pith:HPCAG6O3","schema_version":"1.0","canonical_sha256":"3bc40379dbb45ecf97376d4e1e9f1751c9577e4c3137f00622c4ed4553fb1aa4","source":{"kind":"arxiv","id":"2507.15173","version":1},"attestation_state":"computed","paper":{"title":"Better Models and Algorithms for Learning Ising Models from Dynamics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ankur Moitra, Elchanan Mossel, Jason Gaitonde","submitted_at":"2025-07-21T01:26:57Z","abstract_excerpt":"We study the problem of learning the structure and parameters of the Ising model, a fundamental model of high-dimensional data, when observing the evolution of an associated Markov chain. A recent line of work has studied the natural problem of learning when observing an evolution of the well-known Glauber dynamics [Bresler, Gamarnik, Shah, IEEE Trans. Inf. Theory 2018, Gaitonde, Mossel STOC 2024], which provides an arguably more realistic generative model than the classical i.i.d. setting. However, this prior work crucially assumes that all site update attempts are observed, \\emph{even when t"},"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":"2507.15173","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-21T01:26:57Z","cross_cats_sorted":["cs.DS","stat.ML"],"title_canon_sha256":"271481229d4bedcb154c4c21707424a893b00d35f4f31a85ad430534ceffe0c3","abstract_canon_sha256":"b0b43ace455b9a45fd49e5c8e9991543b6a719d31c4af26379e6181a4d006d24"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:19.625137Z","signature_b64":"kNWrAWbhgBiG2RGoshWTffmNcfLXVK5nQ2UWdxkz781pRKnOZkrraJuGaNWR6QnWdpA+9WxFX9XIg/nurcXXBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3bc40379dbb45ecf97376d4e1e9f1751c9577e4c3137f00622c4ed4553fb1aa4","last_reissued_at":"2026-07-05T11:40:19.624616Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:19.624616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Better Models and Algorithms for Learning Ising Models from Dynamics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ankur Moitra, Elchanan Mossel, Jason Gaitonde","submitted_at":"2025-07-21T01:26:57Z","abstract_excerpt":"We study the problem of learning the structure and parameters of the Ising model, a fundamental model of high-dimensional data, when observing the evolution of an associated Markov chain. A recent line of work has studied the natural problem of learning when observing an evolution of the well-known Glauber dynamics [Bresler, Gamarnik, Shah, IEEE Trans. Inf. Theory 2018, Gaitonde, Mossel STOC 2024], which provides an arguably more realistic generative model than the classical i.i.d. setting. However, this prior work crucially assumes that all site update attempts are observed, \\emph{even when t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15173","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/2507.15173/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":"2507.15173","created_at":"2026-07-05T11:40:19.624689+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.15173v1","created_at":"2026-07-05T11:40:19.624689+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15173","created_at":"2026-07-05T11:40:19.624689+00:00"},{"alias_kind":"pith_short_12","alias_value":"HPCAG6O3WRPM","created_at":"2026-07-05T11:40:19.624689+00:00"},{"alias_kind":"pith_short_16","alias_value":"HPCAG6O3WRPM7FZX","created_at":"2026-07-05T11:40:19.624689+00:00"},{"alias_kind":"pith_short_8","alias_value":"HPCAG6O3","created_at":"2026-07-05T11:40:19.624689+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13576","citing_title":"Learning with Simulators: No Regret in a Computationally Bounded World","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31230","citing_title":"Learning Gaussian Graphical Models from a Glauber Trajectory Without Mixing","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06109","citing_title":"Learning $\\mathsf{AC}^0$ Under Graphical Models","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HPCAG6O3WRPM7FZXNVHB5HYXKH","json":"https://pith.science/pith/HPCAG6O3WRPM7FZXNVHB5HYXKH.json","graph_json":"https://pith.science/api/pith-number/HPCAG6O3WRPM7FZXNVHB5HYXKH/graph.json","events_json":"https://pith.science/api/pith-number/HPCAG6O3WRPM7FZXNVHB5HYXKH/events.json","paper":"https://pith.science/paper/HPCAG6O3"},"agent_actions":{"view_html":"https://pith.science/pith/HPCAG6O3WRPM7FZXNVHB5HYXKH","download_json":"https://pith.science/pith/HPCAG6O3WRPM7FZXNVHB5HYXKH.json","view_paper":"https://pith.science/paper/HPCAG6O3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.15173&json=true","fetch_graph":"https://pith.science/api/pith-number/HPCAG6O3WRPM7FZXNVHB5HYXKH/graph.json","fetch_events":"https://pith.science/api/pith-number/HPCAG6O3WRPM7FZXNVHB5HYXKH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HPCAG6O3WRPM7FZXNVHB5HYXKH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HPCAG6O3WRPM7FZXNVHB5HYXKH/action/storage_attestation","attest_author":"https://pith.science/pith/HPCAG6O3WRPM7FZXNVHB5HYXKH/action/author_attestation","sign_citation":"https://pith.science/pith/HPCAG6O3WRPM7FZXNVHB5HYXKH/action/citation_signature","submit_replication":"https://pith.science/pith/HPCAG6O3WRPM7FZXNVHB5HYXKH/action/replication_record"}},"created_at":"2026-07-05T11:40:19.624689+00:00","updated_at":"2026-07-05T11:40:19.624689+00:00"}