{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JJ5Z55QUQSYBSH5YIUTFFM7U6R","short_pith_number":"pith:JJ5Z55QU","schema_version":"1.0","canonical_sha256":"4a7b9ef61484b0191fb8452652b3f4f46ab29785132b3f119000e3b7a633908b","source":{"kind":"arxiv","id":"2506.00330","version":3},"attestation_state":"computed","paper":{"title":"Accurate Estimation of Mutual Information in High Dimensional Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML"],"primary_cat":"physics.data-an","authors_text":"Eslam Abdelaleem, Ilya Nemenman, K. Michael Martini","submitted_at":"2025-05-31T01:06:18Z","abstract_excerpt":"Mutual information (MI) quantifies statistical dependence between variables and is widely used across scientific disciplines, yet accurate estimation from finite data remains notoriously difficult. Common approaches fail in high-dimensional, undersampled regimes ($N \\lesssim K$) typical of modern experiments, and no accepted tests exist to detect when neural network-based estimators fail, making them effectively unusable as scientific instruments.\n  We show that neural MI estimators can be made reliable when the statistical dependencies admit a low-dimensional latent representation. Sample com"},"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":"2506.00330","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.data-an","submitted_at":"2025-05-31T01:06:18Z","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"title_canon_sha256":"d10e9104ecd886d856968e2776d414074cb3687dedae6c64628e0483b85eac6c","abstract_canon_sha256":"3d9eca480cb5323d15c70dbb1a9dc286de96bfa47fb689d834495384f180e3d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:10:26.630173Z","signature_b64":"6jsnm9EYMom1lMpyGdlC63K63V1E/MYP2zEQbqiwj0ahbr1rxnesDD+YCwXfLDitbygax6kbz5EXGEPeKol5AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a7b9ef61484b0191fb8452652b3f4f46ab29785132b3f119000e3b7a633908b","last_reissued_at":"2026-06-11T01:10:26.629121Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:10:26.629121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accurate Estimation of Mutual Information in High Dimensional Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML"],"primary_cat":"physics.data-an","authors_text":"Eslam Abdelaleem, Ilya Nemenman, K. Michael Martini","submitted_at":"2025-05-31T01:06:18Z","abstract_excerpt":"Mutual information (MI) quantifies statistical dependence between variables and is widely used across scientific disciplines, yet accurate estimation from finite data remains notoriously difficult. Common approaches fail in high-dimensional, undersampled regimes ($N \\lesssim K$) typical of modern experiments, and no accepted tests exist to detect when neural network-based estimators fail, making them effectively unusable as scientific instruments.\n  We show that neural MI estimators can be made reliable when the statistical dependencies admit a low-dimensional latent representation. Sample com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00330","kind":"arxiv","version":3},"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/2506.00330/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":"2506.00330","created_at":"2026-06-11T01:10:26.629268+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00330v3","created_at":"2026-06-11T01:10:26.629268+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00330","created_at":"2026-06-11T01:10:26.629268+00:00"},{"alias_kind":"pith_short_12","alias_value":"JJ5Z55QUQSYB","created_at":"2026-06-11T01:10:26.629268+00:00"},{"alias_kind":"pith_short_16","alias_value":"JJ5Z55QUQSYBSH5Y","created_at":"2026-06-11T01:10:26.629268+00:00"},{"alias_kind":"pith_short_8","alias_value":"JJ5Z55QU","created_at":"2026-06-11T01:10:26.629268+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2507.22207","citing_title":"Better Together: Cross and Joint Covariances Enhance Signal Detectability in Undersampled Data","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24662","citing_title":"Information bottleneck for learning the phase space of dynamics from high-dimensional experimental data","ref_index":56,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JJ5Z55QUQSYBSH5YIUTFFM7U6R","json":"https://pith.science/pith/JJ5Z55QUQSYBSH5YIUTFFM7U6R.json","graph_json":"https://pith.science/api/pith-number/JJ5Z55QUQSYBSH5YIUTFFM7U6R/graph.json","events_json":"https://pith.science/api/pith-number/JJ5Z55QUQSYBSH5YIUTFFM7U6R/events.json","paper":"https://pith.science/paper/JJ5Z55QU"},"agent_actions":{"view_html":"https://pith.science/pith/JJ5Z55QUQSYBSH5YIUTFFM7U6R","download_json":"https://pith.science/pith/JJ5Z55QUQSYBSH5YIUTFFM7U6R.json","view_paper":"https://pith.science/paper/JJ5Z55QU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00330&json=true","fetch_graph":"https://pith.science/api/pith-number/JJ5Z55QUQSYBSH5YIUTFFM7U6R/graph.json","fetch_events":"https://pith.science/api/pith-number/JJ5Z55QUQSYBSH5YIUTFFM7U6R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JJ5Z55QUQSYBSH5YIUTFFM7U6R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JJ5Z55QUQSYBSH5YIUTFFM7U6R/action/storage_attestation","attest_author":"https://pith.science/pith/JJ5Z55QUQSYBSH5YIUTFFM7U6R/action/author_attestation","sign_citation":"https://pith.science/pith/JJ5Z55QUQSYBSH5YIUTFFM7U6R/action/citation_signature","submit_replication":"https://pith.science/pith/JJ5Z55QUQSYBSH5YIUTFFM7U6R/action/replication_record"}},"created_at":"2026-06-11T01:10:26.629268+00:00","updated_at":"2026-06-11T01:10:26.629268+00:00"}