{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:B6V3D5GUS4CF3TKN3JEMLBC7CY","short_pith_number":"pith:B6V3D5GU","schema_version":"1.0","canonical_sha256":"0fabb1f4d497045dcd4dda48c5845f163e99b9d05254cc2b05e35a70e436fc8f","source":{"kind":"arxiv","id":"2601.08929","version":3},"attestation_state":"computed","paper":{"title":"A Global Characterization of $f$-Divergences Yielding PSD Mutual-Information Matrices","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Mutual-information matrices from f-divergences are positive semidefinite for all finite alphabets precisely when the normalized generator expands as a power series with nonnegative coefficients that converges on all positive reals.","cross_cats":["math.IT"],"primary_cat":"cs.IT","authors_text":"Zachary Robertson","submitted_at":"2026-01-13T19:09:19Z","abstract_excerpt":"Given $n$ random variables, when does the matrix of pairwise $f$-mutual informations define a PSD kernel over variables? For convex finite generators $f:(0,\\infty)\\to\\mathbb{R}$ with $f(1)=0$ and finite boundary value $f(0)$, we give a closed characterization up to linear transformation $f\\sim f+c(t-1)$, which leaves every $f$-divergence and every $f$-mutual-information matrix unchanged. The matrix $M^{(f)}_{ij}:=I_f(X_i;X_j)$ is PSD for every finite-alphabet family if and only if the normalized representative has a globally convergent expansion $\\bar f(t)=\\sum_{m\\ge2}a_m(t-1)^m$, with $a_m\\ge"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2601.08929","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IT","submitted_at":"2026-01-13T19:09:19Z","cross_cats_sorted":["math.IT"],"title_canon_sha256":"9f1484ceff67644f2fe001cef2f926c4a94c0a13fcd71ee32ed1e023b45a1795","abstract_canon_sha256":"76cb0e1841cf9733024256918b40c680caa7ba07b955a674a95f70c6b049b040"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:00.248936Z","signature_b64":"ormb7Ztrr9NkIVPWJzzb2km3bATR/FdGRI6PVH06MaH1wsYWoj2CXJqBm1m4ab5v9oVezz/2MO1Y4CsR/Or1Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fabb1f4d497045dcd4dda48c5845f163e99b9d05254cc2b05e35a70e436fc8f","last_reissued_at":"2026-05-17T23:39:00.248211Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:00.248211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Global Characterization of $f$-Divergences Yielding PSD Mutual-Information Matrices","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Mutual-information matrices from f-divergences are positive semidefinite for all finite alphabets precisely when the normalized generator expands as a power series with nonnegative coefficients that converges on all positive reals.","cross_cats":["math.IT"],"primary_cat":"cs.IT","authors_text":"Zachary Robertson","submitted_at":"2026-01-13T19:09:19Z","abstract_excerpt":"Given $n$ random variables, when does the matrix of pairwise $f$-mutual informations define a PSD kernel over variables? For convex finite generators $f:(0,\\infty)\\to\\mathbb{R}$ with $f(1)=0$ and finite boundary value $f(0)$, we give a closed characterization up to linear transformation $f\\sim f+c(t-1)$, which leaves every $f$-divergence and every $f$-mutual-information matrix unchanged. The matrix $M^{(f)}_{ij}:=I_f(X_i;X_j)$ is PSD for every finite-alphabet family if and only if the normalized representative has a globally convergent expansion $\\bar f(t)=\\sum_{m\\ge2}a_m(t-1)^m$, with $a_m\\ge"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The matrix M^{(f)}_{ij}:=I_f(X_i;X_j) is PSD for every finite-alphabet family if and only if the normalized representative has a globally convergent expansion bar f(t)=sum_{m>=2} a_m (t-1)^m, with a_m >=0, on all of (0,infty).","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the local positivity condition at t=1, extracted via biased three-point kernels and the BGKP theorem, extends to global analyticity and holds for all finite alphabets without additional restrictions on the divergence.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Pairwise f-mutual information matrices are positive semi-definite for all finite-alphabet distributions exactly when the f generator has a power series with all nonnegative coefficients that converges on the positive reals.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Mutual-information matrices from f-divergences are positive semidefinite for all finite alphabets precisely when the normalized generator expands as a power series with nonnegative coefficients that converges on all positive reals.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"36331d8bbc5663bf801ff50a529b67cdf3a5bfe52d44b6c1ea131f258c778c73"},"source":{"id":"2601.08929","kind":"arxiv","version":3},"verdict":{"id":"995b01ac-db5b-467b-9b40-ee43b482cacd","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T14:19:49.410149Z","strongest_claim":"The matrix M^{(f)}_{ij}:=I_f(X_i;X_j) is PSD for every finite-alphabet family if and only if the normalized representative has a globally convergent expansion bar f(t)=sum_{m>=2} a_m (t-1)^m, with a_m >=0, on all of (0,infty).","one_line_summary":"Pairwise f-mutual information matrices are positive semi-definite for all finite-alphabet distributions exactly when the f generator has a power series with all nonnegative coefficients that converges on the positive reals.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the local positivity condition at t=1, extracted via biased three-point kernels and the BGKP theorem, extends to global analyticity and holds for all finite alphabets without additional restrictions on the divergence.","pith_extraction_headline":"Mutual-information matrices from f-divergences are positive semidefinite for all finite alphabets precisely when the normalized generator expands as a power series with nonnegative coefficients that converges on all positive reals."},"references":{"count":15,"sample":[{"doi":"","year":2002,"title":"The mutual information: detecting and evaluating dependencies between variables,","work_id":"fea514a5-c474-40a4-8191-09cb088b6324","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2011,"title":"Detecting novel associations in large data sets,","work_id":"2a29cb7f-f51c-4e07-9aaa-8f1c8b20f120","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2015,"title":"G. Ver Steeg and A. Galstyan, “The information sieve,” inInternational Conference on Machine Learning. PMLR, 2015, pp. 164–172","work_id":"4e6194ae-cd5c-40d0-a24d-0c71dbf85498","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"How transformers learn causal structure with gradient descent","work_id":"15b3610a-8bd8-4edd-9296-a4ad1ee0cbaf","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2014,"title":"Mutual information matrices are not always positive semidefinite,","work_id":"e1cede26-bd45-4e22-9829-14606a05006e","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":15,"snapshot_sha256":"bde82dbe5d38aa658d2913bdc2b1bcb600aa6d2d561b5adcc8088e589eb7196c","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"5f66a16c9e181e8738c401ff9bc9cc1d217565dcb9d3d95330702f1659fe1abc"},"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":"2601.08929","created_at":"2026-05-17T23:39:00.248337+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.08929v3","created_at":"2026-05-17T23:39:00.248337+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.08929","created_at":"2026-05-17T23:39:00.248337+00:00"},{"alias_kind":"pith_short_12","alias_value":"B6V3D5GUS4CF","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"B6V3D5GUS4CF3TKN","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"B6V3D5GU","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B6V3D5GUS4CF3TKN3JEMLBC7CY","json":"https://pith.science/pith/B6V3D5GUS4CF3TKN3JEMLBC7CY.json","graph_json":"https://pith.science/api/pith-number/B6V3D5GUS4CF3TKN3JEMLBC7CY/graph.json","events_json":"https://pith.science/api/pith-number/B6V3D5GUS4CF3TKN3JEMLBC7CY/events.json","paper":"https://pith.science/paper/B6V3D5GU"},"agent_actions":{"view_html":"https://pith.science/pith/B6V3D5GUS4CF3TKN3JEMLBC7CY","download_json":"https://pith.science/pith/B6V3D5GUS4CF3TKN3JEMLBC7CY.json","view_paper":"https://pith.science/paper/B6V3D5GU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.08929&json=true","fetch_graph":"https://pith.science/api/pith-number/B6V3D5GUS4CF3TKN3JEMLBC7CY/graph.json","fetch_events":"https://pith.science/api/pith-number/B6V3D5GUS4CF3TKN3JEMLBC7CY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B6V3D5GUS4CF3TKN3JEMLBC7CY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B6V3D5GUS4CF3TKN3JEMLBC7CY/action/storage_attestation","attest_author":"https://pith.science/pith/B6V3D5GUS4CF3TKN3JEMLBC7CY/action/author_attestation","sign_citation":"https://pith.science/pith/B6V3D5GUS4CF3TKN3JEMLBC7CY/action/citation_signature","submit_replication":"https://pith.science/pith/B6V3D5GUS4CF3TKN3JEMLBC7CY/action/replication_record"}},"created_at":"2026-05-17T23:39:00.248337+00:00","updated_at":"2026-05-17T23:39:00.248337+00:00"}