{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IIDWB4LDCST5IYVZ3AQK3ADQB4","short_pith_number":"pith:IIDWB4LD","schema_version":"1.0","canonical_sha256":"420760f16314a7d462b9d820ad80700f058bf0c2c6cd5a71026363ba85305123","source":{"kind":"arxiv","id":"2510.12744","version":2},"attestation_state":"computed","paper":{"title":"Dendrograms of Mixing Measures for Softmax-Gated Gaussian Mixture of Experts: Consistency Without Model Sweeps","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.CO","stat.ME","stat.TH"],"primary_cat":"stat.ML","authors_text":"Binh T. Nguyen, Christopher Drovandi, Do Tien Hai, Nhat Ho, Trung Nguyen Mai, TrungTin Nguyen","submitted_at":"2025-10-14T17:23:44Z","abstract_excerpt":"We develop a unified statistical framework for softmax-gated Gaussian mixture of experts (SGMoE) that addresses three long-standing obstacles in parameter estimation and model selection: (i) non-identifiability of gating parameters up to common translations, (ii) intrinsic gate-expert interactions that induce coupled differential relations in the likelihood, and (iii) the tight numerator-denominator coupling in the softmax-induced conditional density. Our approach introduces Voronoi-type loss functions aligned with the gate-partition geometry and establishes finite-sample convergence rates for"},"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":"2510.12744","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-10-14T17:23:44Z","cross_cats_sorted":["cs.LG","math.ST","stat.CO","stat.ME","stat.TH"],"title_canon_sha256":"afd0d70d8675e980afad199a68969ac385de244f818f7ff17f82161873b866af","abstract_canon_sha256":"8c629e8e7700228da466ff663d00738c2e23378dc3be1a64b3590b9116741a9f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:07:11.257692Z","signature_b64":"MniuQv1aA5PNsldD0GrVE5Ce1PU3EAXawplDmmjsH5RCS7T+YKqnypDBeupzXyvyFDnvTqhsis/FwLuo0g06Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"420760f16314a7d462b9d820ad80700f058bf0c2c6cd5a71026363ba85305123","last_reissued_at":"2026-06-09T02:07:11.256626Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:07:11.256626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dendrograms of Mixing Measures for Softmax-Gated Gaussian Mixture of Experts: Consistency Without Model Sweeps","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.CO","stat.ME","stat.TH"],"primary_cat":"stat.ML","authors_text":"Binh T. Nguyen, Christopher Drovandi, Do Tien Hai, Nhat Ho, Trung Nguyen Mai, TrungTin Nguyen","submitted_at":"2025-10-14T17:23:44Z","abstract_excerpt":"We develop a unified statistical framework for softmax-gated Gaussian mixture of experts (SGMoE) that addresses three long-standing obstacles in parameter estimation and model selection: (i) non-identifiability of gating parameters up to common translations, (ii) intrinsic gate-expert interactions that induce coupled differential relations in the likelihood, and (iii) the tight numerator-denominator coupling in the softmax-induced conditional density. Our approach introduces Voronoi-type loss functions aligned with the gate-partition geometry and establishes finite-sample convergence rates for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.12744","kind":"arxiv","version":2},"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/2510.12744/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":"2510.12744","created_at":"2026-06-09T02:07:11.256779+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.12744v2","created_at":"2026-06-09T02:07:11.256779+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.12744","created_at":"2026-06-09T02:07:11.256779+00:00"},{"alias_kind":"pith_short_12","alias_value":"IIDWB4LDCST5","created_at":"2026-06-09T02:07:11.256779+00:00"},{"alias_kind":"pith_short_16","alias_value":"IIDWB4LDCST5IYVZ","created_at":"2026-06-09T02:07:11.256779+00:00"},{"alias_kind":"pith_short_8","alias_value":"IIDWB4LD","created_at":"2026-06-09T02:07:11.256779+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IIDWB4LDCST5IYVZ3AQK3ADQB4","json":"https://pith.science/pith/IIDWB4LDCST5IYVZ3AQK3ADQB4.json","graph_json":"https://pith.science/api/pith-number/IIDWB4LDCST5IYVZ3AQK3ADQB4/graph.json","events_json":"https://pith.science/api/pith-number/IIDWB4LDCST5IYVZ3AQK3ADQB4/events.json","paper":"https://pith.science/paper/IIDWB4LD"},"agent_actions":{"view_html":"https://pith.science/pith/IIDWB4LDCST5IYVZ3AQK3ADQB4","download_json":"https://pith.science/pith/IIDWB4LDCST5IYVZ3AQK3ADQB4.json","view_paper":"https://pith.science/paper/IIDWB4LD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.12744&json=true","fetch_graph":"https://pith.science/api/pith-number/IIDWB4LDCST5IYVZ3AQK3ADQB4/graph.json","fetch_events":"https://pith.science/api/pith-number/IIDWB4LDCST5IYVZ3AQK3ADQB4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IIDWB4LDCST5IYVZ3AQK3ADQB4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IIDWB4LDCST5IYVZ3AQK3ADQB4/action/storage_attestation","attest_author":"https://pith.science/pith/IIDWB4LDCST5IYVZ3AQK3ADQB4/action/author_attestation","sign_citation":"https://pith.science/pith/IIDWB4LDCST5IYVZ3AQK3ADQB4/action/citation_signature","submit_replication":"https://pith.science/pith/IIDWB4LDCST5IYVZ3AQK3ADQB4/action/replication_record"}},"created_at":"2026-06-09T02:07:11.256779+00:00","updated_at":"2026-06-09T02:07:11.256779+00:00"}