{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MJL6OHI2XTCYFRPVKRQ6RGKG66","short_pith_number":"pith:MJL6OHI2","schema_version":"1.0","canonical_sha256":"6257e71d1abcc582c5f55461e89946f78b04696406326f8307787b00aeecb460","source":{"kind":"arxiv","id":"2606.02199","version":1},"attestation_state":"computed","paper":{"title":"A Contaminated Model for Overdispersed Multinomial Microbiome Count Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Andri\\\"ette Bekker, Antonio Punzo, Arno Otto, Ockert van Heerden, Seite Makgai","submitted_at":"2026-06-01T12:55:39Z","abstract_excerpt":"Multinomial count data, such as microbial composition profiles derived from sequencing studies, frequently contain anomalous observations that distort parameter estimates. The Dirichlet-multinomial (DM) distribution is widely used in this setting but remains sensitive to such contamination. We propose the contaminated Dirichlet-multinomial (CDM) distribution, a two-component mixture in which the regular data come from a DM component with a lower dispersion and the irregular data come from a DM component with an inflated dispersion parameter. This construction accommodates anomalies without req"},"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":"2606.02199","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2026-06-01T12:55:39Z","cross_cats_sorted":[],"title_canon_sha256":"5390a200ee9afbdf8cb20dd7f1773b80aa8d577a894067b10bd083697b4530ef","abstract_canon_sha256":"bb3d81797f54495c176a8e331edd8d9c2fe3ed0c899e6a66f2e34d41ec855823"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T03:04:52.977782Z","signature_b64":"AlqH/6Om/bA8pu2jX7qc6OVrXILuzqgJhrPB7CJziSxzxsA5vjdA4ntZ8bUV2kmSBvK7oTBbJDLo7cwLbdSYAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6257e71d1abcc582c5f55461e89946f78b04696406326f8307787b00aeecb460","last_reissued_at":"2026-06-02T03:04:52.977336Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T03:04:52.977336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Contaminated Model for Overdispersed Multinomial Microbiome Count Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Andri\\\"ette Bekker, Antonio Punzo, Arno Otto, Ockert van Heerden, Seite Makgai","submitted_at":"2026-06-01T12:55:39Z","abstract_excerpt":"Multinomial count data, such as microbial composition profiles derived from sequencing studies, frequently contain anomalous observations that distort parameter estimates. The Dirichlet-multinomial (DM) distribution is widely used in this setting but remains sensitive to such contamination. We propose the contaminated Dirichlet-multinomial (CDM) distribution, a two-component mixture in which the regular data come from a DM component with a lower dispersion and the irregular data come from a DM component with an inflated dispersion parameter. This construction accommodates anomalies without req"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02199","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/2606.02199/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":"2606.02199","created_at":"2026-06-02T03:04:52.977393+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.02199v1","created_at":"2026-06-02T03:04:52.977393+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02199","created_at":"2026-06-02T03:04:52.977393+00:00"},{"alias_kind":"pith_short_12","alias_value":"MJL6OHI2XTCY","created_at":"2026-06-02T03:04:52.977393+00:00"},{"alias_kind":"pith_short_16","alias_value":"MJL6OHI2XTCYFRPV","created_at":"2026-06-02T03:04:52.977393+00:00"},{"alias_kind":"pith_short_8","alias_value":"MJL6OHI2","created_at":"2026-06-02T03:04:52.977393+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/MJL6OHI2XTCYFRPVKRQ6RGKG66","json":"https://pith.science/pith/MJL6OHI2XTCYFRPVKRQ6RGKG66.json","graph_json":"https://pith.science/api/pith-number/MJL6OHI2XTCYFRPVKRQ6RGKG66/graph.json","events_json":"https://pith.science/api/pith-number/MJL6OHI2XTCYFRPVKRQ6RGKG66/events.json","paper":"https://pith.science/paper/MJL6OHI2"},"agent_actions":{"view_html":"https://pith.science/pith/MJL6OHI2XTCYFRPVKRQ6RGKG66","download_json":"https://pith.science/pith/MJL6OHI2XTCYFRPVKRQ6RGKG66.json","view_paper":"https://pith.science/paper/MJL6OHI2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.02199&json=true","fetch_graph":"https://pith.science/api/pith-number/MJL6OHI2XTCYFRPVKRQ6RGKG66/graph.json","fetch_events":"https://pith.science/api/pith-number/MJL6OHI2XTCYFRPVKRQ6RGKG66/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MJL6OHI2XTCYFRPVKRQ6RGKG66/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MJL6OHI2XTCYFRPVKRQ6RGKG66/action/storage_attestation","attest_author":"https://pith.science/pith/MJL6OHI2XTCYFRPVKRQ6RGKG66/action/author_attestation","sign_citation":"https://pith.science/pith/MJL6OHI2XTCYFRPVKRQ6RGKG66/action/citation_signature","submit_replication":"https://pith.science/pith/MJL6OHI2XTCYFRPVKRQ6RGKG66/action/replication_record"}},"created_at":"2026-06-02T03:04:52.977393+00:00","updated_at":"2026-06-02T03:04:52.977393+00:00"}