{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:5ERZ6USJBCMQM5JNDDW2PQJWEA","short_pith_number":"pith:5ERZ6USJ","schema_version":"1.0","canonical_sha256":"e9239f5249089906752d18eda7c13620360e7d5b0891e9f1a3a5eee2ea5f87ad","source":{"kind":"arxiv","id":"2012.00001","version":1},"attestation_state":"computed","paper":{"title":"Utilizing stability criteria in choosing feature selection methods yields reproducible results in microbiome data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.QM","authors_text":"Anna-Paola Carrieri, Austin D. Swafford, Ho-Cheol Kim, Laxmi Parida, Lingjing Jiang, Loki Natarajan, Niina Haiminen, Rob Knight, Shi Huang, Yoshiki Vazquez-Baeza","submitted_at":"2020-11-30T22:23:26Z","abstract_excerpt":"Feature selection is indispensable in microbiome data analysis, but it can be particularly challenging as microbiome data sets are high-dimensional, underdetermined, sparse and compositional. Great efforts have recently been made on developing new methods for feature selection that handle the above data characteristics, but almost all methods were evaluated based on performance of model predictions. However, little attention has been paid to address a fundamental question: how appropriate are those evaluation criteria? Most feature selection methods often control the model fit, but the ability"},"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":"2012.00001","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2020-11-30T22:23:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"89c4aafd3aac1dd93a0e748d0149c1f12f26d3a428f62187bac9a22e6ac3d102","abstract_canon_sha256":"ce2cf4a2d18ca772fa3247572cc2d89e129e0995475ec11f6cb5f7d10145b833"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:02:42.791811Z","signature_b64":"J4Y7QMnuMpmLEVUBZYR2XT6jJ+1oTkIWHcjdvebokjXikwDJS7BFNRrvzIsupeN7R+aQgJXsQYTeGQ9/FbTdDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9239f5249089906752d18eda7c13620360e7d5b0891e9f1a3a5eee2ea5f87ad","last_reissued_at":"2026-07-05T03:02:42.791328Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:02:42.791328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Utilizing stability criteria in choosing feature selection methods yields reproducible results in microbiome data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.QM","authors_text":"Anna-Paola Carrieri, Austin D. Swafford, Ho-Cheol Kim, Laxmi Parida, Lingjing Jiang, Loki Natarajan, Niina Haiminen, Rob Knight, Shi Huang, Yoshiki Vazquez-Baeza","submitted_at":"2020-11-30T22:23:26Z","abstract_excerpt":"Feature selection is indispensable in microbiome data analysis, but it can be particularly challenging as microbiome data sets are high-dimensional, underdetermined, sparse and compositional. Great efforts have recently been made on developing new methods for feature selection that handle the above data characteristics, but almost all methods were evaluated based on performance of model predictions. However, little attention has been paid to address a fundamental question: how appropriate are those evaluation criteria? Most feature selection methods often control the model fit, but the ability"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.00001","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/2012.00001/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":"2012.00001","created_at":"2026-07-05T03:02:42.791385+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.00001v1","created_at":"2026-07-05T03:02:42.791385+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.00001","created_at":"2026-07-05T03:02:42.791385+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ERZ6USJBCMQ","created_at":"2026-07-05T03:02:42.791385+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ERZ6USJBCMQM5JN","created_at":"2026-07-05T03:02:42.791385+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ERZ6USJ","created_at":"2026-07-05T03:02:42.791385+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07463","citing_title":"Should We Dangle a Carrot? The Effect of Performance-based Incentives in Visualization Experiments","ref_index":77,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5ERZ6USJBCMQM5JNDDW2PQJWEA","json":"https://pith.science/pith/5ERZ6USJBCMQM5JNDDW2PQJWEA.json","graph_json":"https://pith.science/api/pith-number/5ERZ6USJBCMQM5JNDDW2PQJWEA/graph.json","events_json":"https://pith.science/api/pith-number/5ERZ6USJBCMQM5JNDDW2PQJWEA/events.json","paper":"https://pith.science/paper/5ERZ6USJ"},"agent_actions":{"view_html":"https://pith.science/pith/5ERZ6USJBCMQM5JNDDW2PQJWEA","download_json":"https://pith.science/pith/5ERZ6USJBCMQM5JNDDW2PQJWEA.json","view_paper":"https://pith.science/paper/5ERZ6USJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.00001&json=true","fetch_graph":"https://pith.science/api/pith-number/5ERZ6USJBCMQM5JNDDW2PQJWEA/graph.json","fetch_events":"https://pith.science/api/pith-number/5ERZ6USJBCMQM5JNDDW2PQJWEA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ERZ6USJBCMQM5JNDDW2PQJWEA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ERZ6USJBCMQM5JNDDW2PQJWEA/action/storage_attestation","attest_author":"https://pith.science/pith/5ERZ6USJBCMQM5JNDDW2PQJWEA/action/author_attestation","sign_citation":"https://pith.science/pith/5ERZ6USJBCMQM5JNDDW2PQJWEA/action/citation_signature","submit_replication":"https://pith.science/pith/5ERZ6USJBCMQM5JNDDW2PQJWEA/action/replication_record"}},"created_at":"2026-07-05T03:02:42.791385+00:00","updated_at":"2026-07-05T03:02:42.791385+00:00"}