{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:J2CN5VZR75DKGCKFMIA3QEKIGQ","short_pith_number":"pith:J2CN5VZR","schema_version":"1.0","canonical_sha256":"4e84ded731ff46a309456201b8114834068716fe00c930580973d2191e724511","source":{"kind":"arxiv","id":"1412.1074","version":1},"attestation_state":"computed","paper":{"title":"Learning interpretable models of phenotypes from whole genome sequences with the Set Covering Machine","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CE","cs.LG","stat.ML"],"primary_cat":"q-bio.GN","authors_text":"Alexandre Drouin, Fran\\c{c}ois Laviolette, Jacques Corbeil, Mario Marchand, Maxime D\\'eraspe, S\\'ebastien Gigu\\`ere, Vladana Sagatovich","submitted_at":"2014-12-02T13:26:50Z","abstract_excerpt":"The increased affordability of whole genome sequencing has motivated its use for phenotypic studies. We address the problem of learning interpretable models for discrete phenotypes from whole genomes. We propose a general approach that relies on the Set Covering Machine and a k-mer representation of the genomes. We show results for the problem of predicting the resistance of Pseudomonas Aeruginosa, an important human pathogen, against 4 antibiotics. Our results demonstrate that extremely sparse models which are biologically relevant can be learnt using this approach."},"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":"1412.1074","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2014-12-02T13:26:50Z","cross_cats_sorted":["cs.CE","cs.LG","stat.ML"],"title_canon_sha256":"44d1ed63f26a19a142b68c3fb10919e32ff51c9ecb6deca600bbcbd6b46e1fd2","abstract_canon_sha256":"d6bc640c151ce7c252beba3688aefe6f02cee021f5a57d31d9a385f658701bc4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:32:13.468102Z","signature_b64":"a03nXImbm2fQXCoKCxZ/osQU9z8m0oK/xARjHNwxi+ne/M53Hvw8XTxh5ztp8NEH9TqbFLJs7zQFCY/1Z0MLBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e84ded731ff46a309456201b8114834068716fe00c930580973d2191e724511","last_reissued_at":"2026-05-18T02:32:13.467451Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:32:13.467451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning interpretable models of phenotypes from whole genome sequences with the Set Covering Machine","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CE","cs.LG","stat.ML"],"primary_cat":"q-bio.GN","authors_text":"Alexandre Drouin, Fran\\c{c}ois Laviolette, Jacques Corbeil, Mario Marchand, Maxime D\\'eraspe, S\\'ebastien Gigu\\`ere, Vladana Sagatovich","submitted_at":"2014-12-02T13:26:50Z","abstract_excerpt":"The increased affordability of whole genome sequencing has motivated its use for phenotypic studies. We address the problem of learning interpretable models for discrete phenotypes from whole genomes. We propose a general approach that relies on the Set Covering Machine and a k-mer representation of the genomes. We show results for the problem of predicting the resistance of Pseudomonas Aeruginosa, an important human pathogen, against 4 antibiotics. Our results demonstrate that extremely sparse models which are biologically relevant can be learnt using this approach."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.1074","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":""},"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":"1412.1074","created_at":"2026-05-18T02:32:13.467548+00:00"},{"alias_kind":"arxiv_version","alias_value":"1412.1074v1","created_at":"2026-05-18T02:32:13.467548+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.1074","created_at":"2026-05-18T02:32:13.467548+00:00"},{"alias_kind":"pith_short_12","alias_value":"J2CN5VZR75DK","created_at":"2026-05-18T12:28:33.132498+00:00"},{"alias_kind":"pith_short_16","alias_value":"J2CN5VZR75DKGCKF","created_at":"2026-05-18T12:28:33.132498+00:00"},{"alias_kind":"pith_short_8","alias_value":"J2CN5VZR","created_at":"2026-05-18T12:28:33.132498+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/J2CN5VZR75DKGCKFMIA3QEKIGQ","json":"https://pith.science/pith/J2CN5VZR75DKGCKFMIA3QEKIGQ.json","graph_json":"https://pith.science/api/pith-number/J2CN5VZR75DKGCKFMIA3QEKIGQ/graph.json","events_json":"https://pith.science/api/pith-number/J2CN5VZR75DKGCKFMIA3QEKIGQ/events.json","paper":"https://pith.science/paper/J2CN5VZR"},"agent_actions":{"view_html":"https://pith.science/pith/J2CN5VZR75DKGCKFMIA3QEKIGQ","download_json":"https://pith.science/pith/J2CN5VZR75DKGCKFMIA3QEKIGQ.json","view_paper":"https://pith.science/paper/J2CN5VZR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1412.1074&json=true","fetch_graph":"https://pith.science/api/pith-number/J2CN5VZR75DKGCKFMIA3QEKIGQ/graph.json","fetch_events":"https://pith.science/api/pith-number/J2CN5VZR75DKGCKFMIA3QEKIGQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J2CN5VZR75DKGCKFMIA3QEKIGQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J2CN5VZR75DKGCKFMIA3QEKIGQ/action/storage_attestation","attest_author":"https://pith.science/pith/J2CN5VZR75DKGCKFMIA3QEKIGQ/action/author_attestation","sign_citation":"https://pith.science/pith/J2CN5VZR75DKGCKFMIA3QEKIGQ/action/citation_signature","submit_replication":"https://pith.science/pith/J2CN5VZR75DKGCKFMIA3QEKIGQ/action/replication_record"}},"created_at":"2026-05-18T02:32:13.467548+00:00","updated_at":"2026-05-18T02:32:13.467548+00:00"}