{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:FSAQNXUCNK5D5MM4SIP7MJNZ5X","short_pith_number":"pith:FSAQNXUC","schema_version":"1.0","canonical_sha256":"2c8106de826aba3eb19c921ff625b9edfab55ef4518a4642136c9049f28544de","source":{"kind":"arxiv","id":"1806.09046","version":1},"attestation_state":"computed","paper":{"title":"Disease Classification in Metagenomics with 2D Embeddings and Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Edi Prifti, Jean-Daniel Zucker, Nataliya Sokolovska, Thanh Hai Nguyen, Yann Chevaleyre","submitted_at":"2018-06-23T22:01:27Z","abstract_excerpt":"Deep learning (DL) techniques have shown unprecedented success when applied to images, waveforms, and text. Generally, when the sample size ($N$) is much bigger than the number of features ($d$), DL often outperforms other machine learning (ML) techniques, often through the use of Convolutional Neural Networks (CNNs). However, in many bioinformatics fields (including metagenomics), we encounter the opposite situation where $d$ is significantly greater than $N$. In these situations, applying DL techniques would lead to severe overfitting.\n  Here we aim to improve classification of various disea"},"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":"1806.09046","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-23T22:01:27Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"66e45ceb9bad797aaf415203e70580b7aa5dd4e5abc1709a5bec47ea5f13b125","abstract_canon_sha256":"4391d06d28592ef6381885313286bce1f67a7623cb1b0290ddd48dbc155321af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:30.524192Z","signature_b64":"vJ/A4LOcnzR2JWhzfU7Tnh42S36XM9jg8pkvJl52kfKhSqY2aWA2ZQ6/AbrK/MG6dJK4opgLO54ehPn8hW+yDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c8106de826aba3eb19c921ff625b9edfab55ef4518a4642136c9049f28544de","last_reissued_at":"2026-05-18T00:12:30.523538Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:30.523538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Disease Classification in Metagenomics with 2D Embeddings and Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Edi Prifti, Jean-Daniel Zucker, Nataliya Sokolovska, Thanh Hai Nguyen, Yann Chevaleyre","submitted_at":"2018-06-23T22:01:27Z","abstract_excerpt":"Deep learning (DL) techniques have shown unprecedented success when applied to images, waveforms, and text. Generally, when the sample size ($N$) is much bigger than the number of features ($d$), DL often outperforms other machine learning (ML) techniques, often through the use of Convolutional Neural Networks (CNNs). However, in many bioinformatics fields (including metagenomics), we encounter the opposite situation where $d$ is significantly greater than $N$. In these situations, applying DL techniques would lead to severe overfitting.\n  Here we aim to improve classification of various disea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.09046","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":"1806.09046","created_at":"2026-05-18T00:12:30.523625+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.09046v1","created_at":"2026-05-18T00:12:30.523625+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.09046","created_at":"2026-05-18T00:12:30.523625+00:00"},{"alias_kind":"pith_short_12","alias_value":"FSAQNXUCNK5D","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"FSAQNXUCNK5D5MM4","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"FSAQNXUC","created_at":"2026-05-18T12:32:25.280505+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/FSAQNXUCNK5D5MM4SIP7MJNZ5X","json":"https://pith.science/pith/FSAQNXUCNK5D5MM4SIP7MJNZ5X.json","graph_json":"https://pith.science/api/pith-number/FSAQNXUCNK5D5MM4SIP7MJNZ5X/graph.json","events_json":"https://pith.science/api/pith-number/FSAQNXUCNK5D5MM4SIP7MJNZ5X/events.json","paper":"https://pith.science/paper/FSAQNXUC"},"agent_actions":{"view_html":"https://pith.science/pith/FSAQNXUCNK5D5MM4SIP7MJNZ5X","download_json":"https://pith.science/pith/FSAQNXUCNK5D5MM4SIP7MJNZ5X.json","view_paper":"https://pith.science/paper/FSAQNXUC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.09046&json=true","fetch_graph":"https://pith.science/api/pith-number/FSAQNXUCNK5D5MM4SIP7MJNZ5X/graph.json","fetch_events":"https://pith.science/api/pith-number/FSAQNXUCNK5D5MM4SIP7MJNZ5X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FSAQNXUCNK5D5MM4SIP7MJNZ5X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FSAQNXUCNK5D5MM4SIP7MJNZ5X/action/storage_attestation","attest_author":"https://pith.science/pith/FSAQNXUCNK5D5MM4SIP7MJNZ5X/action/author_attestation","sign_citation":"https://pith.science/pith/FSAQNXUCNK5D5MM4SIP7MJNZ5X/action/citation_signature","submit_replication":"https://pith.science/pith/FSAQNXUCNK5D5MM4SIP7MJNZ5X/action/replication_record"}},"created_at":"2026-05-18T00:12:30.523625+00:00","updated_at":"2026-05-18T00:12:30.523625+00:00"}