{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:EGUUMIYEKZNGUVUUTAP5H7NIAG","short_pith_number":"pith:EGUUMIYE","schema_version":"1.0","canonical_sha256":"21a9462304565a6a5694981fd3fda801b14851ca1bbcc3eb1fb4acfe88886be5","source":{"kind":"arxiv","id":"1712.00244","version":1},"attestation_state":"computed","paper":{"title":"Deep Learning for Metagenomic Data: using 2D Embeddings and Convolutional Neural Networks","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":"2017-12-01T09:18:04Z","abstract_excerpt":"Deep learning (DL) techniques have had unprecedented success when applied to images, waveforms, and texts to cite a few. In general, when the sample size (N) is much greater than the number of features (d), DL outperforms previous machine learning (ML) techniques, often through the use of convolution neural networks (CNNs). However, in many bioinformatics ML tasks, we encounter the opposite situation where d is greater than N. In these situations, applying DL techniques (such as feed-forward networks) would lead to severe overfitting. Thus, sparse ML techniques (such as LASSO e.g.) usually yie"},"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":"1712.00244","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-01T09:18:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8bc38839dbc0507cb567df1871ca8a72471df99b30034995f275997d7e63d36c","abstract_canon_sha256":"7ccb27357c113285f3e81ffec1e3ed0275956b11450a88225c682eae70384103"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:06.808243Z","signature_b64":"/ZtqS+jaCVKiqBPqEDB6bqa039/rGpREO47V1PiUZ+9AQVJ+E6eUJE3W7vP+Hn0nO5ngk/XvreVHCxInQuDwDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21a9462304565a6a5694981fd3fda801b14851ca1bbcc3eb1fb4acfe88886be5","last_reissued_at":"2026-05-18T00:29:06.807559Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:06.807559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Learning for Metagenomic Data: using 2D Embeddings and Convolutional Neural Networks","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":"2017-12-01T09:18:04Z","abstract_excerpt":"Deep learning (DL) techniques have had unprecedented success when applied to images, waveforms, and texts to cite a few. In general, when the sample size (N) is much greater than the number of features (d), DL outperforms previous machine learning (ML) techniques, often through the use of convolution neural networks (CNNs). However, in many bioinformatics ML tasks, we encounter the opposite situation where d is greater than N. In these situations, applying DL techniques (such as feed-forward networks) would lead to severe overfitting. Thus, sparse ML techniques (such as LASSO e.g.) usually yie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.00244","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":"1712.00244","created_at":"2026-05-18T00:29:06.807674+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.00244v1","created_at":"2026-05-18T00:29:06.807674+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.00244","created_at":"2026-05-18T00:29:06.807674+00:00"},{"alias_kind":"pith_short_12","alias_value":"EGUUMIYEKZNG","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_16","alias_value":"EGUUMIYEKZNGUVUU","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_8","alias_value":"EGUUMIYE","created_at":"2026-05-18T12:31:12.930513+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/EGUUMIYEKZNGUVUUTAP5H7NIAG","json":"https://pith.science/pith/EGUUMIYEKZNGUVUUTAP5H7NIAG.json","graph_json":"https://pith.science/api/pith-number/EGUUMIYEKZNGUVUUTAP5H7NIAG/graph.json","events_json":"https://pith.science/api/pith-number/EGUUMIYEKZNGUVUUTAP5H7NIAG/events.json","paper":"https://pith.science/paper/EGUUMIYE"},"agent_actions":{"view_html":"https://pith.science/pith/EGUUMIYEKZNGUVUUTAP5H7NIAG","download_json":"https://pith.science/pith/EGUUMIYEKZNGUVUUTAP5H7NIAG.json","view_paper":"https://pith.science/paper/EGUUMIYE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.00244&json=true","fetch_graph":"https://pith.science/api/pith-number/EGUUMIYEKZNGUVUUTAP5H7NIAG/graph.json","fetch_events":"https://pith.science/api/pith-number/EGUUMIYEKZNGUVUUTAP5H7NIAG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EGUUMIYEKZNGUVUUTAP5H7NIAG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EGUUMIYEKZNGUVUUTAP5H7NIAG/action/storage_attestation","attest_author":"https://pith.science/pith/EGUUMIYEKZNGUVUUTAP5H7NIAG/action/author_attestation","sign_citation":"https://pith.science/pith/EGUUMIYEKZNGUVUUTAP5H7NIAG/action/citation_signature","submit_replication":"https://pith.science/pith/EGUUMIYEKZNGUVUUTAP5H7NIAG/action/replication_record"}},"created_at":"2026-05-18T00:29:06.807674+00:00","updated_at":"2026-05-18T00:29:06.807674+00:00"}