{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:EHDTRPRO3K5EUJFQQ4HLG4RUAB","short_pith_number":"pith:EHDTRPRO","schema_version":"1.0","canonical_sha256":"21c738be2edaba4a24b0870eb372340064e523a11b436a3c71f72726c9d437a9","source":{"kind":"arxiv","id":"1806.10805","version":1},"attestation_state":"computed","paper":{"title":"Beyond One-hot Encoding: lower dimensional target embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jordi Gonz\\`alez, Miguel A. Bautista, Pau Rodr\\'iguez, Sergio Escalera","submitted_at":"2018-06-28T07:34:14Z","abstract_excerpt":"Target encoding plays a central role when learning Convolutional Neural Networks. In this realm, One-hot encoding is the most prevalent strategy due to its simplicity. However, this so widespread encoding schema assumes a flat label space, thus ignoring rich relationships existing among labels that can be exploited during training. In large-scale datasets, data does not span the full label space, but instead lies in a low-dimensional output manifold. Following this observation, we embed the targets into a low-dimensional space, drastically improving convergence speed while preserving accuracy."},"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":"1806.10805","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-28T07:34:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9d733823501ca19059b69520b9338597ace415e4ee818c1b725bfd0275fca8eb","abstract_canon_sha256":"32314fb51b0a7b201816bdf3d52fc2b59d6d4e288c9f8c0b06724d919a2d1309"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:07.882424Z","signature_b64":"E9lBJ5f3Le3z/ZcL2lNdK2aLVA/h0VrYRiXO+NkEXn8aWGCq877KDEPJVR4rRKtM0e6ZPxCQysGsrPpNoqIEAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21c738be2edaba4a24b0870eb372340064e523a11b436a3c71f72726c9d437a9","last_reissued_at":"2026-05-18T00:12:07.881766Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:07.881766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond One-hot Encoding: lower dimensional target embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jordi Gonz\\`alez, Miguel A. Bautista, Pau Rodr\\'iguez, Sergio Escalera","submitted_at":"2018-06-28T07:34:14Z","abstract_excerpt":"Target encoding plays a central role when learning Convolutional Neural Networks. In this realm, One-hot encoding is the most prevalent strategy due to its simplicity. However, this so widespread encoding schema assumes a flat label space, thus ignoring rich relationships existing among labels that can be exploited during training. In large-scale datasets, data does not span the full label space, but instead lies in a low-dimensional output manifold. Following this observation, we embed the targets into a low-dimensional space, drastically improving convergence speed while preserving accuracy."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.10805","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":"1806.10805","created_at":"2026-05-18T00:12:07.881865+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.10805v1","created_at":"2026-05-18T00:12:07.881865+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.10805","created_at":"2026-05-18T00:12:07.881865+00:00"},{"alias_kind":"pith_short_12","alias_value":"EHDTRPRO3K5E","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"EHDTRPRO3K5EUJFQ","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"EHDTRPRO","created_at":"2026-05-18T12:32:22.470017+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/EHDTRPRO3K5EUJFQQ4HLG4RUAB","json":"https://pith.science/pith/EHDTRPRO3K5EUJFQQ4HLG4RUAB.json","graph_json":"https://pith.science/api/pith-number/EHDTRPRO3K5EUJFQQ4HLG4RUAB/graph.json","events_json":"https://pith.science/api/pith-number/EHDTRPRO3K5EUJFQQ4HLG4RUAB/events.json","paper":"https://pith.science/paper/EHDTRPRO"},"agent_actions":{"view_html":"https://pith.science/pith/EHDTRPRO3K5EUJFQQ4HLG4RUAB","download_json":"https://pith.science/pith/EHDTRPRO3K5EUJFQQ4HLG4RUAB.json","view_paper":"https://pith.science/paper/EHDTRPRO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.10805&json=true","fetch_graph":"https://pith.science/api/pith-number/EHDTRPRO3K5EUJFQQ4HLG4RUAB/graph.json","fetch_events":"https://pith.science/api/pith-number/EHDTRPRO3K5EUJFQQ4HLG4RUAB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EHDTRPRO3K5EUJFQQ4HLG4RUAB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EHDTRPRO3K5EUJFQQ4HLG4RUAB/action/storage_attestation","attest_author":"https://pith.science/pith/EHDTRPRO3K5EUJFQQ4HLG4RUAB/action/author_attestation","sign_citation":"https://pith.science/pith/EHDTRPRO3K5EUJFQQ4HLG4RUAB/action/citation_signature","submit_replication":"https://pith.science/pith/EHDTRPRO3K5EUJFQQ4HLG4RUAB/action/replication_record"}},"created_at":"2026-05-18T00:12:07.881865+00:00","updated_at":"2026-05-18T00:12:07.881865+00:00"}