{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:4QDTIZMEUX6D2OD4AM2LNTRRTB","short_pith_number":"pith:4QDTIZME","schema_version":"1.0","canonical_sha256":"e407346584a5fc3d387c0334b6ce3198659570cdaa507648b24eaec5a217449e","source":{"kind":"arxiv","id":"1812.02676","version":2},"attestation_state":"computed","paper":{"title":"Theoretical Guarantees of Deep Embedding Losses Under Label Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jean-Marc Odobez, Nam Le","submitted_at":"2018-12-06T17:19:01Z","abstract_excerpt":"Collecting labeled data to train deep neural networks is costly and even impractical for many tasks. Thus, research effort has been focused in automatically curated datasets or unsupervised and weakly supervised learning. The common problem in these directions is learning with unreliable label information. In this paper, we address the tolerance of deep embedding learning losses against label noise, i.e. when the observed labels are different from the true labels. Specifically, we provide the sufficient conditions to achieve theoretical guarantees for the 2 common loss functions: marginal loss"},"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":"1812.02676","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-06T17:19:01Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"b70c59f424fddb94560df40719060c483dfb9f14134fc3d9cb4aa6f81c9f8d98","abstract_canon_sha256":"e7dcbfacf3ef766ae59c629b6978c5306153fb6a3a7b2cb9fee91de6519d6553"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:06.056556Z","signature_b64":"ioEIp1Y7A06kF4/V/f/XfEgeNUes0jQvHPgxFJ1H3uPsiHFIi/iLMBWewxg4bxBAdkT3buOlygTmXx+42Xy/Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e407346584a5fc3d387c0334b6ce3198659570cdaa507648b24eaec5a217449e","last_reissued_at":"2026-05-17T23:57:06.055972Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:06.055972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Theoretical Guarantees of Deep Embedding Losses Under Label Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jean-Marc Odobez, Nam Le","submitted_at":"2018-12-06T17:19:01Z","abstract_excerpt":"Collecting labeled data to train deep neural networks is costly and even impractical for many tasks. Thus, research effort has been focused in automatically curated datasets or unsupervised and weakly supervised learning. The common problem in these directions is learning with unreliable label information. In this paper, we address the tolerance of deep embedding learning losses against label noise, i.e. when the observed labels are different from the true labels. Specifically, we provide the sufficient conditions to achieve theoretical guarantees for the 2 common loss functions: marginal loss"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.02676","kind":"arxiv","version":2},"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":"1812.02676","created_at":"2026-05-17T23:57:06.056078+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.02676v2","created_at":"2026-05-17T23:57:06.056078+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.02676","created_at":"2026-05-17T23:57:06.056078+00:00"},{"alias_kind":"pith_short_12","alias_value":"4QDTIZMEUX6D","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"4QDTIZMEUX6D2OD4","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"4QDTIZME","created_at":"2026-05-18T12:32:05.422762+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/4QDTIZMEUX6D2OD4AM2LNTRRTB","json":"https://pith.science/pith/4QDTIZMEUX6D2OD4AM2LNTRRTB.json","graph_json":"https://pith.science/api/pith-number/4QDTIZMEUX6D2OD4AM2LNTRRTB/graph.json","events_json":"https://pith.science/api/pith-number/4QDTIZMEUX6D2OD4AM2LNTRRTB/events.json","paper":"https://pith.science/paper/4QDTIZME"},"agent_actions":{"view_html":"https://pith.science/pith/4QDTIZMEUX6D2OD4AM2LNTRRTB","download_json":"https://pith.science/pith/4QDTIZMEUX6D2OD4AM2LNTRRTB.json","view_paper":"https://pith.science/paper/4QDTIZME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.02676&json=true","fetch_graph":"https://pith.science/api/pith-number/4QDTIZMEUX6D2OD4AM2LNTRRTB/graph.json","fetch_events":"https://pith.science/api/pith-number/4QDTIZMEUX6D2OD4AM2LNTRRTB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4QDTIZMEUX6D2OD4AM2LNTRRTB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4QDTIZMEUX6D2OD4AM2LNTRRTB/action/storage_attestation","attest_author":"https://pith.science/pith/4QDTIZMEUX6D2OD4AM2LNTRRTB/action/author_attestation","sign_citation":"https://pith.science/pith/4QDTIZMEUX6D2OD4AM2LNTRRTB/action/citation_signature","submit_replication":"https://pith.science/pith/4QDTIZMEUX6D2OD4AM2LNTRRTB/action/replication_record"}},"created_at":"2026-05-17T23:57:06.056078+00:00","updated_at":"2026-05-17T23:57:06.056078+00:00"}