{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:PCRXLYJYXD4AOPT5BFRTABLPBJ","short_pith_number":"pith:PCRXLYJY","schema_version":"1.0","canonical_sha256":"78a375e138b8f8073e7d096330056f0a727dd10173014647a7db16f43248123d","source":{"kind":"arxiv","id":"1702.08563","version":3},"attestation_state":"computed","paper":{"title":"Soft Label Memorization-Generalization for Natural Language Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hao Wu, Hong Yu, John P. Lalor","submitted_at":"2017-02-27T22:25:45Z","abstract_excerpt":"Often when multiple labels are obtained for a training example it is assumed that there is an element of noise that must be accounted for. It has been shown that this disagreement can be considered signal instead of noise. In this work we investigate using soft labels for training data to improve generalization in machine learning models. However, using soft labels for training Deep Neural Networks (DNNs) is not practical due to the costs involved in obtaining multiple labels for large data sets. We propose soft label memorization-generalization (SLMG), a fine-tuning approach to using soft lab"},"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":"1702.08563","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-02-27T22:25:45Z","cross_cats_sorted":[],"title_canon_sha256":"8c91bef96863dd593f0584e2dc4118ab8c3089b3d7bed841a1c3a75db138be48","abstract_canon_sha256":"4b2d1be7fc7ebd8226979ba362fb0424390041d48e1ad9df5d9b270077662c6e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:34.782156Z","signature_b64":"JVAe8XXWXDbWT7YMCCwTqlHNQ0dcK7XTKiGfZrTy6i4am7SXMFmhsXDiCJDeCUa02Wg5wgFyx7RwAbSFCyxyDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78a375e138b8f8073e7d096330056f0a727dd10173014647a7db16f43248123d","last_reissued_at":"2026-05-17T23:55:34.781689Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:34.781689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Soft Label Memorization-Generalization for Natural Language Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hao Wu, Hong Yu, John P. Lalor","submitted_at":"2017-02-27T22:25:45Z","abstract_excerpt":"Often when multiple labels are obtained for a training example it is assumed that there is an element of noise that must be accounted for. It has been shown that this disagreement can be considered signal instead of noise. In this work we investigate using soft labels for training data to improve generalization in machine learning models. However, using soft labels for training Deep Neural Networks (DNNs) is not practical due to the costs involved in obtaining multiple labels for large data sets. We propose soft label memorization-generalization (SLMG), a fine-tuning approach to using soft lab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.08563","kind":"arxiv","version":3},"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":"1702.08563","created_at":"2026-05-17T23:55:34.781770+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.08563v3","created_at":"2026-05-17T23:55:34.781770+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.08563","created_at":"2026-05-17T23:55:34.781770+00:00"},{"alias_kind":"pith_short_12","alias_value":"PCRXLYJYXD4A","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_16","alias_value":"PCRXLYJYXD4AOPT5","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_8","alias_value":"PCRXLYJY","created_at":"2026-05-18T12:31:37.085036+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01168","citing_title":"Quantifying and Predicting Disagreement in Graded Human Ratings","ref_index":140,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18069","citing_title":"Modeling Human Perspectives with Socio-Demographic Representations","ref_index":125,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PCRXLYJYXD4AOPT5BFRTABLPBJ","json":"https://pith.science/pith/PCRXLYJYXD4AOPT5BFRTABLPBJ.json","graph_json":"https://pith.science/api/pith-number/PCRXLYJYXD4AOPT5BFRTABLPBJ/graph.json","events_json":"https://pith.science/api/pith-number/PCRXLYJYXD4AOPT5BFRTABLPBJ/events.json","paper":"https://pith.science/paper/PCRXLYJY"},"agent_actions":{"view_html":"https://pith.science/pith/PCRXLYJYXD4AOPT5BFRTABLPBJ","download_json":"https://pith.science/pith/PCRXLYJYXD4AOPT5BFRTABLPBJ.json","view_paper":"https://pith.science/paper/PCRXLYJY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.08563&json=true","fetch_graph":"https://pith.science/api/pith-number/PCRXLYJYXD4AOPT5BFRTABLPBJ/graph.json","fetch_events":"https://pith.science/api/pith-number/PCRXLYJYXD4AOPT5BFRTABLPBJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PCRXLYJYXD4AOPT5BFRTABLPBJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PCRXLYJYXD4AOPT5BFRTABLPBJ/action/storage_attestation","attest_author":"https://pith.science/pith/PCRXLYJYXD4AOPT5BFRTABLPBJ/action/author_attestation","sign_citation":"https://pith.science/pith/PCRXLYJYXD4AOPT5BFRTABLPBJ/action/citation_signature","submit_replication":"https://pith.science/pith/PCRXLYJYXD4AOPT5BFRTABLPBJ/action/replication_record"}},"created_at":"2026-05-17T23:55:34.781770+00:00","updated_at":"2026-05-17T23:55:34.781770+00:00"}