{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:5WKLBOGKRXMN65BGFEFJWMBOL4","short_pith_number":"pith:5WKLBOGK","schema_version":"1.0","canonical_sha256":"ed94b0b8ca8dd8df7426290a9b302e5f3fd97fa3bb334dc1046b6bc91d3c5826","source":{"kind":"arxiv","id":"1306.0239","version":4},"attestation_state":"computed","paper":{"title":"Deep Learning using Linear Support Vector Machines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Yichuan Tang","submitted_at":"2013-06-02T18:46:58Z","abstract_excerpt":"Recently, fully-connected and convolutional neural networks have been trained to achieve state-of-the-art performance on a wide variety of tasks such as speech recognition, image classification, natural language processing, and bioinformatics. For classification tasks, most of these \"deep learning\" models employ the softmax activation function for prediction and minimize cross-entropy loss. In this paper, we demonstrate a small but consistent advantage of replacing the softmax layer with a linear support vector machine. Learning minimizes a margin-based loss instead of the cross-entropy 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":"1306.0239","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-06-02T18:46:58Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c544fc5482b7438a02ddbeaf7e3305b76d52029a2032732d53e74e60b7f17a20","abstract_canon_sha256":"2962be758dccdec058c53e92ec86e8b842b7f44d7fa124ae3a2c6c73900f3a54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:26:39.466623Z","signature_b64":"onwsFw8DlHluSw6trW9Mbic4t4ujenYK5o+k4YM1HEG0mO9RqxpZzTHmqpUGw3y05OqtWGsEFq5DLZy4wX8DDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed94b0b8ca8dd8df7426290a9b302e5f3fd97fa3bb334dc1046b6bc91d3c5826","last_reissued_at":"2026-05-18T02:26:39.466113Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:26:39.466113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Learning using Linear Support Vector Machines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Yichuan Tang","submitted_at":"2013-06-02T18:46:58Z","abstract_excerpt":"Recently, fully-connected and convolutional neural networks have been trained to achieve state-of-the-art performance on a wide variety of tasks such as speech recognition, image classification, natural language processing, and bioinformatics. For classification tasks, most of these \"deep learning\" models employ the softmax activation function for prediction and minimize cross-entropy loss. In this paper, we demonstrate a small but consistent advantage of replacing the softmax layer with a linear support vector machine. Learning minimizes a margin-based loss instead of the cross-entropy loss. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1306.0239","kind":"arxiv","version":4},"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":"1306.0239","created_at":"2026-05-18T02:26:39.466191+00:00"},{"alias_kind":"arxiv_version","alias_value":"1306.0239v4","created_at":"2026-05-18T02:26:39.466191+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1306.0239","created_at":"2026-05-18T02:26:39.466191+00:00"},{"alias_kind":"pith_short_12","alias_value":"5WKLBOGKRXMN","created_at":"2026-05-18T12:27:34.582898+00:00"},{"alias_kind":"pith_short_16","alias_value":"5WKLBOGKRXMN65BG","created_at":"2026-05-18T12:27:34.582898+00:00"},{"alias_kind":"pith_short_8","alias_value":"5WKLBOGK","created_at":"2026-05-18T12:27:34.582898+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.06800","citing_title":"Graph Interpolating Activation Improves Both Natural and Robust Accuracies in Data-Efficient Deep Learning","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"1803.08375","citing_title":"Deep Learning using Rectified Linear Units (ReLU)","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5WKLBOGKRXMN65BGFEFJWMBOL4","json":"https://pith.science/pith/5WKLBOGKRXMN65BGFEFJWMBOL4.json","graph_json":"https://pith.science/api/pith-number/5WKLBOGKRXMN65BGFEFJWMBOL4/graph.json","events_json":"https://pith.science/api/pith-number/5WKLBOGKRXMN65BGFEFJWMBOL4/events.json","paper":"https://pith.science/paper/5WKLBOGK"},"agent_actions":{"view_html":"https://pith.science/pith/5WKLBOGKRXMN65BGFEFJWMBOL4","download_json":"https://pith.science/pith/5WKLBOGKRXMN65BGFEFJWMBOL4.json","view_paper":"https://pith.science/paper/5WKLBOGK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1306.0239&json=true","fetch_graph":"https://pith.science/api/pith-number/5WKLBOGKRXMN65BGFEFJWMBOL4/graph.json","fetch_events":"https://pith.science/api/pith-number/5WKLBOGKRXMN65BGFEFJWMBOL4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5WKLBOGKRXMN65BGFEFJWMBOL4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5WKLBOGKRXMN65BGFEFJWMBOL4/action/storage_attestation","attest_author":"https://pith.science/pith/5WKLBOGKRXMN65BGFEFJWMBOL4/action/author_attestation","sign_citation":"https://pith.science/pith/5WKLBOGKRXMN65BGFEFJWMBOL4/action/citation_signature","submit_replication":"https://pith.science/pith/5WKLBOGKRXMN65BGFEFJWMBOL4/action/replication_record"}},"created_at":"2026-05-18T02:26:39.466191+00:00","updated_at":"2026-05-18T02:26:39.466191+00:00"}