{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2013:5WKLBOGKRXMN65BGFEFJWMBOL4","short_pith_number":"pith:5WKLBOGK","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"},"canonical_sha256":"ed94b0b8ca8dd8df7426290a9b302e5f3fd97fa3bb334dc1046b6bc91d3c5826","source":{"kind":"arxiv","id":"1306.0239","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1306.0239","created_at":"2026-05-18T02:26:39Z"},{"alias_kind":"arxiv_version","alias_value":"1306.0239v4","created_at":"2026-05-18T02:26:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1306.0239","created_at":"2026-05-18T02:26:39Z"},{"alias_kind":"pith_short_12","alias_value":"5WKLBOGKRXMN","created_at":"2026-05-18T12:27:34Z"},{"alias_kind":"pith_short_16","alias_value":"5WKLBOGKRXMN65BG","created_at":"2026-05-18T12:27:34Z"},{"alias_kind":"pith_short_8","alias_value":"5WKLBOGK","created_at":"2026-05-18T12:27:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2013:5WKLBOGKRXMN65BGFEFJWMBOL4","target":"record","payload":{"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"},"canonical_sha256":"ed94b0b8ca8dd8df7426290a9b302e5f3fd97fa3bb334dc1046b6bc91d3c5826","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"},"source_kind":"arxiv","source_id":"1306.0239","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:26:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v8mXDnOyNfz0kSN4jLAzQ55xGkVRK5Ve5f9kwe0lCM2veBTI6W96jcfF+bO6S0iLANzhzy9jrftZtW4+iuS5Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T00:46:21.352390Z"},"content_sha256":"3ce0c5d173207ebfe27ac96ea7718a4d145890ec7847a4de354525bd3837442a","schema_version":"1.0","event_id":"sha256:3ce0c5d173207ebfe27ac96ea7718a4d145890ec7847a4de354525bd3837442a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2013:5WKLBOGKRXMN65BGFEFJWMBOL4","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:26:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rwn7IYR23TFw4RT6QuNQKb38Yn0j/fNGMtGuHqx4nhb4thTIplinOfEWZU142qw8/p2yqVId8Zd5I4Nj71V5Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T00:46:21.352999Z"},"content_sha256":"dee3f525269aeb7465bfce05de29399722197862b8d9ecc8503c2fe30d3a9454","schema_version":"1.0","event_id":"sha256:dee3f525269aeb7465bfce05de29399722197862b8d9ecc8503c2fe30d3a9454"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5WKLBOGKRXMN65BGFEFJWMBOL4/bundle.json","state_url":"https://pith.science/pith/5WKLBOGKRXMN65BGFEFJWMBOL4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5WKLBOGKRXMN65BGFEFJWMBOL4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-04T00:46:21Z","links":{"resolver":"https://pith.science/pith/5WKLBOGKRXMN65BGFEFJWMBOL4","bundle":"https://pith.science/pith/5WKLBOGKRXMN65BGFEFJWMBOL4/bundle.json","state":"https://pith.science/pith/5WKLBOGKRXMN65BGFEFJWMBOL4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5WKLBOGKRXMN65BGFEFJWMBOL4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:5WKLBOGKRXMN65BGFEFJWMBOL4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2962be758dccdec058c53e92ec86e8b842b7f44d7fa124ae3a2c6c73900f3a54","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-06-02T18:46:58Z","title_canon_sha256":"c544fc5482b7438a02ddbeaf7e3305b76d52029a2032732d53e74e60b7f17a20"},"schema_version":"1.0","source":{"id":"1306.0239","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1306.0239","created_at":"2026-05-18T02:26:39Z"},{"alias_kind":"arxiv_version","alias_value":"1306.0239v4","created_at":"2026-05-18T02:26:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1306.0239","created_at":"2026-05-18T02:26:39Z"},{"alias_kind":"pith_short_12","alias_value":"5WKLBOGKRXMN","created_at":"2026-05-18T12:27:34Z"},{"alias_kind":"pith_short_16","alias_value":"5WKLBOGKRXMN65BG","created_at":"2026-05-18T12:27:34Z"},{"alias_kind":"pith_short_8","alias_value":"5WKLBOGK","created_at":"2026-05-18T12:27:34Z"}],"graph_snapshots":[{"event_id":"sha256:dee3f525269aeb7465bfce05de29399722197862b8d9ecc8503c2fe30d3a9454","target":"graph","created_at":"2026-05-18T02:26:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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. ","authors_text":"Yichuan Tang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-06-02T18:46:58Z","title":"Deep Learning using Linear Support Vector Machines"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1306.0239","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3ce0c5d173207ebfe27ac96ea7718a4d145890ec7847a4de354525bd3837442a","target":"record","created_at":"2026-05-18T02:26:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2962be758dccdec058c53e92ec86e8b842b7f44d7fa124ae3a2c6c73900f3a54","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-06-02T18:46:58Z","title_canon_sha256":"c544fc5482b7438a02ddbeaf7e3305b76d52029a2032732d53e74e60b7f17a20"},"schema_version":"1.0","source":{"id":"1306.0239","kind":"arxiv","version":4}},"canonical_sha256":"ed94b0b8ca8dd8df7426290a9b302e5f3fd97fa3bb334dc1046b6bc91d3c5826","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed94b0b8ca8dd8df7426290a9b302e5f3fd97fa3bb334dc1046b6bc91d3c5826","first_computed_at":"2026-05-18T02:26:39.466113Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:26:39.466113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"onwsFw8DlHluSw6trW9Mbic4t4ujenYK5o+k4YM1HEG0mO9RqxpZzTHmqpUGw3y05OqtWGsEFq5DLZy4wX8DDw==","signature_status":"signed_v1","signed_at":"2026-05-18T02:26:39.466623Z","signed_message":"canonical_sha256_bytes"},"source_id":"1306.0239","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ce0c5d173207ebfe27ac96ea7718a4d145890ec7847a4de354525bd3837442a","sha256:dee3f525269aeb7465bfce05de29399722197862b8d9ecc8503c2fe30d3a9454"],"state_sha256":"7c9ebe692d8105a39a097aa7d06256912944d2ff18ca57df46fa7f9d28ef1497"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JThtQL9OYQMoCbkdM0ZA5j1EZa7JpcECXKhyYjdmgRtf0VLABV7rR1Dft+WkTedU9fqEamYPrqrFwiJ79TMdCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T00:46:21.356377Z","bundle_sha256":"ab0b85f03f46e3af5b92bb54c7e0b63d4ed3214a3fb8588b689592593a928876"}}