{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CHRQ26EMBBT6A2XUYZ3TIKLTR5","short_pith_number":"pith:CHRQ26EM","schema_version":"1.0","canonical_sha256":"11e30d788c0867e06af4c6773429738f4d3cde97aa39d553718b084ef1f2a05a","source":{"kind":"arxiv","id":"2206.11589","version":1},"attestation_state":"computed","paper":{"title":"Learning Towards the Largest Margins","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Deming Zhai, Junjun Jiang, Xiangyang Ji, Xianming Liu, Xin Gao, Xiong Zhou","submitted_at":"2022-06-23T10:03:03Z","abstract_excerpt":"One of the main challenges for feature representation in deep learning-based classification is the design of appropriate loss functions that exhibit strong discriminative power. The classical softmax loss does not explicitly encourage discriminative learning of features. A popular direction of research is to incorporate margins in well-established losses in order to enforce extra intra-class compactness and inter-class separability, which, however, were developed through heuristic means, as opposed to rigorous mathematical principles. In this work, we attempt to address this limitation by form"},"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":"2206.11589","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-23T10:03:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"05b9c3f25b2800cd6df3f72d2d9b1e4268ec4230aea02bf596f7819ce6dd7c61","abstract_canon_sha256":"c1315fc1469078b99d1e4dc8c3b7e5d37403cba646bc467c46d8b68dae5fb5dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:34:21.563548Z","signature_b64":"b72GfOZen3aLNYz8D22wnJsKHewBXfSZqsNUAXonXEgdOq5UZg8oF8qQfbtFug1AhQcJR0tXBmOX6zTe8JkgAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11e30d788c0867e06af4c6773429738f4d3cde97aa39d553718b084ef1f2a05a","last_reissued_at":"2026-07-05T04:34:21.563157Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:34:21.563157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Towards the Largest Margins","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Deming Zhai, Junjun Jiang, Xiangyang Ji, Xianming Liu, Xin Gao, Xiong Zhou","submitted_at":"2022-06-23T10:03:03Z","abstract_excerpt":"One of the main challenges for feature representation in deep learning-based classification is the design of appropriate loss functions that exhibit strong discriminative power. The classical softmax loss does not explicitly encourage discriminative learning of features. A popular direction of research is to incorporate margins in well-established losses in order to enforce extra intra-class compactness and inter-class separability, which, however, were developed through heuristic means, as opposed to rigorous mathematical principles. In this work, we attempt to address this limitation by form"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.11589","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2206.11589/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2206.11589","created_at":"2026-07-05T04:34:21.563209+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.11589v1","created_at":"2026-07-05T04:34:21.563209+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.11589","created_at":"2026-07-05T04:34:21.563209+00:00"},{"alias_kind":"pith_short_12","alias_value":"CHRQ26EMBBT6","created_at":"2026-07-05T04:34:21.563209+00:00"},{"alias_kind":"pith_short_16","alias_value":"CHRQ26EMBBT6A2XU","created_at":"2026-07-05T04:34:21.563209+00:00"},{"alias_kind":"pith_short_8","alias_value":"CHRQ26EM","created_at":"2026-07-05T04:34:21.563209+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/CHRQ26EMBBT6A2XUYZ3TIKLTR5","json":"https://pith.science/pith/CHRQ26EMBBT6A2XUYZ3TIKLTR5.json","graph_json":"https://pith.science/api/pith-number/CHRQ26EMBBT6A2XUYZ3TIKLTR5/graph.json","events_json":"https://pith.science/api/pith-number/CHRQ26EMBBT6A2XUYZ3TIKLTR5/events.json","paper":"https://pith.science/paper/CHRQ26EM"},"agent_actions":{"view_html":"https://pith.science/pith/CHRQ26EMBBT6A2XUYZ3TIKLTR5","download_json":"https://pith.science/pith/CHRQ26EMBBT6A2XUYZ3TIKLTR5.json","view_paper":"https://pith.science/paper/CHRQ26EM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.11589&json=true","fetch_graph":"https://pith.science/api/pith-number/CHRQ26EMBBT6A2XUYZ3TIKLTR5/graph.json","fetch_events":"https://pith.science/api/pith-number/CHRQ26EMBBT6A2XUYZ3TIKLTR5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CHRQ26EMBBT6A2XUYZ3TIKLTR5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CHRQ26EMBBT6A2XUYZ3TIKLTR5/action/storage_attestation","attest_author":"https://pith.science/pith/CHRQ26EMBBT6A2XUYZ3TIKLTR5/action/author_attestation","sign_citation":"https://pith.science/pith/CHRQ26EMBBT6A2XUYZ3TIKLTR5/action/citation_signature","submit_replication":"https://pith.science/pith/CHRQ26EMBBT6A2XUYZ3TIKLTR5/action/replication_record"}},"created_at":"2026-07-05T04:34:21.563209+00:00","updated_at":"2026-07-05T04:34:21.563209+00:00"}