{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:CFEXDO7IEIL2XJJPGTYJHJRBOK","short_pith_number":"pith:CFEXDO7I","schema_version":"1.0","canonical_sha256":"114971bbe82217aba52f34f093a62172848241ab5513c620f70a83941d506608","source":{"kind":"arxiv","id":"1801.01687","version":1},"attestation_state":"computed","paper":{"title":"Accelerated Training for Massive Classification via Dynamic Class Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dahua Lin, Junjie Yan, Lei Yang, Xingcheng Zhang","submitted_at":"2018-01-05T10:11:53Z","abstract_excerpt":"Massive classification, a classification task defined over a vast number of classes (hundreds of thousands or even millions), has become an essential part of many real-world systems, such as face recognition. Existing methods, including the deep networks that achieved remarkable success in recent years, were mostly devised for problems with a moderate number of classes. They would meet with substantial difficulties, e.g. excessive memory demand and computational cost, when applied to massive problems. We present a new method to tackle this problem. This method can efficiently and accurately id"},"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":"1801.01687","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-01-05T10:11:53Z","cross_cats_sorted":[],"title_canon_sha256":"0bce908d12e64ffea810c13f1a90dfdb1bbbbf0e7b528aab33248c2ce4cb5248","abstract_canon_sha256":"837c4ba8004307a8e87ec373728a2fc869c5f383737b093b9d698fa07be512da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:26:41.386135Z","signature_b64":"cXmuGtI8wzRk61kw/GKWW6lX2C83eGvZGfJtedEon6S3I3Vrr05yJGLfRfEUiTI1AmP8F7VQ3RGP8NigMXUuBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"114971bbe82217aba52f34f093a62172848241ab5513c620f70a83941d506608","last_reissued_at":"2026-05-18T00:26:41.385596Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:26:41.385596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accelerated Training for Massive Classification via Dynamic Class Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dahua Lin, Junjie Yan, Lei Yang, Xingcheng Zhang","submitted_at":"2018-01-05T10:11:53Z","abstract_excerpt":"Massive classification, a classification task defined over a vast number of classes (hundreds of thousands or even millions), has become an essential part of many real-world systems, such as face recognition. Existing methods, including the deep networks that achieved remarkable success in recent years, were mostly devised for problems with a moderate number of classes. They would meet with substantial difficulties, e.g. excessive memory demand and computational cost, when applied to massive problems. We present a new method to tackle this problem. This method can efficiently and accurately id"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.01687","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":""},"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":"1801.01687","created_at":"2026-05-18T00:26:41.385669+00:00"},{"alias_kind":"arxiv_version","alias_value":"1801.01687v1","created_at":"2026-05-18T00:26:41.385669+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.01687","created_at":"2026-05-18T00:26:41.385669+00:00"},{"alias_kind":"pith_short_12","alias_value":"CFEXDO7IEIL2","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_16","alias_value":"CFEXDO7IEIL2XJJP","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_8","alias_value":"CFEXDO7I","created_at":"2026-05-18T12:32:16.446611+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2511.10834","citing_title":"EarthSight: A Distributed Framework for Low-Latency Satellite Intelligence","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CFEXDO7IEIL2XJJPGTYJHJRBOK","json":"https://pith.science/pith/CFEXDO7IEIL2XJJPGTYJHJRBOK.json","graph_json":"https://pith.science/api/pith-number/CFEXDO7IEIL2XJJPGTYJHJRBOK/graph.json","events_json":"https://pith.science/api/pith-number/CFEXDO7IEIL2XJJPGTYJHJRBOK/events.json","paper":"https://pith.science/paper/CFEXDO7I"},"agent_actions":{"view_html":"https://pith.science/pith/CFEXDO7IEIL2XJJPGTYJHJRBOK","download_json":"https://pith.science/pith/CFEXDO7IEIL2XJJPGTYJHJRBOK.json","view_paper":"https://pith.science/paper/CFEXDO7I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1801.01687&json=true","fetch_graph":"https://pith.science/api/pith-number/CFEXDO7IEIL2XJJPGTYJHJRBOK/graph.json","fetch_events":"https://pith.science/api/pith-number/CFEXDO7IEIL2XJJPGTYJHJRBOK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CFEXDO7IEIL2XJJPGTYJHJRBOK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CFEXDO7IEIL2XJJPGTYJHJRBOK/action/storage_attestation","attest_author":"https://pith.science/pith/CFEXDO7IEIL2XJJPGTYJHJRBOK/action/author_attestation","sign_citation":"https://pith.science/pith/CFEXDO7IEIL2XJJPGTYJHJRBOK/action/citation_signature","submit_replication":"https://pith.science/pith/CFEXDO7IEIL2XJJPGTYJHJRBOK/action/replication_record"}},"created_at":"2026-05-18T00:26:41.385669+00:00","updated_at":"2026-05-18T00:26:41.385669+00:00"}