{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:4HPYVXDRZAEMTZBR2SEVOBBQL6","short_pith_number":"pith:4HPYVXDR","schema_version":"1.0","canonical_sha256":"e1df8adc71c808c9e431d4895704305f9cd3a6ff95ad42119885b0d8cf39c9f2","source":{"kind":"arxiv","id":"1505.05354","version":1},"attestation_state":"computed","paper":{"title":"DropSample: A New Training Method to Enhance Deep Convolutional Neural Networks for Large-Scale Unconstrained Handwritten Chinese Character Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dacheng Tao, Lianwen Jin, Weixin Yang, Zecheng Xie, Ziyong Feng","submitted_at":"2015-05-20T13:08:57Z","abstract_excerpt":"Inspired by the theory of Leitners learning box from the field of psychology, we propose DropSample, a new method for training deep convolutional neural networks (DCNNs), and apply it to large-scale online handwritten Chinese character recognition (HCCR). According to the principle of DropSample, each training sample is associated with a quota function that is dynamically adjusted on the basis of the classification confidence given by the DCNN softmax output. After a learning iteration, samples with low confidence will have a higher probability of being selected as training data in the next it"},"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":"1505.05354","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-05-20T13:08:57Z","cross_cats_sorted":[],"title_canon_sha256":"495f4125f140ba04039ce1f44dcfb048e14b7f8866da80a7888fe7cb6541f1fe","abstract_canon_sha256":"62dc19dd65d7b464b586a91c01da40e2b636e8f37b5b2accbc125013d5ae812a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:03:56.726724Z","signature_b64":"Pg/+EPAdOOKegS8We1USD6PQ7WkvupV6tMwY23RvH7+o3LPR4CUxUgeCuUZvI6prCgms3BEEsryhp0BbjnVTDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1df8adc71c808c9e431d4895704305f9cd3a6ff95ad42119885b0d8cf39c9f2","last_reissued_at":"2026-05-18T02:03:56.726036Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:03:56.726036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DropSample: A New Training Method to Enhance Deep Convolutional Neural Networks for Large-Scale Unconstrained Handwritten Chinese Character Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dacheng Tao, Lianwen Jin, Weixin Yang, Zecheng Xie, Ziyong Feng","submitted_at":"2015-05-20T13:08:57Z","abstract_excerpt":"Inspired by the theory of Leitners learning box from the field of psychology, we propose DropSample, a new method for training deep convolutional neural networks (DCNNs), and apply it to large-scale online handwritten Chinese character recognition (HCCR). According to the principle of DropSample, each training sample is associated with a quota function that is dynamically adjusted on the basis of the classification confidence given by the DCNN softmax output. After a learning iteration, samples with low confidence will have a higher probability of being selected as training data in the next it"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1505.05354","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":"1505.05354","created_at":"2026-05-18T02:03:56.726145+00:00"},{"alias_kind":"arxiv_version","alias_value":"1505.05354v1","created_at":"2026-05-18T02:03:56.726145+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1505.05354","created_at":"2026-05-18T02:03:56.726145+00:00"},{"alias_kind":"pith_short_12","alias_value":"4HPYVXDRZAEM","created_at":"2026-05-18T12:29:05.191682+00:00"},{"alias_kind":"pith_short_16","alias_value":"4HPYVXDRZAEMTZBR","created_at":"2026-05-18T12:29:05.191682+00:00"},{"alias_kind":"pith_short_8","alias_value":"4HPYVXDR","created_at":"2026-05-18T12:29:05.191682+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/4HPYVXDRZAEMTZBR2SEVOBBQL6","json":"https://pith.science/pith/4HPYVXDRZAEMTZBR2SEVOBBQL6.json","graph_json":"https://pith.science/api/pith-number/4HPYVXDRZAEMTZBR2SEVOBBQL6/graph.json","events_json":"https://pith.science/api/pith-number/4HPYVXDRZAEMTZBR2SEVOBBQL6/events.json","paper":"https://pith.science/paper/4HPYVXDR"},"agent_actions":{"view_html":"https://pith.science/pith/4HPYVXDRZAEMTZBR2SEVOBBQL6","download_json":"https://pith.science/pith/4HPYVXDRZAEMTZBR2SEVOBBQL6.json","view_paper":"https://pith.science/paper/4HPYVXDR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1505.05354&json=true","fetch_graph":"https://pith.science/api/pith-number/4HPYVXDRZAEMTZBR2SEVOBBQL6/graph.json","fetch_events":"https://pith.science/api/pith-number/4HPYVXDRZAEMTZBR2SEVOBBQL6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4HPYVXDRZAEMTZBR2SEVOBBQL6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4HPYVXDRZAEMTZBR2SEVOBBQL6/action/storage_attestation","attest_author":"https://pith.science/pith/4HPYVXDRZAEMTZBR2SEVOBBQL6/action/author_attestation","sign_citation":"https://pith.science/pith/4HPYVXDRZAEMTZBR2SEVOBBQL6/action/citation_signature","submit_replication":"https://pith.science/pith/4HPYVXDRZAEMTZBR2SEVOBBQL6/action/replication_record"}},"created_at":"2026-05-18T02:03:56.726145+00:00","updated_at":"2026-05-18T02:03:56.726145+00:00"}