{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:RUZ5Q7N3PF2TDJE34DX7OCF2Z5","short_pith_number":"pith:RUZ5Q7N3","schema_version":"1.0","canonical_sha256":"8d33d87dbb797531a49be0eff708bacf445dca1e100d423882ff534154c1fd0a","source":{"kind":"arxiv","id":"1702.07975","version":1},"attestation_state":"computed","paper":{"title":"Building Fast and Compact Convolutional Neural Networks for Offline Handwritten Chinese Character Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jun Sun, Lianwen Jin, Tianhai Chang, Weixin Yang, Xuefeng Xiao, Yafeng Yang","submitted_at":"2017-02-26T02:13:20Z","abstract_excerpt":"Like other problems in computer vision, offline handwritten Chinese character recognition (HCCR) has achieved impressive results using convolutional neural network (CNN)-based methods. However, larger and deeper networks are needed to deliver state-of-the-art results in this domain. Such networks intuitively appear to incur high computational cost, and require the storage of a large number of parameters, which renders them unfeasible for deployment in portable devices. To solve this problem, we propose a Global Supervised Low-rank Expansion (GSLRE) method and an Adaptive Drop-weight (ADW) tech"},"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":"1702.07975","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-26T02:13:20Z","cross_cats_sorted":[],"title_canon_sha256":"f49570dac12d7b37cc0245b43e214f0f325cd577ff0b5d56bf33d34f74d2e2a6","abstract_canon_sha256":"591dd12e8465dac33e932c132413091df152c55d68a87f46a576e4022c454ea7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:56.506019Z","signature_b64":"Uw8d1aYNY8CsQiMY14zfcHsj5pxxBRewwjrOpKco0yj/4N0RtWJ9kHYdjFFlsWYXTSdKFgSIFOJr0CAhiLJECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d33d87dbb797531a49be0eff708bacf445dca1e100d423882ff534154c1fd0a","last_reissued_at":"2026-05-18T00:49:56.505420Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:56.505420Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Building Fast and Compact Convolutional Neural Networks for Offline Handwritten Chinese Character Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jun Sun, Lianwen Jin, Tianhai Chang, Weixin Yang, Xuefeng Xiao, Yafeng Yang","submitted_at":"2017-02-26T02:13:20Z","abstract_excerpt":"Like other problems in computer vision, offline handwritten Chinese character recognition (HCCR) has achieved impressive results using convolutional neural network (CNN)-based methods. However, larger and deeper networks are needed to deliver state-of-the-art results in this domain. Such networks intuitively appear to incur high computational cost, and require the storage of a large number of parameters, which renders them unfeasible for deployment in portable devices. To solve this problem, we propose a Global Supervised Low-rank Expansion (GSLRE) method and an Adaptive Drop-weight (ADW) tech"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.07975","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":"1702.07975","created_at":"2026-05-18T00:49:56.505498+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.07975v1","created_at":"2026-05-18T00:49:56.505498+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.07975","created_at":"2026-05-18T00:49:56.505498+00:00"},{"alias_kind":"pith_short_12","alias_value":"RUZ5Q7N3PF2T","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_16","alias_value":"RUZ5Q7N3PF2TDJE3","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_8","alias_value":"RUZ5Q7N3","created_at":"2026-05-18T12:31:43.269735+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/RUZ5Q7N3PF2TDJE34DX7OCF2Z5","json":"https://pith.science/pith/RUZ5Q7N3PF2TDJE34DX7OCF2Z5.json","graph_json":"https://pith.science/api/pith-number/RUZ5Q7N3PF2TDJE34DX7OCF2Z5/graph.json","events_json":"https://pith.science/api/pith-number/RUZ5Q7N3PF2TDJE34DX7OCF2Z5/events.json","paper":"https://pith.science/paper/RUZ5Q7N3"},"agent_actions":{"view_html":"https://pith.science/pith/RUZ5Q7N3PF2TDJE34DX7OCF2Z5","download_json":"https://pith.science/pith/RUZ5Q7N3PF2TDJE34DX7OCF2Z5.json","view_paper":"https://pith.science/paper/RUZ5Q7N3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.07975&json=true","fetch_graph":"https://pith.science/api/pith-number/RUZ5Q7N3PF2TDJE34DX7OCF2Z5/graph.json","fetch_events":"https://pith.science/api/pith-number/RUZ5Q7N3PF2TDJE34DX7OCF2Z5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RUZ5Q7N3PF2TDJE34DX7OCF2Z5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RUZ5Q7N3PF2TDJE34DX7OCF2Z5/action/storage_attestation","attest_author":"https://pith.science/pith/RUZ5Q7N3PF2TDJE34DX7OCF2Z5/action/author_attestation","sign_citation":"https://pith.science/pith/RUZ5Q7N3PF2TDJE34DX7OCF2Z5/action/citation_signature","submit_replication":"https://pith.science/pith/RUZ5Q7N3PF2TDJE34DX7OCF2Z5/action/replication_record"}},"created_at":"2026-05-18T00:49:56.505498+00:00","updated_at":"2026-05-18T00:49:56.505498+00:00"}