{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:4ANJYRJYPO6HALXSVSQHXVHSV6","short_pith_number":"pith:4ANJYRJY","schema_version":"1.0","canonical_sha256":"e01a9c45387bbc702ef2aca07bd4f2af81d7a77b320ab7f778dc94a874dae3c9","source":{"kind":"arxiv","id":"2007.04651","version":1},"attestation_state":"computed","paper":{"title":"Maximum Entropy Regularization and Chinese Text Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Feng, Changxu Cheng, Wenyu Liu, Wuheng Xu, Xiang Bai","submitted_at":"2020-07-09T09:19:56Z","abstract_excerpt":"Chinese text recognition is more challenging than Latin text due to the large amount of fine-grained Chinese characters and the great imbalance over classes, which causes a serious overfitting problem. We propose to apply Maximum Entropy Regularization to regularize the training process, which is to simply add a negative entropy term to the canonical cross-entropy loss without any additional parameters and modification of a model. We theoretically give the convergence probability distribution and analyze how the regularization influence the learning process. Experiments on Chinese character re"},"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":"2007.04651","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-09T09:19:56Z","cross_cats_sorted":[],"title_canon_sha256":"1158cb28ff57d104b5850e2c3b68a56867658624cb83d7a6c030dfa74b5231bd","abstract_canon_sha256":"01018ef78ec7cb98843a17ba4471b96de1c1e81da433f8b02ba1129a5c6ea97c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:17:32.349288Z","signature_b64":"3sfnwqvT4hl5BEkjwYxdMw1QZKgG3IuG4jvAWetAxBmycLiFx5LbH/v3v3a0dj/ZMklyO7Z+4zKXQqLrKTJcBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e01a9c45387bbc702ef2aca07bd4f2af81d7a77b320ab7f778dc94a874dae3c9","last_reissued_at":"2026-07-05T01:17:32.348910Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:17:32.348910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Maximum Entropy Regularization and Chinese Text Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Feng, Changxu Cheng, Wenyu Liu, Wuheng Xu, Xiang Bai","submitted_at":"2020-07-09T09:19:56Z","abstract_excerpt":"Chinese text recognition is more challenging than Latin text due to the large amount of fine-grained Chinese characters and the great imbalance over classes, which causes a serious overfitting problem. We propose to apply Maximum Entropy Regularization to regularize the training process, which is to simply add a negative entropy term to the canonical cross-entropy loss without any additional parameters and modification of a model. We theoretically give the convergence probability distribution and analyze how the regularization influence the learning process. Experiments on Chinese character re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.04651","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/2007.04651/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":"2007.04651","created_at":"2026-07-05T01:17:32.348964+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.04651v1","created_at":"2026-07-05T01:17:32.348964+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.04651","created_at":"2026-07-05T01:17:32.348964+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ANJYRJYPO6H","created_at":"2026-07-05T01:17:32.348964+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ANJYRJYPO6HALXS","created_at":"2026-07-05T01:17:32.348964+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ANJYRJY","created_at":"2026-07-05T01:17:32.348964+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/4ANJYRJYPO6HALXSVSQHXVHSV6","json":"https://pith.science/pith/4ANJYRJYPO6HALXSVSQHXVHSV6.json","graph_json":"https://pith.science/api/pith-number/4ANJYRJYPO6HALXSVSQHXVHSV6/graph.json","events_json":"https://pith.science/api/pith-number/4ANJYRJYPO6HALXSVSQHXVHSV6/events.json","paper":"https://pith.science/paper/4ANJYRJY"},"agent_actions":{"view_html":"https://pith.science/pith/4ANJYRJYPO6HALXSVSQHXVHSV6","download_json":"https://pith.science/pith/4ANJYRJYPO6HALXSVSQHXVHSV6.json","view_paper":"https://pith.science/paper/4ANJYRJY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.04651&json=true","fetch_graph":"https://pith.science/api/pith-number/4ANJYRJYPO6HALXSVSQHXVHSV6/graph.json","fetch_events":"https://pith.science/api/pith-number/4ANJYRJYPO6HALXSVSQHXVHSV6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ANJYRJYPO6HALXSVSQHXVHSV6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ANJYRJYPO6HALXSVSQHXVHSV6/action/storage_attestation","attest_author":"https://pith.science/pith/4ANJYRJYPO6HALXSVSQHXVHSV6/action/author_attestation","sign_citation":"https://pith.science/pith/4ANJYRJYPO6HALXSVSQHXVHSV6/action/citation_signature","submit_replication":"https://pith.science/pith/4ANJYRJYPO6HALXSVSQHXVHSV6/action/replication_record"}},"created_at":"2026-07-05T01:17:32.348964+00:00","updated_at":"2026-07-05T01:17:32.348964+00:00"}