{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JSO7HJP65EJQCTEM5B6JBPAQ3C","short_pith_number":"pith:JSO7HJP6","schema_version":"1.0","canonical_sha256":"4c9df3a5fee913014c8ce87c90bc10d8955056f7003fc1400534af9927cdbd24","source":{"kind":"arxiv","id":"2303.06946","version":1},"attestation_state":"computed","paper":{"title":"Context-Aware Selective Label Smoothing for Calibrating Sequence Recognition Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Jin-Gang Yu, Mengchao He, Shuangping Huang, Yongpan Wang, Yu Luo, Zhenzhou Zhuang","submitted_at":"2023-03-13T09:27:52Z","abstract_excerpt":"Despite the success of deep neural network (DNN) on sequential data (i.e., scene text and speech) recognition, it suffers from the over-confidence problem mainly due to overfitting in training with the cross-entropy loss, which may make the decision-making less reliable. Confidence calibration has been recently proposed as one effective solution to this problem. Nevertheless, the majority of existing confidence calibration methods aims at non-sequential data, which is limited if directly applied to sequential data since the intrinsic contextual dependency in sequences or the class-specific sta"},"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":"2303.06946","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-03-13T09:27:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e72cb532f5aab8ea9693e62140d7b69969699adb36db4d20f801f50bba8c2853","abstract_canon_sha256":"2536df60e967d8c7efc01464d3afeb3446d5d330375cc27992785b91e3359563"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:50:33.178240Z","signature_b64":"Ccl0T//df4IY4pN7mdYvV8VkKT1L7IVtQy4YhuQeuH0gEE/yFb/vDzp1K7xzAG6rImHiHbhyHG/L0HPPZ65pBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c9df3a5fee913014c8ce87c90bc10d8955056f7003fc1400534af9927cdbd24","last_reissued_at":"2026-07-05T05:50:33.177781Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:50:33.177781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Context-Aware Selective Label Smoothing for Calibrating Sequence Recognition Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Jin-Gang Yu, Mengchao He, Shuangping Huang, Yongpan Wang, Yu Luo, Zhenzhou Zhuang","submitted_at":"2023-03-13T09:27:52Z","abstract_excerpt":"Despite the success of deep neural network (DNN) on sequential data (i.e., scene text and speech) recognition, it suffers from the over-confidence problem mainly due to overfitting in training with the cross-entropy loss, which may make the decision-making less reliable. Confidence calibration has been recently proposed as one effective solution to this problem. Nevertheless, the majority of existing confidence calibration methods aims at non-sequential data, which is limited if directly applied to sequential data since the intrinsic contextual dependency in sequences or the class-specific sta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.06946","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/2303.06946/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":"2303.06946","created_at":"2026-07-05T05:50:33.177841+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.06946v1","created_at":"2026-07-05T05:50:33.177841+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.06946","created_at":"2026-07-05T05:50:33.177841+00:00"},{"alias_kind":"pith_short_12","alias_value":"JSO7HJP65EJQ","created_at":"2026-07-05T05:50:33.177841+00:00"},{"alias_kind":"pith_short_16","alias_value":"JSO7HJP65EJQCTEM","created_at":"2026-07-05T05:50:33.177841+00:00"},{"alias_kind":"pith_short_8","alias_value":"JSO7HJP6","created_at":"2026-07-05T05:50:33.177841+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/JSO7HJP65EJQCTEM5B6JBPAQ3C","json":"https://pith.science/pith/JSO7HJP65EJQCTEM5B6JBPAQ3C.json","graph_json":"https://pith.science/api/pith-number/JSO7HJP65EJQCTEM5B6JBPAQ3C/graph.json","events_json":"https://pith.science/api/pith-number/JSO7HJP65EJQCTEM5B6JBPAQ3C/events.json","paper":"https://pith.science/paper/JSO7HJP6"},"agent_actions":{"view_html":"https://pith.science/pith/JSO7HJP65EJQCTEM5B6JBPAQ3C","download_json":"https://pith.science/pith/JSO7HJP65EJQCTEM5B6JBPAQ3C.json","view_paper":"https://pith.science/paper/JSO7HJP6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.06946&json=true","fetch_graph":"https://pith.science/api/pith-number/JSO7HJP65EJQCTEM5B6JBPAQ3C/graph.json","fetch_events":"https://pith.science/api/pith-number/JSO7HJP65EJQCTEM5B6JBPAQ3C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JSO7HJP65EJQCTEM5B6JBPAQ3C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JSO7HJP65EJQCTEM5B6JBPAQ3C/action/storage_attestation","attest_author":"https://pith.science/pith/JSO7HJP65EJQCTEM5B6JBPAQ3C/action/author_attestation","sign_citation":"https://pith.science/pith/JSO7HJP65EJQCTEM5B6JBPAQ3C/action/citation_signature","submit_replication":"https://pith.science/pith/JSO7HJP65EJQCTEM5B6JBPAQ3C/action/replication_record"}},"created_at":"2026-07-05T05:50:33.177841+00:00","updated_at":"2026-07-05T05:50:33.177841+00:00"}