{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:X2E5IWPDMP5PQKRI5QLECCYXSD","short_pith_number":"pith:X2E5IWPD","schema_version":"1.0","canonical_sha256":"be89d459e363faf82a28ec16410b1790d8043be5fd7e33cb5ca6a7991e818f1f","source":{"kind":"arxiv","id":"2004.02070","version":2},"attestation_state":"computed","paper":{"title":"ReADS: A Rectified Attentional Double Supervised Network for Scene Text Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Nan Li, Qianyi Jiang, Qi Song, Rui Zhang, Xiaolin Wei","submitted_at":"2020-04-05T02:05:35Z","abstract_excerpt":"In recent years, scene text recognition is always regarded as a sequence-to-sequence problem. Connectionist Temporal Classification (CTC) and Attentional sequence recognition (Attn) are two very prevailing approaches to tackle this problem while they may fail in some scenarios respectively. CTC concentrates more on every individual character but is weak in text semantic dependency modeling. Attn based methods have better context semantic modeling ability while tends to overfit on limited training data. In this paper, we elaborately design a Rectified Attentional Double Supervised Network (ReAD"},"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":"2004.02070","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-05T02:05:35Z","cross_cats_sorted":[],"title_canon_sha256":"e7d65fbe463c7a62b3434ae9b54c50895498d267b47f4b114076532943a6c5a1","abstract_canon_sha256":"884bc865122e0d879f38e781f700a42c0170d00ca7d0c1303857fad2b366cfd7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:53:21.134690Z","signature_b64":"mrbGKD+6qZtzD2Gk/R+YpNqE0M9Rj+abFwb5V4tbLQXkWQweolB/ph751RtyLUobGG40UBnMcVAJ9WexE3t3CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be89d459e363faf82a28ec16410b1790d8043be5fd7e33cb5ca6a7991e818f1f","last_reissued_at":"2026-07-05T00:53:21.134356Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:53:21.134356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReADS: A Rectified Attentional Double Supervised Network for Scene Text Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Nan Li, Qianyi Jiang, Qi Song, Rui Zhang, Xiaolin Wei","submitted_at":"2020-04-05T02:05:35Z","abstract_excerpt":"In recent years, scene text recognition is always regarded as a sequence-to-sequence problem. Connectionist Temporal Classification (CTC) and Attentional sequence recognition (Attn) are two very prevailing approaches to tackle this problem while they may fail in some scenarios respectively. CTC concentrates more on every individual character but is weak in text semantic dependency modeling. Attn based methods have better context semantic modeling ability while tends to overfit on limited training data. In this paper, we elaborately design a Rectified Attentional Double Supervised Network (ReAD"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.02070","kind":"arxiv","version":2},"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/2004.02070/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":"2004.02070","created_at":"2026-07-05T00:53:21.134409+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.02070v2","created_at":"2026-07-05T00:53:21.134409+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.02070","created_at":"2026-07-05T00:53:21.134409+00:00"},{"alias_kind":"pith_short_12","alias_value":"X2E5IWPDMP5P","created_at":"2026-07-05T00:53:21.134409+00:00"},{"alias_kind":"pith_short_16","alias_value":"X2E5IWPDMP5PQKRI","created_at":"2026-07-05T00:53:21.134409+00:00"},{"alias_kind":"pith_short_8","alias_value":"X2E5IWPD","created_at":"2026-07-05T00:53:21.134409+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07733","citing_title":"A Self-Supervised Approach for Minimal-Annotation Hydroacoustic Data Exploration","ref_index":259,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X2E5IWPDMP5PQKRI5QLECCYXSD","json":"https://pith.science/pith/X2E5IWPDMP5PQKRI5QLECCYXSD.json","graph_json":"https://pith.science/api/pith-number/X2E5IWPDMP5PQKRI5QLECCYXSD/graph.json","events_json":"https://pith.science/api/pith-number/X2E5IWPDMP5PQKRI5QLECCYXSD/events.json","paper":"https://pith.science/paper/X2E5IWPD"},"agent_actions":{"view_html":"https://pith.science/pith/X2E5IWPDMP5PQKRI5QLECCYXSD","download_json":"https://pith.science/pith/X2E5IWPDMP5PQKRI5QLECCYXSD.json","view_paper":"https://pith.science/paper/X2E5IWPD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.02070&json=true","fetch_graph":"https://pith.science/api/pith-number/X2E5IWPDMP5PQKRI5QLECCYXSD/graph.json","fetch_events":"https://pith.science/api/pith-number/X2E5IWPDMP5PQKRI5QLECCYXSD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X2E5IWPDMP5PQKRI5QLECCYXSD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X2E5IWPDMP5PQKRI5QLECCYXSD/action/storage_attestation","attest_author":"https://pith.science/pith/X2E5IWPDMP5PQKRI5QLECCYXSD/action/author_attestation","sign_citation":"https://pith.science/pith/X2E5IWPDMP5PQKRI5QLECCYXSD/action/citation_signature","submit_replication":"https://pith.science/pith/X2E5IWPDMP5PQKRI5QLECCYXSD/action/replication_record"}},"created_at":"2026-07-05T00:53:21.134409+00:00","updated_at":"2026-07-05T00:53:21.134409+00:00"}