{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:H6MAGZNM6AU4YAXEMCB5FKHXBF","short_pith_number":"pith:H6MAGZNM","schema_version":"1.0","canonical_sha256":"3f980365acf029cc02e46083d2a8f709720091e737d16d60fe9745782c1ebe60","source":{"kind":"arxiv","id":"2307.08723","version":2},"attestation_state":"computed","paper":{"title":"Revisiting Scene Text Recognition: A Data Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chongyu Liu, Dezhi Peng, Jiapeng Wang, Lianwen Jin, Qing Jiang","submitted_at":"2023-07-17T11:19:41Z","abstract_excerpt":"This paper aims to re-assess scene text recognition (STR) from a data-oriented perspective. We begin by revisiting the six commonly used benchmarks in STR and observe a trend of performance saturation, whereby only 2.91% of the benchmark images cannot be accurately recognized by an ensemble of 13 representative models. While these results are impressive and suggest that STR could be considered solved, however, we argue that this is primarily due to the less challenging nature of the common benchmarks, thus concealing the underlying issues that STR faces. To this end, we consolidate a large-sca"},"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":"2307.08723","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-17T11:19:41Z","cross_cats_sorted":[],"title_canon_sha256":"5e21e1e2063f1a476da8495e1bb4037f697da2ddc4c480c79949306435749722","abstract_canon_sha256":"a90c346733e565b60f7be7422914c20c92e46e2a9658889c2faa560c8ec12899"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:32:41.130171Z","signature_b64":"zTSj9ywqPyry80PZMol4grnGupdxnW8EKYyoyI8a9B9/sKQUfltRXivi3Ok6tJKB57gfSh1wisdMDePA0fW9BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f980365acf029cc02e46083d2a8f709720091e737d16d60fe9745782c1ebe60","last_reissued_at":"2026-07-05T06:32:41.129736Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:32:41.129736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting Scene Text Recognition: A Data Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chongyu Liu, Dezhi Peng, Jiapeng Wang, Lianwen Jin, Qing Jiang","submitted_at":"2023-07-17T11:19:41Z","abstract_excerpt":"This paper aims to re-assess scene text recognition (STR) from a data-oriented perspective. We begin by revisiting the six commonly used benchmarks in STR and observe a trend of performance saturation, whereby only 2.91% of the benchmark images cannot be accurately recognized by an ensemble of 13 representative models. While these results are impressive and suggest that STR could be considered solved, however, we argue that this is primarily due to the less challenging nature of the common benchmarks, thus concealing the underlying issues that STR faces. To this end, we consolidate a large-sca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.08723","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/2307.08723/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":"2307.08723","created_at":"2026-07-05T06:32:41.129796+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.08723v2","created_at":"2026-07-05T06:32:41.129796+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.08723","created_at":"2026-07-05T06:32:41.129796+00:00"},{"alias_kind":"pith_short_12","alias_value":"H6MAGZNM6AU4","created_at":"2026-07-05T06:32:41.129796+00:00"},{"alias_kind":"pith_short_16","alias_value":"H6MAGZNM6AU4YAXE","created_at":"2026-07-05T06:32:41.129796+00:00"},{"alias_kind":"pith_short_8","alias_value":"H6MAGZNM","created_at":"2026-07-05T06:32:41.129796+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24077","citing_title":"LWM-CDE: A Representation Space for Wireless Data Reasoning and Transferability","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H6MAGZNM6AU4YAXEMCB5FKHXBF","json":"https://pith.science/pith/H6MAGZNM6AU4YAXEMCB5FKHXBF.json","graph_json":"https://pith.science/api/pith-number/H6MAGZNM6AU4YAXEMCB5FKHXBF/graph.json","events_json":"https://pith.science/api/pith-number/H6MAGZNM6AU4YAXEMCB5FKHXBF/events.json","paper":"https://pith.science/paper/H6MAGZNM"},"agent_actions":{"view_html":"https://pith.science/pith/H6MAGZNM6AU4YAXEMCB5FKHXBF","download_json":"https://pith.science/pith/H6MAGZNM6AU4YAXEMCB5FKHXBF.json","view_paper":"https://pith.science/paper/H6MAGZNM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.08723&json=true","fetch_graph":"https://pith.science/api/pith-number/H6MAGZNM6AU4YAXEMCB5FKHXBF/graph.json","fetch_events":"https://pith.science/api/pith-number/H6MAGZNM6AU4YAXEMCB5FKHXBF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H6MAGZNM6AU4YAXEMCB5FKHXBF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H6MAGZNM6AU4YAXEMCB5FKHXBF/action/storage_attestation","attest_author":"https://pith.science/pith/H6MAGZNM6AU4YAXEMCB5FKHXBF/action/author_attestation","sign_citation":"https://pith.science/pith/H6MAGZNM6AU4YAXEMCB5FKHXBF/action/citation_signature","submit_replication":"https://pith.science/pith/H6MAGZNM6AU4YAXEMCB5FKHXBF/action/replication_record"}},"created_at":"2026-07-05T06:32:41.129796+00:00","updated_at":"2026-07-05T06:32:41.129796+00:00"}