{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QZHKVBVQCTMJIRDFKKREP26OL5","short_pith_number":"pith:QZHKVBVQ","schema_version":"1.0","canonical_sha256":"864eaa86b014d894446552a247ebce5f543a8f10fb66d61a2b86064ae0c4569d","source":{"kind":"arxiv","id":"2507.02200","version":1},"attestation_state":"computed","paper":{"title":"ESTR-CoT: Towards Explainable and Accurate Event Stream based Scene Text Recognition with Chain-of-Thought Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jingtao Jiang, Jin Tang, Lan Chen, Lin Zhu, Qiang Chen, Xiao Wang, Yaowei Wang, Yonghong Tian","submitted_at":"2025-07-02T23:41:31Z","abstract_excerpt":"Event stream based scene text recognition is a newly arising research topic in recent years which performs better than the widely used RGB cameras in extremely challenging scenarios, especially the low illumination, fast motion. Existing works either adopt end-to-end encoder-decoder framework or large language models for enhanced recognition, however, they are still limited by the challenges of insufficient interpretability and weak contextual logical reasoning. In this work, we propose a novel chain-of-thought reasoning based event stream scene text recognition framework, termed ESTR-CoT. Spe"},"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":"2507.02200","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-02T23:41:31Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"2ba1dabdc2a0801ef8b83d199d06e71a0cd0b6ca975d1d3c037b7419d82ad9fb","abstract_canon_sha256":"e704df379948456f2b5900ccbc794437000ea120192a48e5290e5439fb5ea7f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:13.709589Z","signature_b64":"GzC7lMGjWPEfyak7CuluRGzUrqLOhAuPonmyClzIpY2FRQB7N0GLHxGYXalsFepbxXZ/tiO5h0QxRSz3EashAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"864eaa86b014d894446552a247ebce5f543a8f10fb66d61a2b86064ae0c4569d","last_reissued_at":"2026-07-05T11:31:13.709016Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:13.709016Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ESTR-CoT: Towards Explainable and Accurate Event Stream based Scene Text Recognition with Chain-of-Thought Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jingtao Jiang, Jin Tang, Lan Chen, Lin Zhu, Qiang Chen, Xiao Wang, Yaowei Wang, Yonghong Tian","submitted_at":"2025-07-02T23:41:31Z","abstract_excerpt":"Event stream based scene text recognition is a newly arising research topic in recent years which performs better than the widely used RGB cameras in extremely challenging scenarios, especially the low illumination, fast motion. Existing works either adopt end-to-end encoder-decoder framework or large language models for enhanced recognition, however, they are still limited by the challenges of insufficient interpretability and weak contextual logical reasoning. In this work, we propose a novel chain-of-thought reasoning based event stream scene text recognition framework, termed ESTR-CoT. Spe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02200","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/2507.02200/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":"2507.02200","created_at":"2026-07-05T11:31:13.709078+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.02200v1","created_at":"2026-07-05T11:31:13.709078+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02200","created_at":"2026-07-05T11:31:13.709078+00:00"},{"alias_kind":"pith_short_12","alias_value":"QZHKVBVQCTMJ","created_at":"2026-07-05T11:31:13.709078+00:00"},{"alias_kind":"pith_short_16","alias_value":"QZHKVBVQCTMJIRDF","created_at":"2026-07-05T11:31:13.709078+00:00"},{"alias_kind":"pith_short_8","alias_value":"QZHKVBVQ","created_at":"2026-07-05T11:31:13.709078+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/QZHKVBVQCTMJIRDFKKREP26OL5","json":"https://pith.science/pith/QZHKVBVQCTMJIRDFKKREP26OL5.json","graph_json":"https://pith.science/api/pith-number/QZHKVBVQCTMJIRDFKKREP26OL5/graph.json","events_json":"https://pith.science/api/pith-number/QZHKVBVQCTMJIRDFKKREP26OL5/events.json","paper":"https://pith.science/paper/QZHKVBVQ"},"agent_actions":{"view_html":"https://pith.science/pith/QZHKVBVQCTMJIRDFKKREP26OL5","download_json":"https://pith.science/pith/QZHKVBVQCTMJIRDFKKREP26OL5.json","view_paper":"https://pith.science/paper/QZHKVBVQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.02200&json=true","fetch_graph":"https://pith.science/api/pith-number/QZHKVBVQCTMJIRDFKKREP26OL5/graph.json","fetch_events":"https://pith.science/api/pith-number/QZHKVBVQCTMJIRDFKKREP26OL5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QZHKVBVQCTMJIRDFKKREP26OL5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QZHKVBVQCTMJIRDFKKREP26OL5/action/storage_attestation","attest_author":"https://pith.science/pith/QZHKVBVQCTMJIRDFKKREP26OL5/action/author_attestation","sign_citation":"https://pith.science/pith/QZHKVBVQCTMJIRDFKKREP26OL5/action/citation_signature","submit_replication":"https://pith.science/pith/QZHKVBVQCTMJIRDFKKREP26OL5/action/replication_record"}},"created_at":"2026-07-05T11:31:13.709078+00:00","updated_at":"2026-07-05T11:31:13.709078+00:00"}