{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NKGOP63CPLSZZEBRZ3HNX5VO36","short_pith_number":"pith:NKGOP63C","schema_version":"1.0","canonical_sha256":"6a8ce7fb627ae59c9031cecedbf6aedfa0e5efa544810fe572d985e9a79a6dcb","source":{"kind":"arxiv","id":"2412.15523","version":2},"attestation_state":"computed","paper":{"title":"InstructOCR: Instruction Boosting Scene Text Spotting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chen Duan, Jiamin Chen, Junfeng Luo, Pei Fu, Qianyi Jiang, Shan Guo, Shengxi Li, Zining Wang","submitted_at":"2024-12-20T03:23:26Z","abstract_excerpt":"In the field of scene text spotting, previous OCR methods primarily relied on image encoders and pre-trained text information, but they often overlooked the advantages of incorporating human language instructions. To address this gap, we propose InstructOCR, an innovative instruction-based scene text spotting model that leverages human language instructions to enhance the understanding of text within images. Our framework employs both text and image encoders during training and inference, along with instructions meticulously designed based on text attributes. This approach enables the model to"},"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":"2412.15523","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-20T03:23:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bf90c3cde8303c9e534084f767896b063e8f43d484e4c38d1b2f5811d476770f","abstract_canon_sha256":"6a2867599d42ae19f53a9aa877020372e5d5e937bd4fda182f5b232d4a257877"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:57.482532Z","signature_b64":"/uSNsASkqnUVfKhMT5vtZvB15ad/u/qjwY4+12WVtVCUt36oSlmgeDKVQKftOXsC/0K0YInipcOmwCYOblfqCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a8ce7fb627ae59c9031cecedbf6aedfa0e5efa544810fe572d985e9a79a6dcb","last_reissued_at":"2026-07-05T09:59:57.481988Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:57.481988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InstructOCR: Instruction Boosting Scene Text Spotting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chen Duan, Jiamin Chen, Junfeng Luo, Pei Fu, Qianyi Jiang, Shan Guo, Shengxi Li, Zining Wang","submitted_at":"2024-12-20T03:23:26Z","abstract_excerpt":"In the field of scene text spotting, previous OCR methods primarily relied on image encoders and pre-trained text information, but they often overlooked the advantages of incorporating human language instructions. To address this gap, we propose InstructOCR, an innovative instruction-based scene text spotting model that leverages human language instructions to enhance the understanding of text within images. Our framework employs both text and image encoders during training and inference, along with instructions meticulously designed based on text attributes. This approach enables the model to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15523","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/2412.15523/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":"2412.15523","created_at":"2026-07-05T09:59:57.482065+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.15523v2","created_at":"2026-07-05T09:59:57.482065+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15523","created_at":"2026-07-05T09:59:57.482065+00:00"},{"alias_kind":"pith_short_12","alias_value":"NKGOP63CPLSZ","created_at":"2026-07-05T09:59:57.482065+00:00"},{"alias_kind":"pith_short_16","alias_value":"NKGOP63CPLSZZEBR","created_at":"2026-07-05T09:59:57.482065+00:00"},{"alias_kind":"pith_short_8","alias_value":"NKGOP63C","created_at":"2026-07-05T09:59:57.482065+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/NKGOP63CPLSZZEBRZ3HNX5VO36","json":"https://pith.science/pith/NKGOP63CPLSZZEBRZ3HNX5VO36.json","graph_json":"https://pith.science/api/pith-number/NKGOP63CPLSZZEBRZ3HNX5VO36/graph.json","events_json":"https://pith.science/api/pith-number/NKGOP63CPLSZZEBRZ3HNX5VO36/events.json","paper":"https://pith.science/paper/NKGOP63C"},"agent_actions":{"view_html":"https://pith.science/pith/NKGOP63CPLSZZEBRZ3HNX5VO36","download_json":"https://pith.science/pith/NKGOP63CPLSZZEBRZ3HNX5VO36.json","view_paper":"https://pith.science/paper/NKGOP63C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.15523&json=true","fetch_graph":"https://pith.science/api/pith-number/NKGOP63CPLSZZEBRZ3HNX5VO36/graph.json","fetch_events":"https://pith.science/api/pith-number/NKGOP63CPLSZZEBRZ3HNX5VO36/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NKGOP63CPLSZZEBRZ3HNX5VO36/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NKGOP63CPLSZZEBRZ3HNX5VO36/action/storage_attestation","attest_author":"https://pith.science/pith/NKGOP63CPLSZZEBRZ3HNX5VO36/action/author_attestation","sign_citation":"https://pith.science/pith/NKGOP63CPLSZZEBRZ3HNX5VO36/action/citation_signature","submit_replication":"https://pith.science/pith/NKGOP63CPLSZZEBRZ3HNX5VO36/action/replication_record"}},"created_at":"2026-07-05T09:59:57.482065+00:00","updated_at":"2026-07-05T09:59:57.482065+00:00"}