{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:IE4QB2EOYJYTERYL622D4FJUPS","short_pith_number":"pith:IE4QB2EO","schema_version":"1.0","canonical_sha256":"413900e88ec27132470bf6b43e15347cb22b56b179a1bf74abc2d4cfe3975189","source":{"kind":"arxiv","id":"2003.12462","version":2},"attestation_state":"computed","paper":{"title":"TextCaps: a Dataset for Image Captioning with Reading Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Amanpreet Singh, Marcus Rohrbach, Oleksii Sidorov, Ronghang Hu","submitted_at":"2020-03-24T02:38:35Z","abstract_excerpt":"Image descriptions can help visually impaired people to quickly understand the image content. While we made significant progress in automatically describing images and optical character recognition, current approaches are unable to include written text in their descriptions, although text is omnipresent in human environments and frequently critical to understand our surroundings. To study how to comprehend text in the context of an image we collect a novel dataset, TextCaps, with 145k captions for 28k images. Our dataset challenges a model to recognize text, relate it to its visual context, an"},"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":"2003.12462","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-24T02:38:35Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4cf7e0b2567710e3533ae9b5757fe70cd3d8c12a5a497de4ab1f61a14628ca5a","abstract_canon_sha256":"fd52b0670ce31074f82c7f214980fb7d9e00b94553335b43befa1f0e43885182"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:24:15.925583Z","signature_b64":"NgIHnYlGydEAriQ6uObr+5fvJUFxkj/8rdyHRlbahb85Ka4GoHa1m90Dtak8NHBX1E7T0H0QSrqv+GQXUUE8DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"413900e88ec27132470bf6b43e15347cb22b56b179a1bf74abc2d4cfe3975189","last_reissued_at":"2026-07-05T01:24:15.925065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:24:15.925065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TextCaps: a Dataset for Image Captioning with Reading Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Amanpreet Singh, Marcus Rohrbach, Oleksii Sidorov, Ronghang Hu","submitted_at":"2020-03-24T02:38:35Z","abstract_excerpt":"Image descriptions can help visually impaired people to quickly understand the image content. While we made significant progress in automatically describing images and optical character recognition, current approaches are unable to include written text in their descriptions, although text is omnipresent in human environments and frequently critical to understand our surroundings. To study how to comprehend text in the context of an image we collect a novel dataset, TextCaps, with 145k captions for 28k images. Our dataset challenges a model to recognize text, relate it to its visual context, an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.12462","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/2003.12462/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":"2003.12462","created_at":"2026-07-05T01:24:15.925127+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.12462v2","created_at":"2026-07-05T01:24:15.925127+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.12462","created_at":"2026-07-05T01:24:15.925127+00:00"},{"alias_kind":"pith_short_12","alias_value":"IE4QB2EOYJYT","created_at":"2026-07-05T01:24:15.925127+00:00"},{"alias_kind":"pith_short_16","alias_value":"IE4QB2EOYJYTERYL","created_at":"2026-07-05T01:24:15.925127+00:00"},{"alias_kind":"pith_short_8","alias_value":"IE4QB2EO","created_at":"2026-07-05T01:24:15.925127+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.09925","citing_title":"FLARE: Fully Integration of Vision-Language Representations for Deep Cross-Modal Understanding","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2311.07575","citing_title":"SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2406.16860","citing_title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","ref_index":120,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IE4QB2EOYJYTERYL622D4FJUPS","json":"https://pith.science/pith/IE4QB2EOYJYTERYL622D4FJUPS.json","graph_json":"https://pith.science/api/pith-number/IE4QB2EOYJYTERYL622D4FJUPS/graph.json","events_json":"https://pith.science/api/pith-number/IE4QB2EOYJYTERYL622D4FJUPS/events.json","paper":"https://pith.science/paper/IE4QB2EO"},"agent_actions":{"view_html":"https://pith.science/pith/IE4QB2EOYJYTERYL622D4FJUPS","download_json":"https://pith.science/pith/IE4QB2EOYJYTERYL622D4FJUPS.json","view_paper":"https://pith.science/paper/IE4QB2EO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.12462&json=true","fetch_graph":"https://pith.science/api/pith-number/IE4QB2EOYJYTERYL622D4FJUPS/graph.json","fetch_events":"https://pith.science/api/pith-number/IE4QB2EOYJYTERYL622D4FJUPS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IE4QB2EOYJYTERYL622D4FJUPS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IE4QB2EOYJYTERYL622D4FJUPS/action/storage_attestation","attest_author":"https://pith.science/pith/IE4QB2EOYJYTERYL622D4FJUPS/action/author_attestation","sign_citation":"https://pith.science/pith/IE4QB2EOYJYTERYL622D4FJUPS/action/citation_signature","submit_replication":"https://pith.science/pith/IE4QB2EOYJYTERYL622D4FJUPS/action/replication_record"}},"created_at":"2026-07-05T01:24:15.925127+00:00","updated_at":"2026-07-05T01:24:15.925127+00:00"}