{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EPV64S4JPK5QYL5IJ2X5N4BD63","short_pith_number":"pith:EPV64S4J","schema_version":"1.0","canonical_sha256":"23ebee4b897abb0c2fa84eafd6f023f6e7780248f4693f36aa663553c5bfa165","source":{"kind":"arxiv","id":"2211.09699","version":4},"attestation_state":"computed","paper":{"title":"PromptCap: Prompt-Guided Task-Aware Image Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Hang Hua, Jiebo Luo, Noah A Smith, Weijia Shi, Yushi Hu, Zhengyuan Yang","submitted_at":"2022-11-15T19:07:53Z","abstract_excerpt":"Knowledge-based visual question answering (VQA) involves questions that require world knowledge beyond the image to yield the correct answer. Large language models (LMs) like GPT-3 are particularly helpful for this task because of their strong knowledge retrieval and reasoning capabilities. To enable LM to understand images, prior work uses a captioning model to convert images into text. However, when summarizing an image in a single caption sentence, which visual entities to describe are often underspecified. Generic image captions often miss visual details essential for the LM to answer visu"},"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":"2211.09699","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-15T19:07:53Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"cedce370d4bd9f3bb3f7d9c2c476d1c2fa0741aa703908c4deb5051048b3aaed","abstract_canon_sha256":"5b6822cc1d9116e379b3a1df1d78508c67afb0e549525d77b2625ba182983d62"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:42:18.286123Z","signature_b64":"+HI6N4dPoo8JSPoM+oYbBtoRrt1Qu5z6rJ6xECZg8GaXl0Xn/Id7X1GvzoKmq87BzEbptWS8/g783UHIHrjpDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23ebee4b897abb0c2fa84eafd6f023f6e7780248f4693f36aa663553c5bfa165","last_reissued_at":"2026-07-05T06:42:18.285653Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:42:18.285653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PromptCap: Prompt-Guided Task-Aware Image Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Hang Hua, Jiebo Luo, Noah A Smith, Weijia Shi, Yushi Hu, Zhengyuan Yang","submitted_at":"2022-11-15T19:07:53Z","abstract_excerpt":"Knowledge-based visual question answering (VQA) involves questions that require world knowledge beyond the image to yield the correct answer. Large language models (LMs) like GPT-3 are particularly helpful for this task because of their strong knowledge retrieval and reasoning capabilities. To enable LM to understand images, prior work uses a captioning model to convert images into text. However, when summarizing an image in a single caption sentence, which visual entities to describe are often underspecified. Generic image captions often miss visual details essential for the LM to answer visu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.09699","kind":"arxiv","version":4},"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/2211.09699/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":"2211.09699","created_at":"2026-07-05T06:42:18.285713+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.09699v4","created_at":"2026-07-05T06:42:18.285713+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.09699","created_at":"2026-07-05T06:42:18.285713+00:00"},{"alias_kind":"pith_short_12","alias_value":"EPV64S4JPK5Q","created_at":"2026-07-05T06:42:18.285713+00:00"},{"alias_kind":"pith_short_16","alias_value":"EPV64S4JPK5QYL5I","created_at":"2026-07-05T06:42:18.285713+00:00"},{"alias_kind":"pith_short_8","alias_value":"EPV64S4J","created_at":"2026-07-05T06:42:18.285713+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01733","citing_title":"GEASS: Gated Evidence-Adaptive Selective Caption Trust for Vision-Language Models","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01733","citing_title":"GEASS: Gated Evidence-Adaptive Selective Caption Trust for Vision-Language Models","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2303.08128","citing_title":"ViperGPT: Visual Inference via Python Execution for Reasoning","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2301.12652","citing_title":"REPLUG: Retrieval-Augmented Black-Box Language Models","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2404.12390","citing_title":"BLINK: Multimodal Large Language Models Can See but Not Perceive","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2303.11381","citing_title":"MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03660","citing_title":"TableVision: A Large-Scale Benchmark for Spatially Grounded Reasoning over Complex Hierarchical Tables","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10500","citing_title":"Visual Enhanced Depth Scaling for Multimodal Latent Reasoning","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10500","citing_title":"Visual Enhanced Depth Scaling for Multimodal Latent Reasoning","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10500","citing_title":"Visual Enhanced Depth Scaling for Multimodal Latent Reasoning","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EPV64S4JPK5QYL5IJ2X5N4BD63","json":"https://pith.science/pith/EPV64S4JPK5QYL5IJ2X5N4BD63.json","graph_json":"https://pith.science/api/pith-number/EPV64S4JPK5QYL5IJ2X5N4BD63/graph.json","events_json":"https://pith.science/api/pith-number/EPV64S4JPK5QYL5IJ2X5N4BD63/events.json","paper":"https://pith.science/paper/EPV64S4J"},"agent_actions":{"view_html":"https://pith.science/pith/EPV64S4JPK5QYL5IJ2X5N4BD63","download_json":"https://pith.science/pith/EPV64S4JPK5QYL5IJ2X5N4BD63.json","view_paper":"https://pith.science/paper/EPV64S4J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.09699&json=true","fetch_graph":"https://pith.science/api/pith-number/EPV64S4JPK5QYL5IJ2X5N4BD63/graph.json","fetch_events":"https://pith.science/api/pith-number/EPV64S4JPK5QYL5IJ2X5N4BD63/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EPV64S4JPK5QYL5IJ2X5N4BD63/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EPV64S4JPK5QYL5IJ2X5N4BD63/action/storage_attestation","attest_author":"https://pith.science/pith/EPV64S4JPK5QYL5IJ2X5N4BD63/action/author_attestation","sign_citation":"https://pith.science/pith/EPV64S4JPK5QYL5IJ2X5N4BD63/action/citation_signature","submit_replication":"https://pith.science/pith/EPV64S4JPK5QYL5IJ2X5N4BD63/action/replication_record"}},"created_at":"2026-07-05T06:42:18.285713+00:00","updated_at":"2026-07-05T06:42:18.285713+00:00"}