{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:EPV64S4JPK5QYL5IJ2X5N4BD63","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5b6822cc1d9116e379b3a1df1d78508c67afb0e549525d77b2625ba182983d62","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-15T19:07:53Z","title_canon_sha256":"cedce370d4bd9f3bb3f7d9c2c476d1c2fa0741aa703908c4deb5051048b3aaed"},"schema_version":"1.0","source":{"id":"2211.09699","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.09699","created_at":"2026-07-05T06:42:18Z"},{"alias_kind":"arxiv_version","alias_value":"2211.09699v4","created_at":"2026-07-05T06:42:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.09699","created_at":"2026-07-05T06:42:18Z"},{"alias_kind":"pith_short_12","alias_value":"EPV64S4JPK5Q","created_at":"2026-07-05T06:42:18Z"},{"alias_kind":"pith_short_16","alias_value":"EPV64S4JPK5QYL5I","created_at":"2026-07-05T06:42:18Z"},{"alias_kind":"pith_short_8","alias_value":"EPV64S4J","created_at":"2026-07-05T06:42:18Z"}],"graph_snapshots":[{"event_id":"sha256:b71fff992df6b2dbb9b00acc740c6d78c8069e6fcf4064c52bf5e47bcff098d5","target":"graph","created_at":"2026-07-05T06:42:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2211.09699/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hang Hua, Jiebo Luo, Noah A Smith, Weijia Shi, Yushi Hu, Zhengyuan Yang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-15T19:07:53Z","title":"PromptCap: Prompt-Guided Task-Aware Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.09699","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:461b963afffa70c65a1a348c2c8694ccca0a0a36c1c142deb3a46b1390a3902b","target":"record","created_at":"2026-07-05T06:42:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5b6822cc1d9116e379b3a1df1d78508c67afb0e549525d77b2625ba182983d62","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-15T19:07:53Z","title_canon_sha256":"cedce370d4bd9f3bb3f7d9c2c476d1c2fa0741aa703908c4deb5051048b3aaed"},"schema_version":"1.0","source":{"id":"2211.09699","kind":"arxiv","version":4}},"canonical_sha256":"23ebee4b897abb0c2fa84eafd6f023f6e7780248f4693f36aa663553c5bfa165","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23ebee4b897abb0c2fa84eafd6f023f6e7780248f4693f36aa663553c5bfa165","first_computed_at":"2026-07-05T06:42:18.285653Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:42:18.285653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+HI6N4dPoo8JSPoM+oYbBtoRrt1Qu5z6rJ6xECZg8GaXl0Xn/Id7X1GvzoKmq87BzEbptWS8/g783UHIHrjpDg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:42:18.286123Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.09699","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:461b963afffa70c65a1a348c2c8694ccca0a0a36c1c142deb3a46b1390a3902b","sha256:b71fff992df6b2dbb9b00acc740c6d78c8069e6fcf4064c52bf5e47bcff098d5"],"state_sha256":"d60dc689f2f1ca81ce256634180b9fa7072afc75ca2b65e380b84f7b6263352f"}