{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:5JBQTR7DEYVZKGASFFROY44KI2","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":"59be66b562d0bc15550a8f13e82002e7fbc1a9d65167b05c181e59294cec0397","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-21T08:39:36Z","title_canon_sha256":"4247e4ee99996901381ec11fd1c55669730e870cd8ea62bc6988b1b251a4c2e0"},"schema_version":"1.0","source":{"id":"2212.10846","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.10846","created_at":"2026-07-05T06:07:35Z"},{"alias_kind":"arxiv_version","alias_value":"2212.10846v3","created_at":"2026-07-05T06:07:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10846","created_at":"2026-07-05T06:07:35Z"},{"alias_kind":"pith_short_12","alias_value":"5JBQTR7DEYVZ","created_at":"2026-07-05T06:07:35Z"},{"alias_kind":"pith_short_16","alias_value":"5JBQTR7DEYVZKGAS","created_at":"2026-07-05T06:07:35Z"},{"alias_kind":"pith_short_8","alias_value":"5JBQTR7D","created_at":"2026-07-05T06:07:35Z"}],"graph_snapshots":[{"event_id":"sha256:ab2420410bf075bfc0558c5bc5b3313fbcefb39a2ebff889dbee5fa0cb152bc7","target":"graph","created_at":"2026-07-05T06:07:35Z","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/2212.10846/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have demonstrated excellent zero-shot generalization to new language tasks. However, effective utilization of LLMs for zero-shot visual question-answering (VQA) remains challenging, primarily due to the modality disconnection and task disconnection between LLM and VQA task. End-to-end training on vision and language data may bridge the disconnections, but is inflexible and computationally expensive. To address this issue, we propose \\emph{Img2Prompt}, a plug-and-play module that provides the prompts that can bridge the aforementioned modality and task disconnection","authors_text":"Anthony Meng Huat Tiong, Boyang Li, Dacheng Tao, Dongxu Li, Jiaxian Guo, Junnan Li, Steven C.H. Hoi","cross_cats":["cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-21T08:39:36Z","title":"From Images to Textual Prompts: Zero-shot VQA with Frozen Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10846","kind":"arxiv","version":3},"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:b73ed36f4a2d22faebd70117b4239f420c4a1e37abd5eb686501fe77a2a78415","target":"record","created_at":"2026-07-05T06:07:35Z","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":"59be66b562d0bc15550a8f13e82002e7fbc1a9d65167b05c181e59294cec0397","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-21T08:39:36Z","title_canon_sha256":"4247e4ee99996901381ec11fd1c55669730e870cd8ea62bc6988b1b251a4c2e0"},"schema_version":"1.0","source":{"id":"2212.10846","kind":"arxiv","version":3}},"canonical_sha256":"ea4309c7e3262b9518122962ec738a46bf1012232a987793dd20710a2c309a81","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea4309c7e3262b9518122962ec738a46bf1012232a987793dd20710a2c309a81","first_computed_at":"2026-07-05T06:07:35.509723Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:07:35.509723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IrXmoZQbWcvpRzTkvD2b2LZiawYBa0S50FQCQ8vJrbFEO2euL6RsWjWUnGZeAUT7iyozZbvOMWq9C47DDNWcBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:07:35.510206Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.10846","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b73ed36f4a2d22faebd70117b4239f420c4a1e37abd5eb686501fe77a2a78415","sha256:ab2420410bf075bfc0558c5bc5b3313fbcefb39a2ebff889dbee5fa0cb152bc7"],"state_sha256":"c5d3023fbbc500e1bd290b6474f3602ee8957e116748a020599a765e244513ed"}