{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XHW2BF23RDF4UKL7A3ZSDYTVF2","short_pith_number":"pith:XHW2BF23","schema_version":"1.0","canonical_sha256":"b9eda0975b88cbca297f06f321e2752e8a12c79eccdc3fbcd43620a2f1ad64d6","source":{"kind":"arxiv","id":"2312.01598","version":2},"attestation_state":"computed","paper":{"title":"Good Questions Help Zero-Shot Image Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chongyang Tao, Dacheng Tao, Kaiwen Yang, Tao Shen, Tianyi Zhou, Xinmei Tian, Xiubo Geng","submitted_at":"2023-12-04T03:18:51Z","abstract_excerpt":"Aligning the recent large language models (LLMs) with computer vision models leads to large vision-language models (LVLMs), which have paved the way for zero-shot image reasoning tasks. However, LVLMs are usually trained on short high-level captions only referring to sparse focus regions in images. Such a ``tunnel vision'' limits LVLMs to exploring other relevant contexts in complex scenes. To address this challenge, we introduce Question-Driven Visual Exploration (QVix), a novel prompting strategy that enhances the exploratory capabilities of LVLMs in zero-shot reasoning tasks. QVix leverages"},"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":"2312.01598","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T03:18:51Z","cross_cats_sorted":[],"title_canon_sha256":"5a8047417d3b1175b4346e1b6fa3e2807ebf85df06ecba8c0a62490c2a0011cd","abstract_canon_sha256":"aa4a09d4188ab48fa996afdf9ed1ee91678c6ed311b37a71efc309ce51f3e739"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:22:01.854871Z","signature_b64":"foqsZcE9uvRAAIDaHNvfUIMB2P67IDk92yDg1PU3LxZ1KyCav766w6Y1lUcIaa/QQi04VDEKQrFGrDiKaGI6Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9eda0975b88cbca297f06f321e2752e8a12c79eccdc3fbcd43620a2f1ad64d6","last_reissued_at":"2026-07-05T07:22:01.854468Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:22:01.854468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Good Questions Help Zero-Shot Image Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chongyang Tao, Dacheng Tao, Kaiwen Yang, Tao Shen, Tianyi Zhou, Xinmei Tian, Xiubo Geng","submitted_at":"2023-12-04T03:18:51Z","abstract_excerpt":"Aligning the recent large language models (LLMs) with computer vision models leads to large vision-language models (LVLMs), which have paved the way for zero-shot image reasoning tasks. However, LVLMs are usually trained on short high-level captions only referring to sparse focus regions in images. Such a ``tunnel vision'' limits LVLMs to exploring other relevant contexts in complex scenes. To address this challenge, we introduce Question-Driven Visual Exploration (QVix), a novel prompting strategy that enhances the exploratory capabilities of LVLMs in zero-shot reasoning tasks. QVix leverages"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.01598","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/2312.01598/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":"2312.01598","created_at":"2026-07-05T07:22:01.854521+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.01598v2","created_at":"2026-07-05T07:22:01.854521+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.01598","created_at":"2026-07-05T07:22:01.854521+00:00"},{"alias_kind":"pith_short_12","alias_value":"XHW2BF23RDF4","created_at":"2026-07-05T07:22:01.854521+00:00"},{"alias_kind":"pith_short_16","alias_value":"XHW2BF23RDF4UKL7","created_at":"2026-07-05T07:22:01.854521+00:00"},{"alias_kind":"pith_short_8","alias_value":"XHW2BF23","created_at":"2026-07-05T07:22:01.854521+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/XHW2BF23RDF4UKL7A3ZSDYTVF2","json":"https://pith.science/pith/XHW2BF23RDF4UKL7A3ZSDYTVF2.json","graph_json":"https://pith.science/api/pith-number/XHW2BF23RDF4UKL7A3ZSDYTVF2/graph.json","events_json":"https://pith.science/api/pith-number/XHW2BF23RDF4UKL7A3ZSDYTVF2/events.json","paper":"https://pith.science/paper/XHW2BF23"},"agent_actions":{"view_html":"https://pith.science/pith/XHW2BF23RDF4UKL7A3ZSDYTVF2","download_json":"https://pith.science/pith/XHW2BF23RDF4UKL7A3ZSDYTVF2.json","view_paper":"https://pith.science/paper/XHW2BF23","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.01598&json=true","fetch_graph":"https://pith.science/api/pith-number/XHW2BF23RDF4UKL7A3ZSDYTVF2/graph.json","fetch_events":"https://pith.science/api/pith-number/XHW2BF23RDF4UKL7A3ZSDYTVF2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XHW2BF23RDF4UKL7A3ZSDYTVF2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XHW2BF23RDF4UKL7A3ZSDYTVF2/action/storage_attestation","attest_author":"https://pith.science/pith/XHW2BF23RDF4UKL7A3ZSDYTVF2/action/author_attestation","sign_citation":"https://pith.science/pith/XHW2BF23RDF4UKL7A3ZSDYTVF2/action/citation_signature","submit_replication":"https://pith.science/pith/XHW2BF23RDF4UKL7A3ZSDYTVF2/action/replication_record"}},"created_at":"2026-07-05T07:22:01.854521+00:00","updated_at":"2026-07-05T07:22:01.854521+00:00"}