{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:XHW2BF23RDF4UKL7A3ZSDYTVF2","short_pith_number":"pith:XHW2BF23","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"},"canonical_sha256":"b9eda0975b88cbca297f06f321e2752e8a12c79eccdc3fbcd43620a2f1ad64d6","source":{"kind":"arxiv","id":"2312.01598","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.01598","created_at":"2026-07-05T07:22:01Z"},{"alias_kind":"arxiv_version","alias_value":"2312.01598v2","created_at":"2026-07-05T07:22:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.01598","created_at":"2026-07-05T07:22:01Z"},{"alias_kind":"pith_short_12","alias_value":"XHW2BF23RDF4","created_at":"2026-07-05T07:22:01Z"},{"alias_kind":"pith_short_16","alias_value":"XHW2BF23RDF4UKL7","created_at":"2026-07-05T07:22:01Z"},{"alias_kind":"pith_short_8","alias_value":"XHW2BF23","created_at":"2026-07-05T07:22:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:XHW2BF23RDF4UKL7A3ZSDYTVF2","target":"record","payload":{"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"},"canonical_sha256":"b9eda0975b88cbca297f06f321e2752e8a12c79eccdc3fbcd43620a2f1ad64d6","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"},"source_kind":"arxiv","source_id":"2312.01598","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:22:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gm7cTm4K0jhaDalPrpyU4q0dBdK584PIa7EQRMYxRWHubZtnTBXfML7bqCRTKx9yQrCQfW/6Gh+dpQXKLZMjBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:03:54.601062Z"},"content_sha256":"076d313bf731bf4033fa99be25edc1f18bf0e67220c4b489dc0df8edc3c3666d","schema_version":"1.0","event_id":"sha256:076d313bf731bf4033fa99be25edc1f18bf0e67220c4b489dc0df8edc3c3666d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:XHW2BF23RDF4UKL7A3ZSDYTVF2","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:22:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T2ML4uiFFqjApntIo5nfgDLLYTWQDLdyd2iRWkXn8g56na9dWqs6p+KHKhCmF0zLkVWbWmsxehET1G5faLzMCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:03:54.601564Z"},"content_sha256":"92fe7351e69c833d9232270110dbf23177bf87c51db4c7689f48bbf12e440486","schema_version":"1.0","event_id":"sha256:92fe7351e69c833d9232270110dbf23177bf87c51db4c7689f48bbf12e440486"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XHW2BF23RDF4UKL7A3ZSDYTVF2/bundle.json","state_url":"https://pith.science/pith/XHW2BF23RDF4UKL7A3ZSDYTVF2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XHW2BF23RDF4UKL7A3ZSDYTVF2/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T04:03:54Z","links":{"resolver":"https://pith.science/pith/XHW2BF23RDF4UKL7A3ZSDYTVF2","bundle":"https://pith.science/pith/XHW2BF23RDF4UKL7A3ZSDYTVF2/bundle.json","state":"https://pith.science/pith/XHW2BF23RDF4UKL7A3ZSDYTVF2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XHW2BF23RDF4UKL7A3ZSDYTVF2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XHW2BF23RDF4UKL7A3ZSDYTVF2","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":"aa4a09d4188ab48fa996afdf9ed1ee91678c6ed311b37a71efc309ce51f3e739","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T03:18:51Z","title_canon_sha256":"5a8047417d3b1175b4346e1b6fa3e2807ebf85df06ecba8c0a62490c2a0011cd"},"schema_version":"1.0","source":{"id":"2312.01598","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.01598","created_at":"2026-07-05T07:22:01Z"},{"alias_kind":"arxiv_version","alias_value":"2312.01598v2","created_at":"2026-07-05T07:22:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.01598","created_at":"2026-07-05T07:22:01Z"},{"alias_kind":"pith_short_12","alias_value":"XHW2BF23RDF4","created_at":"2026-07-05T07:22:01Z"},{"alias_kind":"pith_short_16","alias_value":"XHW2BF23RDF4UKL7","created_at":"2026-07-05T07:22:01Z"},{"alias_kind":"pith_short_8","alias_value":"XHW2BF23","created_at":"2026-07-05T07:22:01Z"}],"graph_snapshots":[{"event_id":"sha256:92fe7351e69c833d9232270110dbf23177bf87c51db4c7689f48bbf12e440486","target":"graph","created_at":"2026-07-05T07:22:01Z","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/2312.01598/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chongyang Tao, Dacheng Tao, Kaiwen Yang, Tao Shen, Tianyi Zhou, Xinmei Tian, Xiubo Geng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T03:18:51Z","title":"Good Questions Help Zero-Shot Image Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.01598","kind":"arxiv","version":2},"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":"sha256:076d313bf731bf4033fa99be25edc1f18bf0e67220c4b489dc0df8edc3c3666d","target":"record","created_at":"2026-07-05T07:22:01Z","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":"aa4a09d4188ab48fa996afdf9ed1ee91678c6ed311b37a71efc309ce51f3e739","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T03:18:51Z","title_canon_sha256":"5a8047417d3b1175b4346e1b6fa3e2807ebf85df06ecba8c0a62490c2a0011cd"},"schema_version":"1.0","source":{"id":"2312.01598","kind":"arxiv","version":2}},"canonical_sha256":"b9eda0975b88cbca297f06f321e2752e8a12c79eccdc3fbcd43620a2f1ad64d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b9eda0975b88cbca297f06f321e2752e8a12c79eccdc3fbcd43620a2f1ad64d6","first_computed_at":"2026-07-05T07:22:01.854468Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:22:01.854468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"foqsZcE9uvRAAIDaHNvfUIMB2P67IDk92yDg1PU3LxZ1KyCav766w6Y1lUcIaa/QQi04VDEKQrFGrDiKaGI6Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:22:01.854871Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.01598","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:076d313bf731bf4033fa99be25edc1f18bf0e67220c4b489dc0df8edc3c3666d","sha256:92fe7351e69c833d9232270110dbf23177bf87c51db4c7689f48bbf12e440486"],"state_sha256":"cbf2ab29b11c7ad3999624c495f652d02383cf787ec0f838f137a9b49468d8c3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R5Gez1EB3Om4snhL3v40vHytSHy1sikpRy0kZ+K1sf7h8LCRqQ1lUrfGvJzbc/HYv2LqQNxRAFaHr/P6l9rBDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T04:03:54.606677Z","bundle_sha256":"1fdf57e276d158862db47aaf099909e9e1188d80daa78de50c1a6504d1abd73d"}}