{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PXCPNLVF24DW4FJCHDTGHCIL6Q","short_pith_number":"pith:PXCPNLVF","schema_version":"1.0","canonical_sha256":"7dc4f6aea5d7076e152238e663890bf40b3d861ffa448a90122915079938e618","source":{"kind":"arxiv","id":"2304.07919","version":2},"attestation_state":"computed","paper":{"title":"Chain of Thought Prompt Tuning in Vision Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hongyin Luo, Jiaxin Ge, Jie Fu, Shanghang Zhang, Siyuan Qian, Yulu Gan","submitted_at":"2023-04-16T23:59:25Z","abstract_excerpt":"Language-Image Pre-training has demonstrated promising results on zero-shot and few-shot downstream tasks by prompting visual models with natural language prompts. However, most recent studies only use a single prompt for tuning, neglecting the inherent step-to-step cognitive reasoning process that humans conduct in complex task settings, for example, when processing images from unfamiliar domains. Chain of Thought is a simple and effective approximation to human reasoning process and has been proven useful for natural language processing (NLP) tasks. Based on this cognitive intuition, we beli"},"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":"2304.07919","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-16T23:59:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fa8ced7cd38cb04773e639c0d32775d4747e4a789a2dc51c23c1dd74f3dd5ba6","abstract_canon_sha256":"c612b62b63c06d850997ae78f4ed3926af18f2804fc29d43ee392ee6e3a9cae2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:21:31.278916Z","signature_b64":"CmoA9nz+fgyFuC1mM8b3eXZ/P25M8ajqgZpI2fCf5rrQpPdPwzqSmNJPQBc++O8aEOeUCGBOdiGGGqAALdE9Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7dc4f6aea5d7076e152238e663890bf40b3d861ffa448a90122915079938e618","last_reissued_at":"2026-07-05T06:21:31.278457Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:21:31.278457Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Chain of Thought Prompt Tuning in Vision Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hongyin Luo, Jiaxin Ge, Jie Fu, Shanghang Zhang, Siyuan Qian, Yulu Gan","submitted_at":"2023-04-16T23:59:25Z","abstract_excerpt":"Language-Image Pre-training has demonstrated promising results on zero-shot and few-shot downstream tasks by prompting visual models with natural language prompts. However, most recent studies only use a single prompt for tuning, neglecting the inherent step-to-step cognitive reasoning process that humans conduct in complex task settings, for example, when processing images from unfamiliar domains. Chain of Thought is a simple and effective approximation to human reasoning process and has been proven useful for natural language processing (NLP) tasks. Based on this cognitive intuition, we beli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.07919","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/2304.07919/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":"2304.07919","created_at":"2026-07-05T06:21:31.278509+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.07919v2","created_at":"2026-07-05T06:21:31.278509+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.07919","created_at":"2026-07-05T06:21:31.278509+00:00"},{"alias_kind":"pith_short_12","alias_value":"PXCPNLVF24DW","created_at":"2026-07-05T06:21:31.278509+00:00"},{"alias_kind":"pith_short_16","alias_value":"PXCPNLVF24DW4FJC","created_at":"2026-07-05T06:21:31.278509+00:00"},{"alias_kind":"pith_short_8","alias_value":"PXCPNLVF","created_at":"2026-07-05T06:21:31.278509+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05859","citing_title":"AVA-VLM: Adaptive Visual Attention-Vision Language Model for In-the-Wild Construction Site Monitoring","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19859","citing_title":"Eyes on VLM: Benchmarking Gaze Following and Social Gaze Prediction in Vision Language Models","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19859","citing_title":"Eyes on VLM: Benchmarking Gaze Following and Social Gaze Prediction in Vision Language Models","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2307.06435","citing_title":"A Comprehensive Overview of Large Language Models","ref_index":288,"is_internal_anchor":false},{"citing_arxiv_id":"2306.13549","citing_title":"A Survey on Multimodal Large Language Models","ref_index":190,"is_internal_anchor":false},{"citing_arxiv_id":"2503.12605","citing_title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","ref_index":132,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PXCPNLVF24DW4FJCHDTGHCIL6Q","json":"https://pith.science/pith/PXCPNLVF24DW4FJCHDTGHCIL6Q.json","graph_json":"https://pith.science/api/pith-number/PXCPNLVF24DW4FJCHDTGHCIL6Q/graph.json","events_json":"https://pith.science/api/pith-number/PXCPNLVF24DW4FJCHDTGHCIL6Q/events.json","paper":"https://pith.science/paper/PXCPNLVF"},"agent_actions":{"view_html":"https://pith.science/pith/PXCPNLVF24DW4FJCHDTGHCIL6Q","download_json":"https://pith.science/pith/PXCPNLVF24DW4FJCHDTGHCIL6Q.json","view_paper":"https://pith.science/paper/PXCPNLVF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.07919&json=true","fetch_graph":"https://pith.science/api/pith-number/PXCPNLVF24DW4FJCHDTGHCIL6Q/graph.json","fetch_events":"https://pith.science/api/pith-number/PXCPNLVF24DW4FJCHDTGHCIL6Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PXCPNLVF24DW4FJCHDTGHCIL6Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PXCPNLVF24DW4FJCHDTGHCIL6Q/action/storage_attestation","attest_author":"https://pith.science/pith/PXCPNLVF24DW4FJCHDTGHCIL6Q/action/author_attestation","sign_citation":"https://pith.science/pith/PXCPNLVF24DW4FJCHDTGHCIL6Q/action/citation_signature","submit_replication":"https://pith.science/pith/PXCPNLVF24DW4FJCHDTGHCIL6Q/action/replication_record"}},"created_at":"2026-07-05T06:21:31.278509+00:00","updated_at":"2026-07-05T06:21:31.278509+00:00"}