{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VFO26MT66XDL65WPLWEZL54DY7","short_pith_number":"pith:VFO26MT6","schema_version":"1.0","canonical_sha256":"a95daf327ef5c6bf76cf5d8995f783c7e5f8a3171aa89ded7ad3eb1b460a4523","source":{"kind":"arxiv","id":"2403.12966","version":2},"attestation_state":"computed","paper":{"title":"Chain-of-Spot: Interactive Reasoning Improves Large Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jie Zhou, Jiwen Lu, Yongming Rao, Yuhao Dong, Zuyan Liu","submitted_at":"2024-03-19T17:59:52Z","abstract_excerpt":"In the realm of vision-language understanding, the proficiency of models in interpreting and reasoning over visual content has become a cornerstone for numerous applications. However, it is challenging for the visual encoder in Large Vision-Language Models (LVLMs) to extract useful features tailored to questions that aid the language model's response. Furthermore, a common practice among existing LVLMs is to utilize lower-resolution images, which restricts the ability for visual recognition. Our work introduces the Chain-of-Spot (CoS) method, which we describe as Interactive Reasoning, a novel"},"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":"2403.12966","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-19T17:59:52Z","cross_cats_sorted":[],"title_canon_sha256":"4f9050a2929be8ccfb5b84ccf4ad2decc4853b03b7bc6882fd8cf1dd1c3cbc23","abstract_canon_sha256":"300282cb6eff63025fc04ff8e7813928977552826f9ea1c8e0287e5ffa951e95"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:05.944926Z","signature_b64":"AKVqKneuJN1rWul3OjWmTyhVwH46+1H7CPWKUhTyDVw5R+81dgesgNkfVnc7PsR+YhZhDRGY2/23Tbx8mH79Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a95daf327ef5c6bf76cf5d8995f783c7e5f8a3171aa89ded7ad3eb1b460a4523","last_reissued_at":"2026-07-05T07:59:05.944442Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:05.944442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Chain-of-Spot: Interactive Reasoning Improves Large Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jie Zhou, Jiwen Lu, Yongming Rao, Yuhao Dong, Zuyan Liu","submitted_at":"2024-03-19T17:59:52Z","abstract_excerpt":"In the realm of vision-language understanding, the proficiency of models in interpreting and reasoning over visual content has become a cornerstone for numerous applications. However, it is challenging for the visual encoder in Large Vision-Language Models (LVLMs) to extract useful features tailored to questions that aid the language model's response. Furthermore, a common practice among existing LVLMs is to utilize lower-resolution images, which restricts the ability for visual recognition. Our work introduces the Chain-of-Spot (CoS) method, which we describe as Interactive Reasoning, a novel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12966","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/2403.12966/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":"2403.12966","created_at":"2026-07-05T07:59:05.944502+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.12966v2","created_at":"2026-07-05T07:59:05.944502+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12966","created_at":"2026-07-05T07:59:05.944502+00:00"},{"alias_kind":"pith_short_12","alias_value":"VFO26MT66XDL","created_at":"2026-07-05T07:59:05.944502+00:00"},{"alias_kind":"pith_short_16","alias_value":"VFO26MT66XDL65WP","created_at":"2026-07-05T07:59:05.944502+00:00"},{"alias_kind":"pith_short_8","alias_value":"VFO26MT6","created_at":"2026-07-05T07:59:05.944502+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24292","citing_title":"ActiveScope: Actively Seeking and Correcting Perception for MLLMs","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26196","citing_title":"From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models","ref_index":130,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24118","citing_title":"An LMM for Precisely Grounding Elements in Documents","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17888","citing_title":"MathVis-Fine: Aligning Visual Supervision with Necessity via Progressive Dependency-Guided Training for Multimodal Mathematical Reasoning","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01191","citing_title":"Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18740","citing_title":"Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18740","citing_title":"Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2507.05920","citing_title":"High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement Learning","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2503.12605","citing_title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2603.27494","citing_title":"Learning to Focus and Precise Cropping: A Reinforcement Learning Framework with Information Gaps and Grounding Loss for MLLMs","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09146","citing_title":"Beyond Thinking: Imagining in 360$^\\circ$ for Humanoid Visual Search","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VFO26MT66XDL65WPLWEZL54DY7","json":"https://pith.science/pith/VFO26MT66XDL65WPLWEZL54DY7.json","graph_json":"https://pith.science/api/pith-number/VFO26MT66XDL65WPLWEZL54DY7/graph.json","events_json":"https://pith.science/api/pith-number/VFO26MT66XDL65WPLWEZL54DY7/events.json","paper":"https://pith.science/paper/VFO26MT6"},"agent_actions":{"view_html":"https://pith.science/pith/VFO26MT66XDL65WPLWEZL54DY7","download_json":"https://pith.science/pith/VFO26MT66XDL65WPLWEZL54DY7.json","view_paper":"https://pith.science/paper/VFO26MT6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.12966&json=true","fetch_graph":"https://pith.science/api/pith-number/VFO26MT66XDL65WPLWEZL54DY7/graph.json","fetch_events":"https://pith.science/api/pith-number/VFO26MT66XDL65WPLWEZL54DY7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VFO26MT66XDL65WPLWEZL54DY7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VFO26MT66XDL65WPLWEZL54DY7/action/storage_attestation","attest_author":"https://pith.science/pith/VFO26MT66XDL65WPLWEZL54DY7/action/author_attestation","sign_citation":"https://pith.science/pith/VFO26MT66XDL65WPLWEZL54DY7/action/citation_signature","submit_replication":"https://pith.science/pith/VFO26MT66XDL65WPLWEZL54DY7/action/replication_record"}},"created_at":"2026-07-05T07:59:05.944502+00:00","updated_at":"2026-07-05T07:59:05.944502+00:00"}