{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:D24PM5SGJWFSWBHZT73OM7RKXX","short_pith_number":"pith:D24PM5SG","schema_version":"1.0","canonical_sha256":"1eb8f676464d8b2b04f99ff6e67e2abdd1d1432b99e42cc90f0b97a6c36e9699","source":{"kind":"arxiv","id":"2401.02582","version":1},"attestation_state":"computed","paper":{"title":"CoCoT: Contrastive Chain-of-Thought Prompting for Large Multimodal Models with Multiple Image Inputs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daoan Zhang, Hanjia Lyu, Jiebo Luo, Junming Yang, Mingkai Chen, Yuan Yao, Zijian Jin","submitted_at":"2024-01-05T00:26:07Z","abstract_excerpt":"When exploring the development of Artificial General Intelligence (AGI), a critical task for these models involves interpreting and processing information from multiple image inputs. However, Large Multimodal Models (LMMs) encounter two issues in such scenarios: (1) a lack of fine-grained perception, and (2) a tendency to blend information across multiple images. We first extensively investigate the capability of LMMs to perceive fine-grained visual details when dealing with multiple input images. The research focuses on two aspects: first, image-to-image matching (to evaluate whether LMMs can"},"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":"2401.02582","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-05T00:26:07Z","cross_cats_sorted":[],"title_canon_sha256":"b12d6fc78142f0e11446be0fd55cc6e84fcda1a039d68a389b047a2ccebc9459","abstract_canon_sha256":"81b9cd4e700d93dc89a4b45ca3887f9d175fb735ef27e877706b648260ce230b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:30:27.665235Z","signature_b64":"NtaVuWE9o195dhlWAfqCWvjTzwyXbQSFJvImRSregTeEnhLquiYspbLPFmOEVOrOpp1wkvWxfNN4TKqJs5rMDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1eb8f676464d8b2b04f99ff6e67e2abdd1d1432b99e42cc90f0b97a6c36e9699","last_reissued_at":"2026-07-05T07:30:27.664806Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:30:27.664806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoCoT: Contrastive Chain-of-Thought Prompting for Large Multimodal Models with Multiple Image Inputs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daoan Zhang, Hanjia Lyu, Jiebo Luo, Junming Yang, Mingkai Chen, Yuan Yao, Zijian Jin","submitted_at":"2024-01-05T00:26:07Z","abstract_excerpt":"When exploring the development of Artificial General Intelligence (AGI), a critical task for these models involves interpreting and processing information from multiple image inputs. However, Large Multimodal Models (LMMs) encounter two issues in such scenarios: (1) a lack of fine-grained perception, and (2) a tendency to blend information across multiple images. We first extensively investigate the capability of LMMs to perceive fine-grained visual details when dealing with multiple input images. The research focuses on two aspects: first, image-to-image matching (to evaluate whether LMMs can"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02582","kind":"arxiv","version":1},"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/2401.02582/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":"2401.02582","created_at":"2026-07-05T07:30:27.664865+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.02582v1","created_at":"2026-07-05T07:30:27.664865+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02582","created_at":"2026-07-05T07:30:27.664865+00:00"},{"alias_kind":"pith_short_12","alias_value":"D24PM5SGJWFS","created_at":"2026-07-05T07:30:27.664865+00:00"},{"alias_kind":"pith_short_16","alias_value":"D24PM5SGJWFSWBHZ","created_at":"2026-07-05T07:30:27.664865+00:00"},{"alias_kind":"pith_short_8","alias_value":"D24PM5SG","created_at":"2026-07-05T07:30:27.664865+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.07632","citing_title":"Test-Time Matching: Unlocking Compositional Reasoning in Multimodal Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2503.12605","citing_title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D24PM5SGJWFSWBHZT73OM7RKXX","json":"https://pith.science/pith/D24PM5SGJWFSWBHZT73OM7RKXX.json","graph_json":"https://pith.science/api/pith-number/D24PM5SGJWFSWBHZT73OM7RKXX/graph.json","events_json":"https://pith.science/api/pith-number/D24PM5SGJWFSWBHZT73OM7RKXX/events.json","paper":"https://pith.science/paper/D24PM5SG"},"agent_actions":{"view_html":"https://pith.science/pith/D24PM5SGJWFSWBHZT73OM7RKXX","download_json":"https://pith.science/pith/D24PM5SGJWFSWBHZT73OM7RKXX.json","view_paper":"https://pith.science/paper/D24PM5SG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.02582&json=true","fetch_graph":"https://pith.science/api/pith-number/D24PM5SGJWFSWBHZT73OM7RKXX/graph.json","fetch_events":"https://pith.science/api/pith-number/D24PM5SGJWFSWBHZT73OM7RKXX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D24PM5SGJWFSWBHZT73OM7RKXX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D24PM5SGJWFSWBHZT73OM7RKXX/action/storage_attestation","attest_author":"https://pith.science/pith/D24PM5SGJWFSWBHZT73OM7RKXX/action/author_attestation","sign_citation":"https://pith.science/pith/D24PM5SGJWFSWBHZT73OM7RKXX/action/citation_signature","submit_replication":"https://pith.science/pith/D24PM5SGJWFSWBHZT73OM7RKXX/action/replication_record"}},"created_at":"2026-07-05T07:30:27.664865+00:00","updated_at":"2026-07-05T07:30:27.664865+00:00"}