{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:D24PM5SGJWFSWBHZT73OM7RKXX","short_pith_number":"pith:D24PM5SG","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"},"canonical_sha256":"1eb8f676464d8b2b04f99ff6e67e2abdd1d1432b99e42cc90f0b97a6c36e9699","source":{"kind":"arxiv","id":"2401.02582","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.02582","created_at":"2026-07-05T07:30:27Z"},{"alias_kind":"arxiv_version","alias_value":"2401.02582v1","created_at":"2026-07-05T07:30:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02582","created_at":"2026-07-05T07:30:27Z"},{"alias_kind":"pith_short_12","alias_value":"D24PM5SGJWFS","created_at":"2026-07-05T07:30:27Z"},{"alias_kind":"pith_short_16","alias_value":"D24PM5SGJWFSWBHZ","created_at":"2026-07-05T07:30:27Z"},{"alias_kind":"pith_short_8","alias_value":"D24PM5SG","created_at":"2026-07-05T07:30:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:D24PM5SGJWFSWBHZT73OM7RKXX","target":"record","payload":{"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"},"canonical_sha256":"1eb8f676464d8b2b04f99ff6e67e2abdd1d1432b99e42cc90f0b97a6c36e9699","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"},"source_kind":"arxiv","source_id":"2401.02582","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:30:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S7Trt/aO/rcch+VT+Mdkzm2nwZUZL4key1+/a+bkQRMGoTxUwQEtB13n9IIPSIndxxECS7VW3KR8cj/6ZkfeAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:21:21.712133Z"},"content_sha256":"8dfe2b781e6a33e3ed807a15803856100ad9437a1e2464288ca1186127c6efda","schema_version":"1.0","event_id":"sha256:8dfe2b781e6a33e3ed807a15803856100ad9437a1e2464288ca1186127c6efda"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:D24PM5SGJWFSWBHZT73OM7RKXX","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:30:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0kmwCmL7swnhPQ0kcodimi0K4hSCIrcHaZgt7uSt4QU0jvfhdOG6fmY1GzOTe+PjoWL51IFPRB/5XVxNVvbdAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:21:21.713390Z"},"content_sha256":"17c17fff89da35ff8ee24cb79bea2b436868367f83bf84b535d3c138502bd260","schema_version":"1.0","event_id":"sha256:17c17fff89da35ff8ee24cb79bea2b436868367f83bf84b535d3c138502bd260"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D24PM5SGJWFSWBHZT73OM7RKXX/bundle.json","state_url":"https://pith.science/pith/D24PM5SGJWFSWBHZT73OM7RKXX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D24PM5SGJWFSWBHZT73OM7RKXX/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":"2026-08-09T00:21:21Z","links":{"resolver":"https://pith.science/pith/D24PM5SGJWFSWBHZT73OM7RKXX","bundle":"https://pith.science/pith/D24PM5SGJWFSWBHZT73OM7RKXX/bundle.json","state":"https://pith.science/pith/D24PM5SGJWFSWBHZT73OM7RKXX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D24PM5SGJWFSWBHZT73OM7RKXX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:D24PM5SGJWFSWBHZT73OM7RKXX","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":"81b9cd4e700d93dc89a4b45ca3887f9d175fb735ef27e877706b648260ce230b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-05T00:26:07Z","title_canon_sha256":"b12d6fc78142f0e11446be0fd55cc6e84fcda1a039d68a389b047a2ccebc9459"},"schema_version":"1.0","source":{"id":"2401.02582","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.02582","created_at":"2026-07-05T07:30:27Z"},{"alias_kind":"arxiv_version","alias_value":"2401.02582v1","created_at":"2026-07-05T07:30:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02582","created_at":"2026-07-05T07:30:27Z"},{"alias_kind":"pith_short_12","alias_value":"D24PM5SGJWFS","created_at":"2026-07-05T07:30:27Z"},{"alias_kind":"pith_short_16","alias_value":"D24PM5SGJWFSWBHZ","created_at":"2026-07-05T07:30:27Z"},{"alias_kind":"pith_short_8","alias_value":"D24PM5SG","created_at":"2026-07-05T07:30:27Z"}],"graph_snapshots":[{"event_id":"sha256:17c17fff89da35ff8ee24cb79bea2b436868367f83bf84b535d3c138502bd260","target":"graph","created_at":"2026-07-05T07:30:27Z","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/2401.02582/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Daoan Zhang, Hanjia Lyu, Jiebo Luo, Junming Yang, Mingkai Chen, Yuan Yao, Zijian Jin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-05T00:26:07Z","title":"CoCoT: Contrastive Chain-of-Thought Prompting for Large Multimodal Models with Multiple Image Inputs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02582","kind":"arxiv","version":1},"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":"sha256:8dfe2b781e6a33e3ed807a15803856100ad9437a1e2464288ca1186127c6efda","target":"record","created_at":"2026-07-05T07:30:27Z","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":"81b9cd4e700d93dc89a4b45ca3887f9d175fb735ef27e877706b648260ce230b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-05T00:26:07Z","title_canon_sha256":"b12d6fc78142f0e11446be0fd55cc6e84fcda1a039d68a389b047a2ccebc9459"},"schema_version":"1.0","source":{"id":"2401.02582","kind":"arxiv","version":1}},"canonical_sha256":"1eb8f676464d8b2b04f99ff6e67e2abdd1d1432b99e42cc90f0b97a6c36e9699","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1eb8f676464d8b2b04f99ff6e67e2abdd1d1432b99e42cc90f0b97a6c36e9699","first_computed_at":"2026-07-05T07:30:27.664806Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:30:27.664806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NtaVuWE9o195dhlWAfqCWvjTzwyXbQSFJvImRSregTeEnhLquiYspbLPFmOEVOrOpp1wkvWxfNN4TKqJs5rMDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:30:27.665235Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.02582","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8dfe2b781e6a33e3ed807a15803856100ad9437a1e2464288ca1186127c6efda","sha256:17c17fff89da35ff8ee24cb79bea2b436868367f83bf84b535d3c138502bd260"],"state_sha256":"9d64f97bbe109ce5e401696a4126a6789af7d5b9521e7db3c2fac7cd4f3cce65"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TZHSGvOmdRG8Ux3ODFn14+5X9+XgB0szybzYzrpE+7cgDXu6ajMbZAWgiCDAUhiA61JgkL8YwAE98mnUSzSNBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T00:21:21.718980Z","bundle_sha256":"d42dce6d9f2469ea2900e2fd2535f772876d12038e7a43b4401edf68d830144f"}}