{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MEMFY45KTFSUA4CNBCZCCRU23F","short_pith_number":"pith:MEMFY45K","canonical_record":{"source":{"id":"2405.13872","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-22T17:56:51Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"e04f6f8b724cfc9dcb26364cb8f1e4f5f9aa74a25c8c504c72c7ef4bb2c896d9","abstract_canon_sha256":"b0728d79bd9efe81478609971173e96e5fd1233eb926fba3366a1d2c51832d36"},"schema_version":"1.0"},"canonical_sha256":"61185c73aa996540704d08b221469ad97cf095e7a3d51690f8cefd57adc9daf8","source":{"kind":"arxiv","id":"2405.13872","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.13872","created_at":"2026-07-05T08:24:25Z"},{"alias_kind":"arxiv_version","alias_value":"2405.13872v2","created_at":"2026-07-05T08:24:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.13872","created_at":"2026-07-05T08:24:25Z"},{"alias_kind":"pith_short_12","alias_value":"MEMFY45KTFSU","created_at":"2026-07-05T08:24:25Z"},{"alias_kind":"pith_short_16","alias_value":"MEMFY45KTFSUA4CN","created_at":"2026-07-05T08:24:25Z"},{"alias_kind":"pith_short_8","alias_value":"MEMFY45K","created_at":"2026-07-05T08:24:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MEMFY45KTFSUA4CNBCZCCRU23F","target":"record","payload":{"canonical_record":{"source":{"id":"2405.13872","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-22T17:56:51Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"e04f6f8b724cfc9dcb26364cb8f1e4f5f9aa74a25c8c504c72c7ef4bb2c896d9","abstract_canon_sha256":"b0728d79bd9efe81478609971173e96e5fd1233eb926fba3366a1d2c51832d36"},"schema_version":"1.0"},"canonical_sha256":"61185c73aa996540704d08b221469ad97cf095e7a3d51690f8cefd57adc9daf8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:25.155133Z","signature_b64":"3WF9rqAC7QS/RABPQm/j+bLz7jcze1keUElZZo4GaPAhccEiHx6AFJuEJ5lAIEGixXJ0wplO5IHd+7GVYH0MDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61185c73aa996540704d08b221469ad97cf095e7a3d51690f8cefd57adc9daf8","last_reissued_at":"2026-07-05T08:24:25.154685Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:25.154685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.13872","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":"2026-07-05T08:24:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Meg6tqIhTq4NaILG1x4jnuda/wOvPmXNp3aF4ekIKrkM+sWT1olEo8LIqyDWh52UWKXVtnOXZzTVLmYag1isDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T14:33:41.449268Z"},"content_sha256":"b2b6bd33d84a083dcf51fb2199c5764f44e9c065323b6c57d3c76762cb37fd12","schema_version":"1.0","event_id":"sha256:b2b6bd33d84a083dcf51fb2199c5764f44e9c065323b6c57d3c76762cb37fd12"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MEMFY45KTFSUA4CNBCZCCRU23F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Panzhong Lu, Qiji Zhou, Ruochen Zhou, Siyang Gao, Yue Zhang, Zike Hu","submitted_at":"2024-05-22T17:56:51Z","abstract_excerpt":"Recent advancements in Chain-of-Thought (CoT) and related rationale-based works have significantly improved the performance of Large Language Models (LLMs) in complex reasoning tasks. With the evolution of Multimodal Large Language Models (MLLMs), enhancing their capability to tackle complex multimodal reasoning problems is a crucial frontier. However, incorporating multimodal rationales in CoT has yet to be thoroughly investigated. We propose the Image-of-Thought (IoT) prompting method, which helps MLLMs to extract visual rationales step-by-step. Specifically, IoT prompting can automatically "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.13872","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/2405.13872/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":"2026-07-05T08:24:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+qWyzlEOuhVgJFEw9KypdUm79wjEsMPcQntoTW/e41BeqGeBYwOYr6bGEnAT+eNZrGphEKH5purkXQIYSgn9DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T14:33:41.449800Z"},"content_sha256":"3671878956ef1123bef1d3a7096403a725d2e66baab7098c15052e281da9fa8a","schema_version":"1.0","event_id":"sha256:3671878956ef1123bef1d3a7096403a725d2e66baab7098c15052e281da9fa8a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MEMFY45KTFSUA4CNBCZCCRU23F/bundle.json","state_url":"https://pith.science/pith/MEMFY45KTFSUA4CNBCZCCRU23F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MEMFY45KTFSUA4CNBCZCCRU23F/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":"2026-08-19T14:33:41Z","links":{"resolver":"https://pith.science/pith/MEMFY45KTFSUA4CNBCZCCRU23F","bundle":"https://pith.science/pith/MEMFY45KTFSUA4CNBCZCCRU23F/bundle.json","state":"https://pith.science/pith/MEMFY45KTFSUA4CNBCZCCRU23F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MEMFY45KTFSUA4CNBCZCCRU23F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MEMFY45KTFSUA4CNBCZCCRU23F","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":"b0728d79bd9efe81478609971173e96e5fd1233eb926fba3366a1d2c51832d36","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-22T17:56:51Z","title_canon_sha256":"e04f6f8b724cfc9dcb26364cb8f1e4f5f9aa74a25c8c504c72c7ef4bb2c896d9"},"schema_version":"1.0","source":{"id":"2405.13872","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.13872","created_at":"2026-07-05T08:24:25Z"},{"alias_kind":"arxiv_version","alias_value":"2405.13872v2","created_at":"2026-07-05T08:24:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.13872","created_at":"2026-07-05T08:24:25Z"},{"alias_kind":"pith_short_12","alias_value":"MEMFY45KTFSU","created_at":"2026-07-05T08:24:25Z"},{"alias_kind":"pith_short_16","alias_value":"MEMFY45KTFSUA4CN","created_at":"2026-07-05T08:24:25Z"},{"alias_kind":"pith_short_8","alias_value":"MEMFY45K","created_at":"2026-07-05T08:24:25Z"}],"graph_snapshots":[{"event_id":"sha256:3671878956ef1123bef1d3a7096403a725d2e66baab7098c15052e281da9fa8a","target":"graph","created_at":"2026-07-05T08:24:25Z","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/2405.13872/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in Chain-of-Thought (CoT) and related rationale-based works have significantly improved the performance of Large Language Models (LLMs) in complex reasoning tasks. With the evolution of Multimodal Large Language Models (MLLMs), enhancing their capability to tackle complex multimodal reasoning problems is a crucial frontier. However, incorporating multimodal rationales in CoT has yet to be thoroughly investigated. We propose the Image-of-Thought (IoT) prompting method, which helps MLLMs to extract visual rationales step-by-step. Specifically, IoT prompting can automatically ","authors_text":"Panzhong Lu, Qiji Zhou, Ruochen Zhou, Siyang Gao, Yue Zhang, Zike Hu","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-22T17:56:51Z","title":"Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.13872","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:b2b6bd33d84a083dcf51fb2199c5764f44e9c065323b6c57d3c76762cb37fd12","target":"record","created_at":"2026-07-05T08:24:25Z","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":"b0728d79bd9efe81478609971173e96e5fd1233eb926fba3366a1d2c51832d36","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-22T17:56:51Z","title_canon_sha256":"e04f6f8b724cfc9dcb26364cb8f1e4f5f9aa74a25c8c504c72c7ef4bb2c896d9"},"schema_version":"1.0","source":{"id":"2405.13872","kind":"arxiv","version":2}},"canonical_sha256":"61185c73aa996540704d08b221469ad97cf095e7a3d51690f8cefd57adc9daf8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"61185c73aa996540704d08b221469ad97cf095e7a3d51690f8cefd57adc9daf8","first_computed_at":"2026-07-05T08:24:25.154685Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:24:25.154685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3WF9rqAC7QS/RABPQm/j+bLz7jcze1keUElZZo4GaPAhccEiHx6AFJuEJ5lAIEGixXJ0wplO5IHd+7GVYH0MDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:24:25.155133Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.13872","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2b6bd33d84a083dcf51fb2199c5764f44e9c065323b6c57d3c76762cb37fd12","sha256:3671878956ef1123bef1d3a7096403a725d2e66baab7098c15052e281da9fa8a"],"state_sha256":"3c49684a01a61545d5c2c2390dfa70ea22e9ffbf7f5228b3e968f2c1d0ad6248"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QTZpokGl3eKysPc4AL1xJz3jiLfvVFrEKTmdZpV0jvM7pgPiW7kHSETdHJv0FLuGX3NnsrR0fZQzOHgSL+eqCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T14:33:41.453821Z","bundle_sha256":"02c1e352273cbd96066fbe387ac730c3972c48b524f5de154db6ba58efc6aebf"}}