{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QX5VEDMDUQZ6HS3EMYG7GIY27A","short_pith_number":"pith:QX5VEDMD","canonical_record":{"source":{"id":"2403.16999","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-25T17:59:23Z","cross_cats_sorted":[],"title_canon_sha256":"0cd95bea3494f033bd819b73ff15c74b45817e14ebdd65aab7bef8f59fb810d9","abstract_canon_sha256":"dde7084216d0c19acf3c7253c64ca0ef97b6bf16211ee578d8ee8fc8c1eb7acc"},"schema_version":"1.0"},"canonical_sha256":"85fb520d83a433e3cb64660df3231af81557db2de3e0920dc03b874a3ee17444","source":{"kind":"arxiv","id":"2403.16999","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.16999","created_at":"2026-07-05T09:30:11Z"},{"alias_kind":"arxiv_version","alias_value":"2403.16999v3","created_at":"2026-07-05T09:30:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16999","created_at":"2026-07-05T09:30:11Z"},{"alias_kind":"pith_short_12","alias_value":"QX5VEDMDUQZ6","created_at":"2026-07-05T09:30:11Z"},{"alias_kind":"pith_short_16","alias_value":"QX5VEDMDUQZ6HS3E","created_at":"2026-07-05T09:30:11Z"},{"alias_kind":"pith_short_8","alias_value":"QX5VEDMD","created_at":"2026-07-05T09:30:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QX5VEDMDUQZ6HS3EMYG7GIY27A","target":"record","payload":{"canonical_record":{"source":{"id":"2403.16999","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-25T17:59:23Z","cross_cats_sorted":[],"title_canon_sha256":"0cd95bea3494f033bd819b73ff15c74b45817e14ebdd65aab7bef8f59fb810d9","abstract_canon_sha256":"dde7084216d0c19acf3c7253c64ca0ef97b6bf16211ee578d8ee8fc8c1eb7acc"},"schema_version":"1.0"},"canonical_sha256":"85fb520d83a433e3cb64660df3231af81557db2de3e0920dc03b874a3ee17444","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:11.613018Z","signature_b64":"GNe/LoUq8dVRXY/kvU38a3c3Y4ZWZCr/EdY6uXw2iOsELQTG4l7eJLgZz6jlTlOO8IE8e+NYvvZ8saGFrBJHAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85fb520d83a433e3cb64660df3231af81557db2de3e0920dc03b874a3ee17444","last_reissued_at":"2026-07-05T09:30:11.612589Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:11.612589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.16999","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:30:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9McP0D2pM9Ts49Ldze85OkOfG8g1Czy6VMxuuXbjdT4SAfkABn5iU+HRfx08xYKEm8XZkwkz4KpdnZRZQ1ffAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:01:18.569744Z"},"content_sha256":"180024c918a82663401e69df83b0ecb374e28904abf21cb39cf0e44c166bac61","schema_version":"1.0","event_id":"sha256:180024c918a82663401e69df83b0ecb374e28904abf21cb39cf0e44c166bac61"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QX5VEDMDUQZ6HS3EMYG7GIY27A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guanglu Song, Han Xiao, Hao Shao, Hongsheng Li, Letian Wang, Shengju Qian, Yu Liu, Zhuofan Zong","submitted_at":"2024-03-25T17:59:23Z","abstract_excerpt":"Multi-Modal Large Language Models (MLLMs) have demonstrated impressive performance in various VQA tasks. However, they often lack interpretability and struggle with complex visual inputs, especially when the resolution of the input image is high or when the interested region that could provide key information for answering the question is small. To address these challenges, we collect and introduce the large-scale Visual CoT dataset comprising 438k question-answer pairs, annotated with intermediate bounding boxes highlighting key regions essential for answering the questions. Additionally, abo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16999","kind":"arxiv","version":3},"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/2403.16999/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":"2026-07-05T09:30:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wf3QApV5Gjnwq3jm3tezFnhbLkQJGteOl1+ImCKfm6siXy2PCON1nqQtLE+S7hwO1Uxqpx1RLT7VvhLRzih9BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:01:18.570277Z"},"content_sha256":"d5a03a837ea288d61d93cde577064fcf2f0c08c93911d6d07f3bf0c1c1bc8052","schema_version":"1.0","event_id":"sha256:d5a03a837ea288d61d93cde577064fcf2f0c08c93911d6d07f3bf0c1c1bc8052"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QX5VEDMDUQZ6HS3EMYG7GIY27A/bundle.json","state_url":"https://pith.science/pith/QX5VEDMDUQZ6HS3EMYG7GIY27A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QX5VEDMDUQZ6HS3EMYG7GIY27A/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":"2026-08-06T07:01:18Z","links":{"resolver":"https://pith.science/pith/QX5VEDMDUQZ6HS3EMYG7GIY27A","bundle":"https://pith.science/pith/QX5VEDMDUQZ6HS3EMYG7GIY27A/bundle.json","state":"https://pith.science/pith/QX5VEDMDUQZ6HS3EMYG7GIY27A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QX5VEDMDUQZ6HS3EMYG7GIY27A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QX5VEDMDUQZ6HS3EMYG7GIY27A","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":"dde7084216d0c19acf3c7253c64ca0ef97b6bf16211ee578d8ee8fc8c1eb7acc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-25T17:59:23Z","title_canon_sha256":"0cd95bea3494f033bd819b73ff15c74b45817e14ebdd65aab7bef8f59fb810d9"},"schema_version":"1.0","source":{"id":"2403.16999","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.16999","created_at":"2026-07-05T09:30:11Z"},{"alias_kind":"arxiv_version","alias_value":"2403.16999v3","created_at":"2026-07-05T09:30:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16999","created_at":"2026-07-05T09:30:11Z"},{"alias_kind":"pith_short_12","alias_value":"QX5VEDMDUQZ6","created_at":"2026-07-05T09:30:11Z"},{"alias_kind":"pith_short_16","alias_value":"QX5VEDMDUQZ6HS3E","created_at":"2026-07-05T09:30:11Z"},{"alias_kind":"pith_short_8","alias_value":"QX5VEDMD","created_at":"2026-07-05T09:30:11Z"}],"graph_snapshots":[{"event_id":"sha256:d5a03a837ea288d61d93cde577064fcf2f0c08c93911d6d07f3bf0c1c1bc8052","target":"graph","created_at":"2026-07-05T09:30:11Z","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/2403.16999/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-Modal Large Language Models (MLLMs) have demonstrated impressive performance in various VQA tasks. However, they often lack interpretability and struggle with complex visual inputs, especially when the resolution of the input image is high or when the interested region that could provide key information for answering the question is small. To address these challenges, we collect and introduce the large-scale Visual CoT dataset comprising 438k question-answer pairs, annotated with intermediate bounding boxes highlighting key regions essential for answering the questions. Additionally, abo","authors_text":"Guanglu Song, Han Xiao, Hao Shao, Hongsheng Li, Letian Wang, Shengju Qian, Yu Liu, Zhuofan Zong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-25T17:59:23Z","title":"Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16999","kind":"arxiv","version":3},"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":"sha256:180024c918a82663401e69df83b0ecb374e28904abf21cb39cf0e44c166bac61","target":"record","created_at":"2026-07-05T09:30:11Z","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":"dde7084216d0c19acf3c7253c64ca0ef97b6bf16211ee578d8ee8fc8c1eb7acc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-25T17:59:23Z","title_canon_sha256":"0cd95bea3494f033bd819b73ff15c74b45817e14ebdd65aab7bef8f59fb810d9"},"schema_version":"1.0","source":{"id":"2403.16999","kind":"arxiv","version":3}},"canonical_sha256":"85fb520d83a433e3cb64660df3231af81557db2de3e0920dc03b874a3ee17444","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"85fb520d83a433e3cb64660df3231af81557db2de3e0920dc03b874a3ee17444","first_computed_at":"2026-07-05T09:30:11.612589Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:30:11.612589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GNe/LoUq8dVRXY/kvU38a3c3Y4ZWZCr/EdY6uXw2iOsELQTG4l7eJLgZz6jlTlOO8IE8e+NYvvZ8saGFrBJHAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:30:11.613018Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.16999","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:180024c918a82663401e69df83b0ecb374e28904abf21cb39cf0e44c166bac61","sha256:d5a03a837ea288d61d93cde577064fcf2f0c08c93911d6d07f3bf0c1c1bc8052"],"state_sha256":"c7fb06c3e78976427e44fc96382069e89c90519dfa51655b39d355e20005137c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0qNB0xUl4VehYAtaX5/rrI16vCZEfcSCWl86cEqJ0MhAU2H+xN19dgcawCKD1N8kP6szvqIQBLlqVEswczzVBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T07:01:18.574395Z","bundle_sha256":"552d3eb68017f887f0b65cde3ea1bf6dff052d980f223eacc518c70dd39be4fd"}}