{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NRI7CSXNXBWLMQ4LYXDCUPQ5HJ","short_pith_number":"pith:NRI7CSXN","canonical_record":{"source":{"id":"2412.05243","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-06T18:22:47Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"917fcc319e915c8435b1e9c38b4a819951aed2a3de7739e346a5bce92e22afc1","abstract_canon_sha256":"f9e1aa2da75311dbf654bfc32992758eb0959ea79181813dc4b561c21e7b10d5"},"schema_version":"1.0"},"canonical_sha256":"6c51f14aedb86cb6438bc5c62a3e1d3a709eeceda96a50b75c1ef0b70349ce33","source":{"kind":"arxiv","id":"2412.05243","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.05243","created_at":"2026-07-05T09:45:30Z"},{"alias_kind":"arxiv_version","alias_value":"2412.05243v1","created_at":"2026-07-05T09:45:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05243","created_at":"2026-07-05T09:45:30Z"},{"alias_kind":"pith_short_12","alias_value":"NRI7CSXNXBWL","created_at":"2026-07-05T09:45:30Z"},{"alias_kind":"pith_short_16","alias_value":"NRI7CSXNXBWLMQ4L","created_at":"2026-07-05T09:45:30Z"},{"alias_kind":"pith_short_8","alias_value":"NRI7CSXN","created_at":"2026-07-05T09:45:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NRI7CSXNXBWLMQ4LYXDCUPQ5HJ","target":"record","payload":{"canonical_record":{"source":{"id":"2412.05243","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-06T18:22:47Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"917fcc319e915c8435b1e9c38b4a819951aed2a3de7739e346a5bce92e22afc1","abstract_canon_sha256":"f9e1aa2da75311dbf654bfc32992758eb0959ea79181813dc4b561c21e7b10d5"},"schema_version":"1.0"},"canonical_sha256":"6c51f14aedb86cb6438bc5c62a3e1d3a709eeceda96a50b75c1ef0b70349ce33","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:30.710055Z","signature_b64":"KfUuEWH8/W2VzOwBMAscPbdXVttf0k0pIK8Tb5iRthJ9ry1CqbE7iK7hrQmyRKCs+s+ybZh59xRrEwdOCtmFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c51f14aedb86cb6438bc5c62a3e1d3a709eeceda96a50b75c1ef0b70349ce33","last_reissued_at":"2026-07-05T09:45:30.709624Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:30.709624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.05243","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":"2026-07-05T09:45:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B/ax4RVsPqR/8Ee0cvbK+HBq4kwExlT+7wkgrosgAC3dI9Q+f9TXxODn0gmPMzEDw0zh79uEO4v6uPIJwt7ICQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:59:13.748452Z"},"content_sha256":"23b3b4972d8320c059ff62a0e2dd28b37101eaf96280c202235ec1efee111ac1","schema_version":"1.0","event_id":"sha256:23b3b4972d8320c059ff62a0e2dd28b37101eaf96280c202235ec1efee111ac1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NRI7CSXNXBWLMQ4LYXDCUPQ5HJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CompCap: Improving Multimodal Large Language Models with Composite Captions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Aashu Singh, Baosheng He, David Yang, Hanchao Yu, Mahmoud Azab, Qifan Wang, Satya Narayan Shukla, ShengYun Peng, Shen Yan, Xiaohui Chen, Xuewen Zhang","submitted_at":"2024-12-06T18:22:47Z","abstract_excerpt":"How well can Multimodal Large Language Models (MLLMs) understand composite images? Composite images (CIs) are synthetic visuals created by merging multiple visual elements, such as charts, posters, or screenshots, rather than being captured directly by a camera. While CIs are prevalent in real-world applications, recent MLLM developments have primarily focused on interpreting natural images (NIs). Our research reveals that current MLLMs face significant challenges in accurately understanding CIs, often struggling to extract information or perform complex reasoning based on these images. We fin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05243","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/2412.05243/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":"2026-07-05T09:45:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E32TEQUcIZunhLWIa0PdQWQGU9SBOcnrNpGuuB8pN909iA+EHc/AOsTgC2wCw8qGMi6JZF/yM05+i7DT395SDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:59:13.748834Z"},"content_sha256":"02f913b786ee3d2ea7bc7e4452f0c60ce28d8c64efc93fe212ed6a963676a5d7","schema_version":"1.0","event_id":"sha256:02f913b786ee3d2ea7bc7e4452f0c60ce28d8c64efc93fe212ed6a963676a5d7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NRI7CSXNXBWLMQ4LYXDCUPQ5HJ/bundle.json","state_url":"https://pith.science/pith/NRI7CSXNXBWLMQ4LYXDCUPQ5HJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NRI7CSXNXBWLMQ4LYXDCUPQ5HJ/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":"2026-07-07T05:59:13Z","links":{"resolver":"https://pith.science/pith/NRI7CSXNXBWLMQ4LYXDCUPQ5HJ","bundle":"https://pith.science/pith/NRI7CSXNXBWLMQ4LYXDCUPQ5HJ/bundle.json","state":"https://pith.science/pith/NRI7CSXNXBWLMQ4LYXDCUPQ5HJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NRI7CSXNXBWLMQ4LYXDCUPQ5HJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NRI7CSXNXBWLMQ4LYXDCUPQ5HJ","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":"f9e1aa2da75311dbf654bfc32992758eb0959ea79181813dc4b561c21e7b10d5","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-06T18:22:47Z","title_canon_sha256":"917fcc319e915c8435b1e9c38b4a819951aed2a3de7739e346a5bce92e22afc1"},"schema_version":"1.0","source":{"id":"2412.05243","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.05243","created_at":"2026-07-05T09:45:30Z"},{"alias_kind":"arxiv_version","alias_value":"2412.05243v1","created_at":"2026-07-05T09:45:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05243","created_at":"2026-07-05T09:45:30Z"},{"alias_kind":"pith_short_12","alias_value":"NRI7CSXNXBWL","created_at":"2026-07-05T09:45:30Z"},{"alias_kind":"pith_short_16","alias_value":"NRI7CSXNXBWLMQ4L","created_at":"2026-07-05T09:45:30Z"},{"alias_kind":"pith_short_8","alias_value":"NRI7CSXN","created_at":"2026-07-05T09:45:30Z"}],"graph_snapshots":[{"event_id":"sha256:02f913b786ee3d2ea7bc7e4452f0c60ce28d8c64efc93fe212ed6a963676a5d7","target":"graph","created_at":"2026-07-05T09:45:30Z","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/2412.05243/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"How well can Multimodal Large Language Models (MLLMs) understand composite images? Composite images (CIs) are synthetic visuals created by merging multiple visual elements, such as charts, posters, or screenshots, rather than being captured directly by a camera. While CIs are prevalent in real-world applications, recent MLLM developments have primarily focused on interpreting natural images (NIs). Our research reveals that current MLLMs face significant challenges in accurately understanding CIs, often struggling to extract information or perform complex reasoning based on these images. We fin","authors_text":"Aashu Singh, Baosheng He, David Yang, Hanchao Yu, Mahmoud Azab, Qifan Wang, Satya Narayan Shukla, ShengYun Peng, Shen Yan, Xiaohui Chen, Xuewen Zhang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-06T18:22:47Z","title":"CompCap: Improving Multimodal Large Language Models with Composite Captions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05243","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":"sha256:23b3b4972d8320c059ff62a0e2dd28b37101eaf96280c202235ec1efee111ac1","target":"record","created_at":"2026-07-05T09:45:30Z","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":"f9e1aa2da75311dbf654bfc32992758eb0959ea79181813dc4b561c21e7b10d5","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-06T18:22:47Z","title_canon_sha256":"917fcc319e915c8435b1e9c38b4a819951aed2a3de7739e346a5bce92e22afc1"},"schema_version":"1.0","source":{"id":"2412.05243","kind":"arxiv","version":1}},"canonical_sha256":"6c51f14aedb86cb6438bc5c62a3e1d3a709eeceda96a50b75c1ef0b70349ce33","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6c51f14aedb86cb6438bc5c62a3e1d3a709eeceda96a50b75c1ef0b70349ce33","first_computed_at":"2026-07-05T09:45:30.709624Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:30.709624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KfUuEWH8/W2VzOwBMAscPbdXVttf0k0pIK8Tb5iRthJ9ry1CqbE7iK7hrQmyRKCs+s+ybZh59xRrEwdOCtmFDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:30.710055Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.05243","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23b3b4972d8320c059ff62a0e2dd28b37101eaf96280c202235ec1efee111ac1","sha256:02f913b786ee3d2ea7bc7e4452f0c60ce28d8c64efc93fe212ed6a963676a5d7"],"state_sha256":"418cad040fd61a48e313647fee941bfe72586405f3c4b7ca041582a9a717ba90"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4H6ZGOVh91EV8Cwl+ybwi9vpOPTAewIbJ8z1u1c7kjrSRSqiYBWWn1mQVZCHoyPsmJ79ZJivsCzCdZETxQ/KAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T05:59:13.751023Z","bundle_sha256":"184daf98cb96f3a3df5cbe1109c1b763ee128183a91c1af127fe79f3a2ef74dc"}}