{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LFUUEEEYAGHG3Z6I6ESCZMQJY6","short_pith_number":"pith:LFUUEEEY","canonical_record":{"source":{"id":"2409.19339","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-28T12:49:16Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"026def747f156d2347fd00b83b4f2d06be372660d8080e4793a5713839fc326b","abstract_canon_sha256":"ac754b70bd8c10c10aee7cb344e2f5be7447740aa6d22301856cc6c786d8557e"},"schema_version":"1.0"},"canonical_sha256":"5969421098018e6de7c8f1242cb209c7b7cdbdb9d514b9a62750ad46d7ee0d73","source":{"kind":"arxiv","id":"2409.19339","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.19339","created_at":"2026-07-05T09:16:53Z"},{"alias_kind":"arxiv_version","alias_value":"2409.19339v2","created_at":"2026-07-05T09:16:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19339","created_at":"2026-07-05T09:16:53Z"},{"alias_kind":"pith_short_12","alias_value":"LFUUEEEYAGHG","created_at":"2026-07-05T09:16:53Z"},{"alias_kind":"pith_short_16","alias_value":"LFUUEEEYAGHG3Z6I","created_at":"2026-07-05T09:16:53Z"},{"alias_kind":"pith_short_8","alias_value":"LFUUEEEY","created_at":"2026-07-05T09:16:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LFUUEEEYAGHG3Z6I6ESCZMQJY6","target":"record","payload":{"canonical_record":{"source":{"id":"2409.19339","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-28T12:49:16Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"026def747f156d2347fd00b83b4f2d06be372660d8080e4793a5713839fc326b","abstract_canon_sha256":"ac754b70bd8c10c10aee7cb344e2f5be7447740aa6d22301856cc6c786d8557e"},"schema_version":"1.0"},"canonical_sha256":"5969421098018e6de7c8f1242cb209c7b7cdbdb9d514b9a62750ad46d7ee0d73","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:53.133281Z","signature_b64":"p2w6nIlN2J1bKE2XYZpAzc2UO62Zkpr+P2JxtA9d0kwYAg7z03nOZaQW/c8ID8HjEkg9RNKjdL6J1c6n/vRMDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5969421098018e6de7c8f1242cb209c7b7cdbdb9d514b9a62750ad46d7ee0d73","last_reissued_at":"2026-07-05T09:16:53.132799Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:53.132799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.19339","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":"2026-07-05T09:16:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f/VWZdg32z3LdoBG11kgu9BCtazoa7/B4HvU7/GXfee72bk90mTdvHfucP7G+L+gYXgiaIfEOxJlMHXsMgzlCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:36:15.690879Z"},"content_sha256":"e66d1e244054dfd159e4f81582a72f66e9dc81778a295eb722c419e9da1318bd","schema_version":"1.0","event_id":"sha256:e66d1e244054dfd159e4f81582a72f66e9dc81778a295eb722c419e9da1318bd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LFUUEEEYAGHG3Z6I6ESCZMQJY6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visual Question Decomposition on Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bailan He, Haowei Zhang, Jianzhe Liu, Jindong Gu, Shuo Chen, Volker Tresp, Zhen Han, Zhiqiang Xu","submitted_at":"2024-09-28T12:49:16Z","abstract_excerpt":"Question decomposition has emerged as an effective strategy for prompting Large Language Models (LLMs) to answer complex questions. However, while existing methods primarily focus on unimodal language models, the question decomposition capability of Multimodal Large Language Models (MLLMs) has yet to be explored. To this end, this paper explores visual question decomposition on MLLMs. Specifically, we introduce a systematic evaluation framework including a dataset and several evaluation criteria to assess the quality of the decomposed sub-questions, revealing that existing MLLMs struggle to pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19339","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/2409.19339/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":"2026-07-05T09:16:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"We8A3Yp0iNboDkgIjZSnMXy1mleaeR8YCgd27X8QiNnR21roca2jj9P3rypuo2XveHPvPtcUWGD4vcWwdFofAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:36:15.691885Z"},"content_sha256":"8fd49325aea8113fb8829921099104348eb5b7fc3d2248d748cf31a941d5c4f3","schema_version":"1.0","event_id":"sha256:8fd49325aea8113fb8829921099104348eb5b7fc3d2248d748cf31a941d5c4f3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LFUUEEEYAGHG3Z6I6ESCZMQJY6/bundle.json","state_url":"https://pith.science/pith/LFUUEEEYAGHG3Z6I6ESCZMQJY6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LFUUEEEYAGHG3Z6I6ESCZMQJY6/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":"2026-08-05T12:36:15Z","links":{"resolver":"https://pith.science/pith/LFUUEEEYAGHG3Z6I6ESCZMQJY6","bundle":"https://pith.science/pith/LFUUEEEYAGHG3Z6I6ESCZMQJY6/bundle.json","state":"https://pith.science/pith/LFUUEEEYAGHG3Z6I6ESCZMQJY6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LFUUEEEYAGHG3Z6I6ESCZMQJY6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LFUUEEEYAGHG3Z6I6ESCZMQJY6","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":"ac754b70bd8c10c10aee7cb344e2f5be7447740aa6d22301856cc6c786d8557e","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-28T12:49:16Z","title_canon_sha256":"026def747f156d2347fd00b83b4f2d06be372660d8080e4793a5713839fc326b"},"schema_version":"1.0","source":{"id":"2409.19339","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.19339","created_at":"2026-07-05T09:16:53Z"},{"alias_kind":"arxiv_version","alias_value":"2409.19339v2","created_at":"2026-07-05T09:16:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19339","created_at":"2026-07-05T09:16:53Z"},{"alias_kind":"pith_short_12","alias_value":"LFUUEEEYAGHG","created_at":"2026-07-05T09:16:53Z"},{"alias_kind":"pith_short_16","alias_value":"LFUUEEEYAGHG3Z6I","created_at":"2026-07-05T09:16:53Z"},{"alias_kind":"pith_short_8","alias_value":"LFUUEEEY","created_at":"2026-07-05T09:16:53Z"}],"graph_snapshots":[{"event_id":"sha256:8fd49325aea8113fb8829921099104348eb5b7fc3d2248d748cf31a941d5c4f3","target":"graph","created_at":"2026-07-05T09:16:53Z","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/2409.19339/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Question decomposition has emerged as an effective strategy for prompting Large Language Models (LLMs) to answer complex questions. However, while existing methods primarily focus on unimodal language models, the question decomposition capability of Multimodal Large Language Models (MLLMs) has yet to be explored. To this end, this paper explores visual question decomposition on MLLMs. Specifically, we introduce a systematic evaluation framework including a dataset and several evaluation criteria to assess the quality of the decomposed sub-questions, revealing that existing MLLMs struggle to pr","authors_text":"Bailan He, Haowei Zhang, Jianzhe Liu, Jindong Gu, Shuo Chen, Volker Tresp, Zhen Han, Zhiqiang Xu","cross_cats":["cs.AI","cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-28T12:49:16Z","title":"Visual Question Decomposition on Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19339","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:e66d1e244054dfd159e4f81582a72f66e9dc81778a295eb722c419e9da1318bd","target":"record","created_at":"2026-07-05T09:16:53Z","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":"ac754b70bd8c10c10aee7cb344e2f5be7447740aa6d22301856cc6c786d8557e","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-28T12:49:16Z","title_canon_sha256":"026def747f156d2347fd00b83b4f2d06be372660d8080e4793a5713839fc326b"},"schema_version":"1.0","source":{"id":"2409.19339","kind":"arxiv","version":2}},"canonical_sha256":"5969421098018e6de7c8f1242cb209c7b7cdbdb9d514b9a62750ad46d7ee0d73","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5969421098018e6de7c8f1242cb209c7b7cdbdb9d514b9a62750ad46d7ee0d73","first_computed_at":"2026-07-05T09:16:53.132799Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:53.132799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p2w6nIlN2J1bKE2XYZpAzc2UO62Zkpr+P2JxtA9d0kwYAg7z03nOZaQW/c8ID8HjEkg9RNKjdL6J1c6n/vRMDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:53.133281Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.19339","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e66d1e244054dfd159e4f81582a72f66e9dc81778a295eb722c419e9da1318bd","sha256:8fd49325aea8113fb8829921099104348eb5b7fc3d2248d748cf31a941d5c4f3"],"state_sha256":"c7ab1843d36731a38493b8d5aec63d1680ef6f838160556afc7e562f28587087"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"14cpsC+pa+b4/KOo0hnnhqSJz2rNqJtHHJJ1oRMfRpWvNnHcJnifVfE/F7Lt57qs/nRjWoVc3YNl2RA8r6JyAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T12:36:15.698842Z","bundle_sha256":"8aed47b0b6b6bf93bf3c093b513b9e7bb768cae504b63e44302e86000228e384"}}