{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:I5OBOOBFIDUBUKY7QVPJCRZEAN","short_pith_number":"pith:I5OBOOBF","canonical_record":{"source":{"id":"2411.17558","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-26T16:21:03Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"492ad469afbad66762f9a7c43667696024566e3eef44b8ffab96c54a4531d2a9","abstract_canon_sha256":"28b679baa4da05ed4625f7584b1b697caa5317f4235020762afa2e9781ace9e9"},"schema_version":"1.0"},"canonical_sha256":"475c17382540e81a2b1f855e914724035301effba3be551cb3bad7292137156b","source":{"kind":"arxiv","id":"2411.17558","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.17558","created_at":"2026-07-05T09:40:48Z"},{"alias_kind":"arxiv_version","alias_value":"2411.17558v1","created_at":"2026-07-05T09:40:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17558","created_at":"2026-07-05T09:40:48Z"},{"alias_kind":"pith_short_12","alias_value":"I5OBOOBFIDUB","created_at":"2026-07-05T09:40:48Z"},{"alias_kind":"pith_short_16","alias_value":"I5OBOOBFIDUBUKY7","created_at":"2026-07-05T09:40:48Z"},{"alias_kind":"pith_short_8","alias_value":"I5OBOOBF","created_at":"2026-07-05T09:40:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:I5OBOOBFIDUBUKY7QVPJCRZEAN","target":"record","payload":{"canonical_record":{"source":{"id":"2411.17558","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-26T16:21:03Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"492ad469afbad66762f9a7c43667696024566e3eef44b8ffab96c54a4531d2a9","abstract_canon_sha256":"28b679baa4da05ed4625f7584b1b697caa5317f4235020762afa2e9781ace9e9"},"schema_version":"1.0"},"canonical_sha256":"475c17382540e81a2b1f855e914724035301effba3be551cb3bad7292137156b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:48.944746Z","signature_b64":"Svyb9dt8hU5grUh404AWRRv/686IaeazifHipALAdCpnaJ3CnQB97mxkOoLguX4Aj/P/7WU7Fd9R6+EjpulaAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"475c17382540e81a2b1f855e914724035301effba3be551cb3bad7292137156b","last_reissued_at":"2026-07-05T09:40:48.944275Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:48.944275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.17558","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":"2026-07-05T09:40:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S8HUEoSAp5wy0+y9gZljxTc7WdHHFqGTzzz6JoWlGIb0TNQyVysVHjiSZMo3HXlNJsHikFdNSV0uqmX9cR/nDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:05:25.781612Z"},"content_sha256":"a208c452dc850d246c3e2d386828d04006bf982165e68c50d93d1539a68969b7","schema_version":"1.0","event_id":"sha256:a208c452dc850d246c3e2d386828d04006bf982165e68c50d93d1539a68969b7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:I5OBOOBFIDUBUKY7QVPJCRZEAN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Haohao Luo, Jiayi Kuang, Jingyou Xie, Ronghao Li, Xianfeng Cheng, Xika Lin, Yinghui Li, Ying Shen, Zhe Xu","submitted_at":"2024-11-26T16:21:03Z","abstract_excerpt":"Visual Question Answering (VQA) is a challenge task that combines natural language processing and computer vision techniques and gradually becomes a benchmark test task in multimodal large language models (MLLMs). The goal of our survey is to provide an overview of the development of VQA and a detailed description of the latest models with high timeliness. This survey gives an up-to-date synthesis of natural language understanding of images and text, as well as the knowledge reasoning module based on image-question information on the core VQA tasks. In addition, we elaborate on recent advances"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17558","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/2411.17558/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":"2026-07-05T09:40:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ega+MfmwHMUl8+7mpEMCBMQsJlLmNg/Ap21piMKVbG4r0yKudNZfaGd8POM4H22Uv2gJCyvh+/2WDO4S8FtjDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:05:25.782463Z"},"content_sha256":"8b428a6ca6017e4be8845af3e15966d4137f4bd8142ef16af9672a0b3d02badc","schema_version":"1.0","event_id":"sha256:8b428a6ca6017e4be8845af3e15966d4137f4bd8142ef16af9672a0b3d02badc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I5OBOOBFIDUBUKY7QVPJCRZEAN/bundle.json","state_url":"https://pith.science/pith/I5OBOOBFIDUBUKY7QVPJCRZEAN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I5OBOOBFIDUBUKY7QVPJCRZEAN/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":"2026-08-10T08:05:25Z","links":{"resolver":"https://pith.science/pith/I5OBOOBFIDUBUKY7QVPJCRZEAN","bundle":"https://pith.science/pith/I5OBOOBFIDUBUKY7QVPJCRZEAN/bundle.json","state":"https://pith.science/pith/I5OBOOBFIDUBUKY7QVPJCRZEAN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I5OBOOBFIDUBUKY7QVPJCRZEAN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:I5OBOOBFIDUBUKY7QVPJCRZEAN","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":"28b679baa4da05ed4625f7584b1b697caa5317f4235020762afa2e9781ace9e9","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-26T16:21:03Z","title_canon_sha256":"492ad469afbad66762f9a7c43667696024566e3eef44b8ffab96c54a4531d2a9"},"schema_version":"1.0","source":{"id":"2411.17558","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.17558","created_at":"2026-07-05T09:40:48Z"},{"alias_kind":"arxiv_version","alias_value":"2411.17558v1","created_at":"2026-07-05T09:40:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17558","created_at":"2026-07-05T09:40:48Z"},{"alias_kind":"pith_short_12","alias_value":"I5OBOOBFIDUB","created_at":"2026-07-05T09:40:48Z"},{"alias_kind":"pith_short_16","alias_value":"I5OBOOBFIDUBUKY7","created_at":"2026-07-05T09:40:48Z"},{"alias_kind":"pith_short_8","alias_value":"I5OBOOBF","created_at":"2026-07-05T09:40:48Z"}],"graph_snapshots":[{"event_id":"sha256:8b428a6ca6017e4be8845af3e15966d4137f4bd8142ef16af9672a0b3d02badc","target":"graph","created_at":"2026-07-05T09:40:48Z","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/2411.17558/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual Question Answering (VQA) is a challenge task that combines natural language processing and computer vision techniques and gradually becomes a benchmark test task in multimodal large language models (MLLMs). The goal of our survey is to provide an overview of the development of VQA and a detailed description of the latest models with high timeliness. This survey gives an up-to-date synthesis of natural language understanding of images and text, as well as the knowledge reasoning module based on image-question information on the core VQA tasks. In addition, we elaborate on recent advances","authors_text":"Haohao Luo, Jiayi Kuang, Jingyou Xie, Ronghao Li, Xianfeng Cheng, Xika Lin, Yinghui Li, Ying Shen, Zhe Xu","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-26T16:21:03Z","title":"Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17558","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:a208c452dc850d246c3e2d386828d04006bf982165e68c50d93d1539a68969b7","target":"record","created_at":"2026-07-05T09:40:48Z","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":"28b679baa4da05ed4625f7584b1b697caa5317f4235020762afa2e9781ace9e9","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-26T16:21:03Z","title_canon_sha256":"492ad469afbad66762f9a7c43667696024566e3eef44b8ffab96c54a4531d2a9"},"schema_version":"1.0","source":{"id":"2411.17558","kind":"arxiv","version":1}},"canonical_sha256":"475c17382540e81a2b1f855e914724035301effba3be551cb3bad7292137156b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"475c17382540e81a2b1f855e914724035301effba3be551cb3bad7292137156b","first_computed_at":"2026-07-05T09:40:48.944275Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:40:48.944275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Svyb9dt8hU5grUh404AWRRv/686IaeazifHipALAdCpnaJ3CnQB97mxkOoLguX4Aj/P/7WU7Fd9R6+EjpulaAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:40:48.944746Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.17558","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a208c452dc850d246c3e2d386828d04006bf982165e68c50d93d1539a68969b7","sha256:8b428a6ca6017e4be8845af3e15966d4137f4bd8142ef16af9672a0b3d02badc"],"state_sha256":"2acb5ca25d8922149656632d09ff4cbb28d9dd6473b50f0ef5b08a9efd6ac3c6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cIzJ5vujiIz6fxIs9FMXTduKXYGWq8TmNYxK1KQ1ZPS7QyVFZzZBzZ8zLE9RYo9NgcJgs+/rt81fSk0pUjisDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T08:05:25.788757Z","bundle_sha256":"0afc1ecece44eb22441db171422be0d0bf18a122a87df0ecb039e3f338a0328e"}}