{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VBYH3THJDLFVKAXZVC53QFJH2T","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":"dd181815c623ff0f0aaedecb81964b93f5df6c9d8944956fa8b5cc26dff6c72b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-03T02:54:31Z","title_canon_sha256":"6f44ad61054ea5f23bd45245230649321ac0b8dd697467cea8cd6555dffcb3ff"},"schema_version":"1.0","source":{"id":"2412.02104","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.02104","created_at":"2026-07-05T09:43:44Z"},{"alias_kind":"arxiv_version","alias_value":"2412.02104v1","created_at":"2026-07-05T09:43:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02104","created_at":"2026-07-05T09:43:44Z"},{"alias_kind":"pith_short_12","alias_value":"VBYH3THJDLFV","created_at":"2026-07-05T09:43:44Z"},{"alias_kind":"pith_short_16","alias_value":"VBYH3THJDLFVKAXZ","created_at":"2026-07-05T09:43:44Z"},{"alias_kind":"pith_short_8","alias_value":"VBYH3THJ","created_at":"2026-07-05T09:43:44Z"}],"graph_snapshots":[{"event_id":"sha256:36aedb82e7b005b2e3ffffddf428f0fd207df1acb640be648d18ce9509f2091d","target":"graph","created_at":"2026-07-05T09:43:44Z","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/2412.02104/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid development of Artificial Intelligence (AI) has revolutionized numerous fields, with large language models (LLMs) and computer vision (CV) systems driving advancements in natural language understanding and visual processing, respectively. The convergence of these technologies has catalyzed the rise of multimodal AI, enabling richer, cross-modal understanding that spans text, vision, audio, and video modalities. Multimodal large language models (MLLMs), in particular, have emerged as a powerful framework, demonstrating impressive capabilities in tasks like image-text generation, visua","authors_text":"Chen Qian, Dongrui Liu, Hui Xiong, Jiahao Huo, Jie Zhang, Jing Shao, Kaichen Huang, Kun Wang, Mengxi Gao, Sirui Huang, Xuming Hu, Yibo Yan, Yong Liu, Yunkai Dang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-03T02:54:31Z","title":"Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02104","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":"sha256:9d6eb7dee971699a5f23510698c7a034b693ed637d16378f995373b84456c622","target":"record","created_at":"2026-07-05T09:43:44Z","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":"dd181815c623ff0f0aaedecb81964b93f5df6c9d8944956fa8b5cc26dff6c72b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-03T02:54:31Z","title_canon_sha256":"6f44ad61054ea5f23bd45245230649321ac0b8dd697467cea8cd6555dffcb3ff"},"schema_version":"1.0","source":{"id":"2412.02104","kind":"arxiv","version":1}},"canonical_sha256":"a8707dcce91acb5502f9a8bbb81527d4d2d59b047479ae1253b47e84c2ff83c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8707dcce91acb5502f9a8bbb81527d4d2d59b047479ae1253b47e84c2ff83c7","first_computed_at":"2026-07-05T09:43:44.065414Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:43:44.065414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kdi0lVvu7/DC6sPDNOIf4WcaE9/eWW9LQl1PVBR04xl2ULrahFg44JN86MBk0Vma/qOYrb3Q5G+1mJVGmTrJBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:43:44.065932Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.02104","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9d6eb7dee971699a5f23510698c7a034b693ed637d16378f995373b84456c622","sha256:36aedb82e7b005b2e3ffffddf428f0fd207df1acb640be648d18ce9509f2091d"],"state_sha256":"87ab5168d451e60ac2e99eb93413e748b20206a120f9b75dca0ad5cedd5c75c5"}