{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KEBYCFA5IGU3RWA6PG5WHFJWGT","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":"ac862419ce3d9740f1aa4720d3dee1c5b1bc29f76ec3788f9cf4b565b91cf503","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-28T15:53:45Z","title_canon_sha256":"8ca4bc7d2d7c2254cc1e88c2eefc7585f2979066a420b232a10a870cd862c1ae"},"schema_version":"1.0","source":{"id":"2404.01322","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.01322","created_at":"2026-07-05T08:03:12Z"},{"alias_kind":"arxiv_version","alias_value":"2404.01322v1","created_at":"2026-07-05T08:03:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01322","created_at":"2026-07-05T08:03:12Z"},{"alias_kind":"pith_short_12","alias_value":"KEBYCFA5IGU3","created_at":"2026-07-05T08:03:12Z"},{"alias_kind":"pith_short_16","alias_value":"KEBYCFA5IGU3RWA6","created_at":"2026-07-05T08:03:12Z"},{"alias_kind":"pith_short_8","alias_value":"KEBYCFA5","created_at":"2026-07-05T08:03:12Z"}],"graph_snapshots":[{"event_id":"sha256:c1e4117bec1968ae8e838e5d3d089e2ac6b4894a1070c6a160df59f070f09059","target":"graph","created_at":"2026-07-05T08:03:12Z","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/2404.01322/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have recently emerged as a focal point of research and application, driven by their unprecedented ability to understand and generate text with human-like quality. Even more recently, LLMs have been extended into multi-modal large language models (MM-LLMs) which extends their capabilities to deal with image, video and audio information, in addition to text. This opens up applications like text-to-video generation, image captioning, text-to-speech, and more and is achieved either by retro-fitting an LLM with multi-modal capabilities, or building a MM-LLM from scratch","authors_text":"Alan F. Smeaton, Kilian Carolan, Laura Fennelly","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-28T15:53:45Z","title":"A Review of Multi-Modal Large Language and Vision Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01322","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:f2658f7e23f7a89e8fad3e0128d926b087fda1d98cb1a6077a2ffb9255587b17","target":"record","created_at":"2026-07-05T08:03:12Z","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":"ac862419ce3d9740f1aa4720d3dee1c5b1bc29f76ec3788f9cf4b565b91cf503","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-28T15:53:45Z","title_canon_sha256":"8ca4bc7d2d7c2254cc1e88c2eefc7585f2979066a420b232a10a870cd862c1ae"},"schema_version":"1.0","source":{"id":"2404.01322","kind":"arxiv","version":1}},"canonical_sha256":"510381141d41a9b8d81e79bb63953634d3c90f8e76958508b5293d1b30b5beaa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"510381141d41a9b8d81e79bb63953634d3c90f8e76958508b5293d1b30b5beaa","first_computed_at":"2026-07-05T08:03:12.612259Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:03:12.612259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1SOq1ouyG2cDq/2KWSl/0TYsWySS7wnwzSb/AhqhIBS8B+nDMLakMCPIcbs2RckQ2SafdGbmTDitfkB+ZvqOCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:03:12.612729Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.01322","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f2658f7e23f7a89e8fad3e0128d926b087fda1d98cb1a6077a2ffb9255587b17","sha256:c1e4117bec1968ae8e838e5d3d089e2ac6b4894a1070c6a160df59f070f09059"],"state_sha256":"4d154ca1beae6a1c04fe82aaa737836348eb4ebab385611e6de9f65abd9c6a1b"}