{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KEBYCFA5IGU3RWA6PG5WHFJWGT","short_pith_number":"pith:KEBYCFA5","schema_version":"1.0","canonical_sha256":"510381141d41a9b8d81e79bb63953634d3c90f8e76958508b5293d1b30b5beaa","source":{"kind":"arxiv","id":"2404.01322","version":1},"attestation_state":"computed","paper":{"title":"A Review of Multi-Modal Large Language and Vision Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alan F. Smeaton, Kilian Carolan, Laura Fennelly","submitted_at":"2024-03-28T15:53:45Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2404.01322","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-28T15:53:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8ca4bc7d2d7c2254cc1e88c2eefc7585f2979066a420b232a10a870cd862c1ae","abstract_canon_sha256":"ac862419ce3d9740f1aa4720d3dee1c5b1bc29f76ec3788f9cf4b565b91cf503"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:12.612729Z","signature_b64":"1SOq1ouyG2cDq/2KWSl/0TYsWySS7wnwzSb/AhqhIBS8B+nDMLakMCPIcbs2RckQ2SafdGbmTDitfkB+ZvqOCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"510381141d41a9b8d81e79bb63953634d3c90f8e76958508b5293d1b30b5beaa","last_reissued_at":"2026-07-05T08:03:12.612259Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:12.612259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Review of Multi-Modal Large Language and Vision Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alan F. Smeaton, Kilian Carolan, Laura Fennelly","submitted_at":"2024-03-28T15:53:45Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01322","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/2404.01322/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2404.01322","created_at":"2026-07-05T08:03:12.612322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.01322v1","created_at":"2026-07-05T08:03:12.612322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01322","created_at":"2026-07-05T08:03:12.612322+00:00"},{"alias_kind":"pith_short_12","alias_value":"KEBYCFA5IGU3","created_at":"2026-07-05T08:03:12.612322+00:00"},{"alias_kind":"pith_short_16","alias_value":"KEBYCFA5IGU3RWA6","created_at":"2026-07-05T08:03:12.612322+00:00"},{"alias_kind":"pith_short_8","alias_value":"KEBYCFA5","created_at":"2026-07-05T08:03:12.612322+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27920","citing_title":"Rethinking Video-Language Model from the Language Input Perspective","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01938","citing_title":"Cross-Layer Energy Analysis of Multimodal Training on Grace Hopper Superchips","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20190","citing_title":"WildFireVQA: A Large-Scale Radiometric Thermal VQA Benchmark for Aerial Wildfire Monitoring","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01938","citing_title":"Cross-Layer Energy Analysis of Multimodal Training on Grace Hopper Superchips","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KEBYCFA5IGU3RWA6PG5WHFJWGT","json":"https://pith.science/pith/KEBYCFA5IGU3RWA6PG5WHFJWGT.json","graph_json":"https://pith.science/api/pith-number/KEBYCFA5IGU3RWA6PG5WHFJWGT/graph.json","events_json":"https://pith.science/api/pith-number/KEBYCFA5IGU3RWA6PG5WHFJWGT/events.json","paper":"https://pith.science/paper/KEBYCFA5"},"agent_actions":{"view_html":"https://pith.science/pith/KEBYCFA5IGU3RWA6PG5WHFJWGT","download_json":"https://pith.science/pith/KEBYCFA5IGU3RWA6PG5WHFJWGT.json","view_paper":"https://pith.science/paper/KEBYCFA5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.01322&json=true","fetch_graph":"https://pith.science/api/pith-number/KEBYCFA5IGU3RWA6PG5WHFJWGT/graph.json","fetch_events":"https://pith.science/api/pith-number/KEBYCFA5IGU3RWA6PG5WHFJWGT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KEBYCFA5IGU3RWA6PG5WHFJWGT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KEBYCFA5IGU3RWA6PG5WHFJWGT/action/storage_attestation","attest_author":"https://pith.science/pith/KEBYCFA5IGU3RWA6PG5WHFJWGT/action/author_attestation","sign_citation":"https://pith.science/pith/KEBYCFA5IGU3RWA6PG5WHFJWGT/action/citation_signature","submit_replication":"https://pith.science/pith/KEBYCFA5IGU3RWA6PG5WHFJWGT/action/replication_record"}},"created_at":"2026-07-05T08:03:12.612322+00:00","updated_at":"2026-07-05T08:03:12.612322+00:00"}