{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GHYYKOU3XMGQLTTW6ACAUHZBVY","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":"e426540062eefb76a0b47f1b5f148243e43f28d0edc7303bd27aeac932077fc1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-09T11:00:19Z","title_canon_sha256":"4893efa0233a060e0eef6b1fb0eea42026e4fae404163d33e0ee9500eeaad1eb"},"schema_version":"1.0","source":{"id":"2404.06212","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.06212","created_at":"2026-07-05T08:06:05Z"},{"alias_kind":"arxiv_version","alias_value":"2404.06212v1","created_at":"2026-07-05T08:06:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.06212","created_at":"2026-07-05T08:06:05Z"},{"alias_kind":"pith_short_12","alias_value":"GHYYKOU3XMGQ","created_at":"2026-07-05T08:06:05Z"},{"alias_kind":"pith_short_16","alias_value":"GHYYKOU3XMGQLTTW","created_at":"2026-07-05T08:06:05Z"},{"alias_kind":"pith_short_8","alias_value":"GHYYKOU3","created_at":"2026-07-05T08:06:05Z"}],"graph_snapshots":[{"event_id":"sha256:fb88da79d592b8f04ceb1688707b551383e7210745d944290489b9213c2dbc74","target":"graph","created_at":"2026-07-05T08:06:05Z","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/2404.06212/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Last year, multimodal architectures served up a revolution in AI-based approaches and solutions, extending the capabilities of large language models (LLM). We propose an \\textit{OmniFusion} model based on a pretrained LLM and adapters for visual modality. We evaluated and compared several architecture design principles for better text and visual data coupling: MLP and transformer adapters, various CLIP ViT-based encoders (SigLIP, InternVIT, etc.), and their fusing approach, image encoding method (whole image or tiles encoding) and two 7B LLMs (the proprietary one and open-source Mistral). Expe","authors_text":"Andrey Kuznetsov, Anton Razzhigaev, Denis Dimitrov, Elizaveta Goncharova, Irina Abdullaeva, Ivan Oseledets, Matvey Mikhalchuk, Matvey Skripkin, Maxim Kurkin","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-09T11:00:19Z","title":"OmniFusion Technical Report"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.06212","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":"sha256:03e4069df4426bb689137e9000cbc9a24f5863ecdf9e14ac68f874ce648dca56","target":"record","created_at":"2026-07-05T08:06:05Z","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":"e426540062eefb76a0b47f1b5f148243e43f28d0edc7303bd27aeac932077fc1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-09T11:00:19Z","title_canon_sha256":"4893efa0233a060e0eef6b1fb0eea42026e4fae404163d33e0ee9500eeaad1eb"},"schema_version":"1.0","source":{"id":"2404.06212","kind":"arxiv","version":1}},"canonical_sha256":"31f1853a9bbb0d05ce76f0040a1f21ae29128ded58b3f208967447f4caf15a40","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31f1853a9bbb0d05ce76f0040a1f21ae29128ded58b3f208967447f4caf15a40","first_computed_at":"2026-07-05T08:06:05.811933Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:06:05.811933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x6+/3wr6FPj6NIMcAdzyPZp3MfA4tobcRuP4vRxTcb2WmMXAWC6CCwBcmRwDeo8shkQDVmR7M7QgCagU1LYlCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:06:05.812404Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.06212","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03e4069df4426bb689137e9000cbc9a24f5863ecdf9e14ac68f874ce648dca56","sha256:fb88da79d592b8f04ceb1688707b551383e7210745d944290489b9213c2dbc74"],"state_sha256":"6e099b9448703df2593c01c488114db293272adff8a103cb6e7c02f2a944be8e"}