{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:H67FM4VT4P37MQEWLUAIWGKGVK","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":"085dc31e2275f8e17195b3547903eb72067555a04da2c4e311f8e1382614d257","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T13:58:21Z","title_canon_sha256":"8933109e6e5c4211175a048b0012c51e0efe88f6d5f609d441135777328cd286"},"schema_version":"1.0","source":{"id":"2507.00754","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00754","created_at":"2026-07-05T11:34:10Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00754v2","created_at":"2026-07-05T11:34:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00754","created_at":"2026-07-05T11:34:10Z"},{"alias_kind":"pith_short_12","alias_value":"H67FM4VT4P37","created_at":"2026-07-05T11:34:10Z"},{"alias_kind":"pith_short_16","alias_value":"H67FM4VT4P37MQEW","created_at":"2026-07-05T11:34:10Z"},{"alias_kind":"pith_short_8","alias_value":"H67FM4VT","created_at":"2026-07-05T11:34:10Z"}],"graph_snapshots":[{"event_id":"sha256:4d75acd15ed651a912afd6e9708c1239e9b2a8da3a3f20714873d0b389c9f014","target":"graph","created_at":"2026-07-05T11:34:10Z","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/2507.00754/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The integration of Large Language Model (LLMs) blocks with Vision Transformers (ViTs) holds immense promise for vision-only tasks by leveraging the rich semantic knowledge and reasoning capabilities of LLMs. However, a fundamental challenge lies in the inherent modality mismatch between text-centric pretraining of LLMs and vision-centric training of ViTs. Direct fusion often fails to fully exploit the LLM's potential and suffers from unstable finetuning. As a result, LLM blocks are kept frozen while only the vision components are learned. As a remedy to these challenges, we introduce Language-","authors_text":"Anna Kukleva, Bernt Schiele, Federico Tombari, Muhammad Ferjad Naeem, Selim Kuzucu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T13:58:21Z","title":"Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00754","kind":"arxiv","version":2},"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":"sha256:2fcea8fd1b4117e9e8c38e936013928a0e849b83ff51dd0ee2125210200ddf06","target":"record","created_at":"2026-07-05T11:34:10Z","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":"085dc31e2275f8e17195b3547903eb72067555a04da2c4e311f8e1382614d257","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T13:58:21Z","title_canon_sha256":"8933109e6e5c4211175a048b0012c51e0efe88f6d5f609d441135777328cd286"},"schema_version":"1.0","source":{"id":"2507.00754","kind":"arxiv","version":2}},"canonical_sha256":"3fbe5672b3e3f7f640965d008b1946aab8e721f79fe65cfae00a54405bcf670b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3fbe5672b3e3f7f640965d008b1946aab8e721f79fe65cfae00a54405bcf670b","first_computed_at":"2026-07-05T11:34:10.464002Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:10.464002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Cc7M3XLJ4H7Xb5GBlXA1HKmvFFwydJ5vsqgRtYUKkBgTJs7ht/4k8Wg1mZr6bXhq802o2q+G+Z4d/QUK+otSAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:10.464441Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.00754","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2fcea8fd1b4117e9e8c38e936013928a0e849b83ff51dd0ee2125210200ddf06","sha256:4d75acd15ed651a912afd6e9708c1239e9b2a8da3a3f20714873d0b389c9f014"],"state_sha256":"b72cfb463440a646198ed72dc7982aa21e0a2238cd26939d626b03a93fc1fd88"}