{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MNDJGFLDQNF7TVCBJ2YK473SDP","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":"503c5caf82a23cadef5168e4e0014f63f10344188f09af4b08bcef0d7ac10ac7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-13T17:34:05Z","title_canon_sha256":"861f5f0e4c1d1309bd00efca3b68b99792902a50138c20f0bb74566a276ea1dd"},"schema_version":"1.0","source":{"id":"2506.11976","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11976","created_at":"2026-07-05T11:25:12Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11976v2","created_at":"2026-07-05T11:25:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11976","created_at":"2026-07-05T11:25:12Z"},{"alias_kind":"pith_short_12","alias_value":"MNDJGFLDQNF7","created_at":"2026-07-05T11:25:12Z"},{"alias_kind":"pith_short_16","alias_value":"MNDJGFLDQNF7TVCB","created_at":"2026-07-05T11:25:12Z"},{"alias_kind":"pith_short_8","alias_value":"MNDJGFLD","created_at":"2026-07-05T11:25:12Z"}],"graph_snapshots":[{"event_id":"sha256:cff38136367d7e22db1477ffb2a13e098694bddac66337d6467f1f6f90ea8bd9","target":"graph","created_at":"2026-07-05T11:25:12Z","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/2506.11976/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Effective multimodal reasoning depends on the alignment of visual and linguistic representations, yet the mechanisms by which vision-language models (VLMs) achieve this alignment remain poorly understood. Following the LiMBeR framework, we deliberately maintain a frozen large language model (LLM) and a frozen vision transformer (ViT), connected solely by training a linear adapter during visual instruction tuning. By keeping the language model frozen, we ensure it maintains its original language representations without adaptation to visual data. Consequently, the linear adapter must map visual ","authors_text":"Ashkan Khakzar, Constantin Venhoff, Neel Nanda, Philip Torr, Sonia Joseph","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-13T17:34:05Z","title":"How Visual Representations Map to Language Feature Space in Multimodal LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11976","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:f84d7d5a27a7704c4a4cf1351a614c8960add34102db389cd86de0371c38fb6f","target":"record","created_at":"2026-07-05T11:25:12Z","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":"503c5caf82a23cadef5168e4e0014f63f10344188f09af4b08bcef0d7ac10ac7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-13T17:34:05Z","title_canon_sha256":"861f5f0e4c1d1309bd00efca3b68b99792902a50138c20f0bb74566a276ea1dd"},"schema_version":"1.0","source":{"id":"2506.11976","kind":"arxiv","version":2}},"canonical_sha256":"6346931563834bf9d4414eb0ae7f721bec71b467a98794c3121691121b358ec8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6346931563834bf9d4414eb0ae7f721bec71b467a98794c3121691121b358ec8","first_computed_at":"2026-07-05T11:25:12.538430Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:12.538430Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/lLj/fCGXMAERERMY6Cn2l8/noGLwgbnc1cqsqAyGNn32DIcFeY7jUso4ZJrLpfgeU5WN2hbU4YDA7EMC3ZtAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:12.538982Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.11976","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f84d7d5a27a7704c4a4cf1351a614c8960add34102db389cd86de0371c38fb6f","sha256:cff38136367d7e22db1477ffb2a13e098694bddac66337d6467f1f6f90ea8bd9"],"state_sha256":"ba2ac6fa23f527897504ea1f2d0bbee7240cd92ab81e5a86a62a4ea1e5e595db"}