{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KK4FGJ3IIGDYUTD47K3AGRDZXR","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":"8204e0a2935430c7e2f3b6030a9833c7108180a6f5bdd23b7d20692aea59f265","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-27T21:22:01Z","title_canon_sha256":"002023e19f810158d6944db945b8f6ac8d82143619fef49e164eff2b3941a138"},"schema_version":"1.0","source":{"id":"2508.20279","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.20279","created_at":"2026-07-05T12:00:33Z"},{"alias_kind":"arxiv_version","alias_value":"2508.20279v1","created_at":"2026-07-05T12:00:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20279","created_at":"2026-07-05T12:00:33Z"},{"alias_kind":"pith_short_12","alias_value":"KK4FGJ3IIGDY","created_at":"2026-07-05T12:00:33Z"},{"alias_kind":"pith_short_16","alias_value":"KK4FGJ3IIGDYUTD4","created_at":"2026-07-05T12:00:33Z"},{"alias_kind":"pith_short_8","alias_value":"KK4FGJ3I","created_at":"2026-07-05T12:00:33Z"}],"graph_snapshots":[{"event_id":"sha256:860bfa6690bc0da75126d9428aa443105fd3d225d5323cdf42872aa2a6f5e08a","target":"graph","created_at":"2026-07-05T12:00:33Z","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/2508.20279/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) have demonstrated strong performance across a wide range of vision-language tasks, yet their internal processing dynamics remain underexplored. In this work, we introduce a probing framework to systematically analyze how MLLMs process visual and textual inputs across layers. We train linear classifiers to predict fine-grained visual categories (e.g., dog breeds) from token embeddings extracted at each layer, using a standardized anchor question. To uncover the functional roles of different layers, we evaluate these probes under three types of controlled","authors_text":"Yong Jae Lee, Zhuoran Yu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-27T21:22:01Z","title":"How Multimodal LLMs Solve Image Tasks: A Lens on Visual Grounding, Task Reasoning, and Answer Decoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.20279","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:b2e8a81b2f4535179024aef45d8028fc61bee7e6280ff8cd62a7772df15310d6","target":"record","created_at":"2026-07-05T12:00:33Z","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":"8204e0a2935430c7e2f3b6030a9833c7108180a6f5bdd23b7d20692aea59f265","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-27T21:22:01Z","title_canon_sha256":"002023e19f810158d6944db945b8f6ac8d82143619fef49e164eff2b3941a138"},"schema_version":"1.0","source":{"id":"2508.20279","kind":"arxiv","version":1}},"canonical_sha256":"52b853276841878a4c7cfab6034479bc6dccfe844f53838ea7fae36bf554917e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"52b853276841878a4c7cfab6034479bc6dccfe844f53838ea7fae36bf554917e","first_computed_at":"2026-07-05T12:00:33.471300Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:00:33.471300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h7eISUHcWl8e5b9YZkWdRsfpvLBkdBkxq16CcZDy7HW9lUOK5dmsToAb7W8dII/IYdW7m+I/j8daHSoV6DkODA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:00:33.471806Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.20279","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2e8a81b2f4535179024aef45d8028fc61bee7e6280ff8cd62a7772df15310d6","sha256:860bfa6690bc0da75126d9428aa443105fd3d225d5323cdf42872aa2a6f5e08a"],"state_sha256":"64072c07447516c8b5ad4ec002300499ab186b487a1cb3eee3f665a27c79afa2"}