{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OEZYPUPOB77FHRKWHAQWSRJTYG","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":"92cfe49cff894f46726a44b20caee67c4cdd2ff63056896d4adc42873a2199a2","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-13T03:13:44Z","title_canon_sha256":"901f951dff1ad0b0d450c90c4dfd146bd207dcb9c70d5e7ecf9fe46be291d46e"},"schema_version":"1.0","source":{"id":"2412.09817","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.09817","created_at":"2026-07-05T09:48:41Z"},{"alias_kind":"arxiv_version","alias_value":"2412.09817v1","created_at":"2026-07-05T09:48:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09817","created_at":"2026-07-05T09:48:41Z"},{"alias_kind":"pith_short_12","alias_value":"OEZYPUPOB77F","created_at":"2026-07-05T09:48:41Z"},{"alias_kind":"pith_short_16","alias_value":"OEZYPUPOB77FHRKW","created_at":"2026-07-05T09:48:41Z"},{"alias_kind":"pith_short_8","alias_value":"OEZYPUPO","created_at":"2026-07-05T09:48:41Z"}],"graph_snapshots":[{"event_id":"sha256:b7ee1ed05a28f5fbde4da1186272280f2c4ca2abbc7f1148e20b5155cb243823","target":"graph","created_at":"2026-07-05T09:48:41Z","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/2412.09817/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models have experienced rapid growth, and numerous different models have emerged. The interpretability of LVLMs remains an under-explored area. Especially when faced with more complex tasks such as chain-of-thought reasoning, its internal mechanisms still resemble a black box that is difficult to decipher. By studying the interaction and information flow between images and text, we noticed that in models such as LLaVA1.5, image tokens that are semantically related to text are more likely to have information flow convergence in the LLM decoding layer, and these image t","authors_text":"Fanshuo Zeng, Jiawei Yao, Xiaofeng Zhang, Yihao Quan, Zheng Hui","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-13T03:13:44Z","title":"Enhancing Multimodal Large Language Models Complex Reason via Similarity Computation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09817","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:c2ca3c292b91eeef87a11921f371b525fea90b6b491b3ee65e69a0fa080afe4c","target":"record","created_at":"2026-07-05T09:48:41Z","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":"92cfe49cff894f46726a44b20caee67c4cdd2ff63056896d4adc42873a2199a2","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-13T03:13:44Z","title_canon_sha256":"901f951dff1ad0b0d450c90c4dfd146bd207dcb9c70d5e7ecf9fe46be291d46e"},"schema_version":"1.0","source":{"id":"2412.09817","kind":"arxiv","version":1}},"canonical_sha256":"713387d1ee0ffe53c5563821694533c1a24965f5c89b865bbff4b056c1a97441","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"713387d1ee0ffe53c5563821694533c1a24965f5c89b865bbff4b056c1a97441","first_computed_at":"2026-07-05T09:48:41.999626Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:48:41.999626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g1uncEDWxt+S2oNXxUnnG1TwUJz7e5q6kA4ibviKj4K7eEq8D1UOSET5g22xiwzdVHZTGtP7PcG3z8oxEN5hCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:48:42.000013Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.09817","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2ca3c292b91eeef87a11921f371b525fea90b6b491b3ee65e69a0fa080afe4c","sha256:b7ee1ed05a28f5fbde4da1186272280f2c4ca2abbc7f1148e20b5155cb243823"],"state_sha256":"4e2ed98be21d7eb573e0cdf7e33b6340c36b4c8787a01ea3b88f16e872b60d34"}