{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:R6SZF4T4233WTC2Y6RQM7GRM4B","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":"91c5556d93f131f09b62e93d782f21728b53ff13cb435966011f0f5806907439","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-08T17:56:23Z","title_canon_sha256":"5e88e305f31820fe0a76fe5710db68352c5f0b110a3abb6440fc6bc2e99a1ee5"},"schema_version":"1.0","source":{"id":"2505.05464","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.05464","created_at":"2026-07-05T11:37:19Z"},{"alias_kind":"arxiv_version","alias_value":"2505.05464v2","created_at":"2026-07-05T11:37:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05464","created_at":"2026-07-05T11:37:19Z"},{"alias_kind":"pith_short_12","alias_value":"R6SZF4T4233W","created_at":"2026-07-05T11:37:19Z"},{"alias_kind":"pith_short_16","alias_value":"R6SZF4T4233WTC2Y","created_at":"2026-07-05T11:37:19Z"},{"alias_kind":"pith_short_8","alias_value":"R6SZF4T4","created_at":"2026-07-05T11:37:19Z"}],"graph_snapshots":[{"event_id":"sha256:a87222661f529381d9b0faa4f5512f11c19784bc310eab37acfcf5b0daa13717","target":"graph","created_at":"2026-07-05T11:37:19Z","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/2505.05464/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models (VLMs) combine visual perception with the general capabilities, such as reasoning, of Large Language Models (LLMs). However, the mechanisms by which these two abilities can be combined and contribute remain poorly understood. In this work, we explore to compose perception and reasoning through model merging that connects parameters of different models. Unlike previous works that often focus on merging models of the same kind, we propose merging models across modalities, enabling the incorporation of the reasoning capabilities of LLMs into VLMs. Through extensive experime","authors_text":"Jinghan Zhang, Junxian He, Manling Li, Miao Xiong, Shiqi Chen, Siyang Gao, Tongyao Zhu, Wei Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-08T17:56:23Z","title":"Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05464","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:bd4be286a7eadc5013a30ce803380a74498f986ac15ef4c5735b624a6ab35e4e","target":"record","created_at":"2026-07-05T11:37:19Z","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":"91c5556d93f131f09b62e93d782f21728b53ff13cb435966011f0f5806907439","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-08T17:56:23Z","title_canon_sha256":"5e88e305f31820fe0a76fe5710db68352c5f0b110a3abb6440fc6bc2e99a1ee5"},"schema_version":"1.0","source":{"id":"2505.05464","kind":"arxiv","version":2}},"canonical_sha256":"8fa592f27cd6f7698b58f460cf9a2ce04428f3815c70d2dec10cc70857b53f0d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8fa592f27cd6f7698b58f460cf9a2ce04428f3815c70d2dec10cc70857b53f0d","first_computed_at":"2026-07-05T11:37:19.757749Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:37:19.757749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/HCS9T7Ua4W4dX3Z7QAhMyA9Ro9iyuBN9mgUPXManbP3KfBfoqdAkEabPl/Sur3uLtjN1QM4Sus4SNIsa92YCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:37:19.758245Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.05464","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd4be286a7eadc5013a30ce803380a74498f986ac15ef4c5735b624a6ab35e4e","sha256:a87222661f529381d9b0faa4f5512f11c19784bc310eab37acfcf5b0daa13717"],"state_sha256":"8058532c8df4397530ff559c166d6aaadf1f4da844433e1ead119b9f5395d862"}