{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WKP2IC7SI5DKRF7MFITCAKBSXZ","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":"1158020028430bfa009ef88169b50c1d65bf1a00a9131c7f4efdd94376567e36","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T10:04:22Z","title_canon_sha256":"9a65c3a510b56109537f04de7d0db762e3e1cce70bccd1f0f581a9485acc1d97"},"schema_version":"1.0","source":{"id":"2605.18160","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18160","created_at":"2026-05-20T00:05:48Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18160v1","created_at":"2026-05-20T00:05:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18160","created_at":"2026-05-20T00:05:48Z"},{"alias_kind":"pith_short_12","alias_value":"WKP2IC7SI5DK","created_at":"2026-05-20T00:05:48Z"},{"alias_kind":"pith_short_16","alias_value":"WKP2IC7SI5DKRF7M","created_at":"2026-05-20T00:05:48Z"},{"alias_kind":"pith_short_8","alias_value":"WKP2IC7S","created_at":"2026-05-20T00:05:48Z"}],"graph_snapshots":[{"event_id":"sha256:295e691ce558b3c62c754c304fc11bbb4ca659d9ff54ea606c1d3c2ad6434d23","target":"graph","created_at":"2026-05-20T00:05:48Z","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":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T23:41:59.073399Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:35.362506Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.18160/integrity.json","findings":[],"snapshot_sha256":"f658bd97f569116feb518ff42934a5cbd14f9c8f6ee9c64f728ffbe9bb3b5c40","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, multimodal large language models (MLLMs) have achieved remarkable progress, primarily attributed to effective paradigms for integrating visual and textual information. The dominant connector-based paradigm projects visual features into textual sequence, enabling unified multimodal alignment and reasoning within a generative architecture. However, our experiments reveal two key limitations: (1) Although visual information serves as the core evidential modality in MLLMs, it is treated on par with textual tokens, diminishing the unique contribution of the visual modality; (2) As ","authors_text":"Fei Wu, Kairong Han, Kun Kuang, Min Zhang, Xinpeng Dong, Xu Tan","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T10:04:22Z","title":"Vision Inference Former: Sustaining Visual Consistency in Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18160","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:c686b0ff761daeb0eddeb0ae7565f12f59f9d904969dd6847d3c885d3031b438","target":"record","created_at":"2026-05-20T00:05:48Z","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":"1158020028430bfa009ef88169b50c1d65bf1a00a9131c7f4efdd94376567e36","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T10:04:22Z","title_canon_sha256":"9a65c3a510b56109537f04de7d0db762e3e1cce70bccd1f0f581a9485acc1d97"},"schema_version":"1.0","source":{"id":"2605.18160","kind":"arxiv","version":1}},"canonical_sha256":"b29fa40bf24746a897ec2a26202832be47b3717917d367eab40efbd638ff0381","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b29fa40bf24746a897ec2a26202832be47b3717917d367eab40efbd638ff0381","first_computed_at":"2026-05-20T00:05:48.768026Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:05:48.768026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W7SoQyG9XbzRihxXs+edoPM9wDrolnC5s56ytQRjqCh8EwzeUWFxQ3SHCTqyxoUGbEHgTytXipz7tqD8y2vsBw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:05:48.768552Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18160","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c686b0ff761daeb0eddeb0ae7565f12f59f9d904969dd6847d3c885d3031b438","sha256:295e691ce558b3c62c754c304fc11bbb4ca659d9ff54ea606c1d3c2ad6434d23"],"state_sha256":"ad8b17689eefecb91fa00341e8f47303160ac10d6245af44866510caa1df6aa5"}