{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CY6V7C3CCNPJDSVTNQYXKQKKUN","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":"d72585bf496a64150aa391cf8202115276d3e0708f66d726d279088a16f6e9df","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-06T02:02:34Z","title_canon_sha256":"e91d55267b99a37ccf138a5e93ed5edf07e69b5bcb3df9d7c23963accb999703"},"schema_version":"1.0","source":{"id":"2401.03105","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.03105","created_at":"2026-07-05T07:33:25Z"},{"alias_kind":"arxiv_version","alias_value":"2401.03105v2","created_at":"2026-07-05T07:33:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.03105","created_at":"2026-07-05T07:33:25Z"},{"alias_kind":"pith_short_12","alias_value":"CY6V7C3CCNPJ","created_at":"2026-07-05T07:33:25Z"},{"alias_kind":"pith_short_16","alias_value":"CY6V7C3CCNPJDSVT","created_at":"2026-07-05T07:33:25Z"},{"alias_kind":"pith_short_8","alias_value":"CY6V7C3C","created_at":"2026-07-05T07:33:25Z"}],"graph_snapshots":[{"event_id":"sha256:7e2ebc6617e6561b6be819aa73c13b28bd8148cf07479711f1d0e0da58b4cbe4","target":"graph","created_at":"2026-07-05T07:33:25Z","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/2401.03105/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) are experiencing rapid growth, yielding a plethora of noteworthy contributions in recent months. The prevailing trend involves adopting data-driven methodologies, wherein diverse instruction-following datasets are collected. However, a prevailing challenge persists in these approaches, specifically in relation to the limited visual perception ability, as CLIP-like encoders employed for extracting visual information from inputs. Though these encoders are pre-trained on billions of image-text pairs, they still grapple with the information loss dilemma, gi","authors_text":"Lingxi Xie, Longhui Wei, Qi Tian, Xin He","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-06T02:02:34Z","title":"Incorporating Visual Experts to Resolve the Information Loss in Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.03105","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:d2ef35fb09812171b982b494a4c06c417641a2afa7a883a3011051815c7aa1c9","target":"record","created_at":"2026-07-05T07:33:25Z","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":"d72585bf496a64150aa391cf8202115276d3e0708f66d726d279088a16f6e9df","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-06T02:02:34Z","title_canon_sha256":"e91d55267b99a37ccf138a5e93ed5edf07e69b5bcb3df9d7c23963accb999703"},"schema_version":"1.0","source":{"id":"2401.03105","kind":"arxiv","version":2}},"canonical_sha256":"163d5f8b62135e91cab36c3175414aa34700c4d212ee7e6f52cc5a24cb3cbd73","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"163d5f8b62135e91cab36c3175414aa34700c4d212ee7e6f52cc5a24cb3cbd73","first_computed_at":"2026-07-05T07:33:25.456154Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:33:25.456154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"903BChijvHkhxYgLCQbqJY5wB7CYwA3/yLoJcUHFejrm4dghbhJZlK6KKpNc2/JotLB/xh7paR1pHZLTNZ15DA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:33:25.456657Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.03105","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2ef35fb09812171b982b494a4c06c417641a2afa7a883a3011051815c7aa1c9","sha256:7e2ebc6617e6561b6be819aa73c13b28bd8148cf07479711f1d0e0da58b4cbe4"],"state_sha256":"b0bf6e0981bd57a73aaeb5cf7f2e24f6b761dd14b666f3babad9eb03ef90fab6"}