{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7W5KWKU2VGQVKAO3IE5Q5ZY4SC","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":"a3758f7458822f2740186c6fc3f8752c298218980d32ceaf177d212d6c2f8201","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-14T11:44:52Z","title_canon_sha256":"52fb752c4cb3f56f21cfa83f5345ce4bb8b05ef3f460053a12c4217c7563fb27"},"schema_version":"1.0","source":{"id":"2508.10552","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.10552","created_at":"2026-07-05T11:53:58Z"},{"alias_kind":"arxiv_version","alias_value":"2508.10552v1","created_at":"2026-07-05T11:53:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10552","created_at":"2026-07-05T11:53:58Z"},{"alias_kind":"pith_short_12","alias_value":"7W5KWKU2VGQV","created_at":"2026-07-05T11:53:58Z"},{"alias_kind":"pith_short_16","alias_value":"7W5KWKU2VGQVKAO3","created_at":"2026-07-05T11:53:58Z"},{"alias_kind":"pith_short_8","alias_value":"7W5KWKU2","created_at":"2026-07-05T11:53:58Z"}],"graph_snapshots":[{"event_id":"sha256:4f025d8324338db07cb78e7252ae326775b0835ee0ffea0ede8c06b16dc77318","target":"graph","created_at":"2026-07-05T11:53:58Z","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/2508.10552/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 remarkable capabilities across a diverse range of multimodal tasks. However, these models suffer from a core problem known as text dominance: they depend heavily on text for their inference, while underutilizing other modalities. While prior work has acknowledged this phenomenon in vision-language tasks, often attributing it to data biases or model architectures. In this paper, we conduct the first systematic investigation of text dominance across diverse data modalities, including images, videos, audio, time-series, and graphs. To mea","authors_text":"Haiyun Jiang, Huyu Wu, Meng Tang, Xinhan Zheng","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-14T11:44:52Z","title":"When Language Overrules: Revealing Text Dominance in Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.10552","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":"sha256:93db101b1f8c5d584fa32bf7d47e83d146c2e6f36799675aa7897823a004ad12","target":"record","created_at":"2026-07-05T11:53:58Z","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":"a3758f7458822f2740186c6fc3f8752c298218980d32ceaf177d212d6c2f8201","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-14T11:44:52Z","title_canon_sha256":"52fb752c4cb3f56f21cfa83f5345ce4bb8b05ef3f460053a12c4217c7563fb27"},"schema_version":"1.0","source":{"id":"2508.10552","kind":"arxiv","version":1}},"canonical_sha256":"fdbaab2a9aa9a15501db413b0ee71c90ac6e964a1ed526425d30b1ea5cb1a23d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fdbaab2a9aa9a15501db413b0ee71c90ac6e964a1ed526425d30b1ea5cb1a23d","first_computed_at":"2026-07-05T11:53:58.148964Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:53:58.148964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Sxacnhgpgor/5r5p8QckCiXF3A30/22dnJttO0YHWPzir8dEuxfXvyE9q3Huyi2RkkBpgkhfWHfSGzRRCaW7DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:53:58.149387Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.10552","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:93db101b1f8c5d584fa32bf7d47e83d146c2e6f36799675aa7897823a004ad12","sha256:4f025d8324338db07cb78e7252ae326775b0835ee0ffea0ede8c06b16dc77318"],"state_sha256":"630253220288c8450169e0f1498198e1a0af7b1b97a7b0702e48a8579c107ad0"}