{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XQMNBUGI5UAXOD2UL3ABKYDLOS","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":"d4cd4622a64dfde23702b18c607221f6b07e54ec66f6174846c8508d8ec4b220","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-19T07:16:18Z","title_canon_sha256":"bfe72401d30daf93931042f5245664081269235243f26f1116d225793257720c"},"schema_version":"1.0","source":{"id":"2506.21600","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.21600","created_at":"2026-07-05T11:27:57Z"},{"alias_kind":"arxiv_version","alias_value":"2506.21600v1","created_at":"2026-07-05T11:27:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21600","created_at":"2026-07-05T11:27:57Z"},{"alias_kind":"pith_short_12","alias_value":"XQMNBUGI5UAX","created_at":"2026-07-05T11:27:57Z"},{"alias_kind":"pith_short_16","alias_value":"XQMNBUGI5UAXOD2U","created_at":"2026-07-05T11:27:57Z"},{"alias_kind":"pith_short_8","alias_value":"XQMNBUGI","created_at":"2026-07-05T11:27:57Z"}],"graph_snapshots":[{"event_id":"sha256:9aec8947d66c111ae2b86a5fc7c87748539c5b70def96f7180e6d7d4c5a2a65e","target":"graph","created_at":"2026-07-05T11:27:57Z","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/2506.21600/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Document understanding remains a significant challenge for multimodal large language models (MLLMs). While previous research has primarily focused on locating evidence pages through precise multimodal queries, our work investigates a fundamental yet overlooked aspect: how input format influences document comprehension performance. Through systematic analysis, we discover that raw OCR text often impairs rather than improves MLLMs' performance, which is a counterintuitive finding we attribute to attention dispersion and structure loss. To further substantiate our hypothesis, we propose a novel s","authors_text":"Chang Liu, Hang Wu, Hongkai Chen, Ming-Hsuan Yang, Qingwen Ye, Yiwei Wang, Yujun Cai","cross_cats":["cs.AI","cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-19T07:16:18Z","title":"Structured Attention Matters to Multimodal LLMs in Document Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21600","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:d246dc94556ceb99a0314bcd980b32810e9d216dc96a80400a3cb7f5e11de468","target":"record","created_at":"2026-07-05T11:27:57Z","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":"d4cd4622a64dfde23702b18c607221f6b07e54ec66f6174846c8508d8ec4b220","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-19T07:16:18Z","title_canon_sha256":"bfe72401d30daf93931042f5245664081269235243f26f1116d225793257720c"},"schema_version":"1.0","source":{"id":"2506.21600","kind":"arxiv","version":1}},"canonical_sha256":"bc18d0d0c8ed01770f545ec015606b74982de6bd87ad93611b7baee3c7fb5bf1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc18d0d0c8ed01770f545ec015606b74982de6bd87ad93611b7baee3c7fb5bf1","first_computed_at":"2026-07-05T11:27:57.052512Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:27:57.052512Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/tfSI/mIUhMo5YcW2nLaoediqQqAU4eH2JYu/IAfjPIgqugV7kZehlaHbF7H+MmoAst9p0E1BYvQv+yTJcWWCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:27:57.052952Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.21600","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d246dc94556ceb99a0314bcd980b32810e9d216dc96a80400a3cb7f5e11de468","sha256:9aec8947d66c111ae2b86a5fc7c87748539c5b70def96f7180e6d7d4c5a2a65e"],"state_sha256":"df5691d5e66ca0e07e5846ebb6f52bb6b130444f606403fb191f3dc7bbddbcde"}