{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VPVNNLTIXDG4AODE62W32ZPOLO","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":"7acf155b8c3d7872c32fa9e4749c20a84d9fe799bfe950ad05c99680c2c1e0df","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-11T05:51:44Z","title_canon_sha256":"2812ba3994251deb769a5992cde8a3b459c9eb244bd5b115b17b0f837756cccd"},"schema_version":"1.0","source":{"id":"2504.08269","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.08269","created_at":"2026-07-05T10:47:46Z"},{"alias_kind":"arxiv_version","alias_value":"2504.08269v1","created_at":"2026-07-05T10:47:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.08269","created_at":"2026-07-05T10:47:46Z"},{"alias_kind":"pith_short_12","alias_value":"VPVNNLTIXDG4","created_at":"2026-07-05T10:47:46Z"},{"alias_kind":"pith_short_16","alias_value":"VPVNNLTIXDG4AODE","created_at":"2026-07-05T10:47:46Z"},{"alias_kind":"pith_short_8","alias_value":"VPVNNLTI","created_at":"2026-07-05T10:47:46Z"}],"graph_snapshots":[{"event_id":"sha256:58af5014a75a67f5dd25ebb25b424fd00f863b77d65def99269cfd8ef8ef8641","target":"graph","created_at":"2026-07-05T10:47:46Z","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/2504.08269/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The increasing availability of multimodal data across text, tables, and images presents new challenges for developing models capable of complex cross-modal reasoning. Existing methods for Multimodal Multi-hop Question Answering (MMQA) often suffer from limited reasoning capabilities, reliance on modality conversion, and inadequate alignment between visual and textual representations. To address these limitations, this paper introduces Vision-Language Multimodal Transformer (VLMT), a unified architecture that integrates a transformer-based vision encoder with a sequence-to-sequence language mod","authors_text":"Chin Poo Lee, Kalaiarasi Sonai Muthu Anbananthen, Kian Ming Lim, Qi Zhi Lim","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-11T05:51:44Z","title":"VLMT: Vision-Language Multimodal Transformer for Multimodal Multi-hop Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.08269","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":"sha256:1ee88b9af8efbce0155b3be27f6812ed35015a46d36170de306ad1073a34f5aa","target":"record","created_at":"2026-07-05T10:47:46Z","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":"7acf155b8c3d7872c32fa9e4749c20a84d9fe799bfe950ad05c99680c2c1e0df","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-11T05:51:44Z","title_canon_sha256":"2812ba3994251deb769a5992cde8a3b459c9eb244bd5b115b17b0f837756cccd"},"schema_version":"1.0","source":{"id":"2504.08269","kind":"arxiv","version":1}},"canonical_sha256":"abead6ae68b8cdc03864f6adbd65ee5ba683b5998b31568f663b3a40a8271bdd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"abead6ae68b8cdc03864f6adbd65ee5ba683b5998b31568f663b3a40a8271bdd","first_computed_at":"2026-07-05T10:47:46.198806Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:47:46.198806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/OyFG0/fgmrWwh8PRPD6m38oHUR/hfu6M0JSkIeKRILfGu4VJRNvcjb5vRZAdN9mT6GXCXoAox/+dCcoo0+KCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:47:46.199378Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.08269","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ee88b9af8efbce0155b3be27f6812ed35015a46d36170de306ad1073a34f5aa","sha256:58af5014a75a67f5dd25ebb25b424fd00f863b77d65def99269cfd8ef8ef8641"],"state_sha256":"65bf8a5d3ae1a859850c1a4ccefd017f3a7e819299ed411f8b82b3b1ccfa3633"}