{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IV2T2ZXTTIPF774J2EEQIENUOY","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":"6bb5be786cfcac1623d15ee296612f93f338af9a8550a9830c96b53baf619573","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-26T14:10:00Z","title_canon_sha256":"28593c8aa66bd582f071f16d01aa1770955602c96958bb4f075a1da5cff19154"},"schema_version":"1.0","source":{"id":"2407.09541","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.09541","created_at":"2026-07-05T08:43:32Z"},{"alias_kind":"arxiv_version","alias_value":"2407.09541v1","created_at":"2026-07-05T08:43:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.09541","created_at":"2026-07-05T08:43:32Z"},{"alias_kind":"pith_short_12","alias_value":"IV2T2ZXTTIPF","created_at":"2026-07-05T08:43:32Z"},{"alias_kind":"pith_short_16","alias_value":"IV2T2ZXTTIPF774J","created_at":"2026-07-05T08:43:32Z"},{"alias_kind":"pith_short_8","alias_value":"IV2T2ZXT","created_at":"2026-07-05T08:43:32Z"}],"graph_snapshots":[{"event_id":"sha256:eaba009f390bfc884b86cc2015cf24ee1daf8a0be53b29c37418b8ba47d04286","target":"graph","created_at":"2026-07-05T08:43:32Z","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/2407.09541/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While advancements in Vision Language Models (VLMs) have significantly improved the alignment of visual and textual data, these models primarily focus on aligning images with short descriptive captions. This focus limits their ability to handle complex text interactions, particularly with longer texts such as lengthy captions or documents, which have not been extensively explored yet. In this paper, we introduce Meet At The Embedding (MATE), a novel approach that combines the capabilities of VLMs with Large Language Models (LLMs) to overcome this challenge without the need for additional image","authors_text":"Donghyun Kim, Junmo Kang, Yong Jae Lee, Young Kyun Jang","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-26T14:10:00Z","title":"MATE: Meet At The Embedding -- Connecting Images with Long Texts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.09541","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:fa71b4c45c9fcd6f8fd472352d783666ff833d8d43cba05e4b15131f3ed93ce7","target":"record","created_at":"2026-07-05T08:43:32Z","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":"6bb5be786cfcac1623d15ee296612f93f338af9a8550a9830c96b53baf619573","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-26T14:10:00Z","title_canon_sha256":"28593c8aa66bd582f071f16d01aa1770955602c96958bb4f075a1da5cff19154"},"schema_version":"1.0","source":{"id":"2407.09541","kind":"arxiv","version":1}},"canonical_sha256":"45753d66f39a1e5fff89d1090411b476022b9b98ee98e96ba8f90e93d14db7a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45753d66f39a1e5fff89d1090411b476022b9b98ee98e96ba8f90e93d14db7a3","first_computed_at":"2026-07-05T08:43:32.046972Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:43:32.046972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T1eswM21u3iOdSVYcWtZBt0tCfzcvoncXziMSu3Oau8fK+NXjcukoMSvjnUkuMurtGa4aOpQF7VaxA+jMS26Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T08:43:32.047396Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.09541","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fa71b4c45c9fcd6f8fd472352d783666ff833d8d43cba05e4b15131f3ed93ce7","sha256:eaba009f390bfc884b86cc2015cf24ee1daf8a0be53b29c37418b8ba47d04286"],"state_sha256":"0b21ed99a3e5949c8591667df2c72cdbcc5d4a130794f5cbef7afe5bc6808840"}