{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PGCMJT5FP2XNOLOWBEJJYFGNZB","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":"49503e360c4046ec8856a8b9298e199f70ba0015a7e875dea401b9b0ffb6f143","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-13T10:40:53Z","title_canon_sha256":"2131df975fed7747c78d166cfa8783a744014d8285d70168c7f5a8e7c3f94727"},"schema_version":"1.0","source":{"id":"2402.08360","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.08360","created_at":"2026-07-05T07:44:31Z"},{"alias_kind":"arxiv_version","alias_value":"2402.08360v1","created_at":"2026-07-05T07:44:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08360","created_at":"2026-07-05T07:44:31Z"},{"alias_kind":"pith_short_12","alias_value":"PGCMJT5FP2XN","created_at":"2026-07-05T07:44:31Z"},{"alias_kind":"pith_short_16","alias_value":"PGCMJT5FP2XNOLOW","created_at":"2026-07-05T07:44:31Z"},{"alias_kind":"pith_short_8","alias_value":"PGCMJT5F","created_at":"2026-07-05T07:44:31Z"}],"graph_snapshots":[{"event_id":"sha256:79207bd61f6f4b1ccc858e2b971e32594df624e8b1b57f8b0382e93b24fad0f4","target":"graph","created_at":"2026-07-05T07:44:31Z","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/2402.08360/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Having revolutionized natural language processing (NLP) applications, large language models (LLMs) are expanding into the realm of multimodal inputs. Owing to their ability to interpret images, multimodal LLMs (MLLMs) have been primarily used for vision-language tasks. Currently, MLLMs have not yet been extended for domain-specific visual tasks, which require a more explicit understanding of visual information. We developed a method to transform domain-specific visual and vision-language datasets into a unified question answering format called Visual Question Answering Instruction (VQA-IN), th","authors_text":"Cheoljong Yang, Jusung Lee, Sungguk Cha, Younghyun Lee","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-13T10:40:53Z","title":"Visual Question Answering Instruction: Unlocking Multimodal Large Language Model To Domain-Specific Visual Multitasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08360","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":"sha256:4fd3bb2f4504f70ac19a75470988969720b45483a8791d7ebf73ae030997f39b","target":"record","created_at":"2026-07-05T07:44:31Z","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":"49503e360c4046ec8856a8b9298e199f70ba0015a7e875dea401b9b0ffb6f143","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-13T10:40:53Z","title_canon_sha256":"2131df975fed7747c78d166cfa8783a744014d8285d70168c7f5a8e7c3f94727"},"schema_version":"1.0","source":{"id":"2402.08360","kind":"arxiv","version":1}},"canonical_sha256":"7984c4cfa57eaed72dd609129c14cdc867ca6198e8490c87406247208bfe2e3e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7984c4cfa57eaed72dd609129c14cdc867ca6198e8490c87406247208bfe2e3e","first_computed_at":"2026-07-05T07:44:31.424432Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:44:31.424432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Go9qN6LoHsulDDM6xG2G4rdJaFHBgrgpxsPet2KckhG90ehpQ/H+OTjRuDVNgIJ+JuHDOjvwVFTozCcf1zW1CA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:44:31.424807Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.08360","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fd3bb2f4504f70ac19a75470988969720b45483a8791d7ebf73ae030997f39b","sha256:79207bd61f6f4b1ccc858e2b971e32594df624e8b1b57f8b0382e93b24fad0f4"],"state_sha256":"96d1e59bf735e80bde9ecbe9f2371af2f756d33bb8ae6918b97e1212fecda6d2"}