{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WGUX6YAQTO2453NU3QDVF4RCQS","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":"c8490fa1a7c9243088f552526f13aab0c6c2befaab7f7236a53c64dade63d977","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-03T16:39:36Z","title_canon_sha256":"d54d2665c9ff8d22d882761c9ad30ab6c1a45099cbec5ccadb6c17554b1aa842"},"schema_version":"1.0","source":{"id":"2312.02219","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.02219","created_at":"2026-07-05T11:12:16Z"},{"alias_kind":"arxiv_version","alias_value":"2312.02219v3","created_at":"2026-07-05T11:12:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.02219","created_at":"2026-07-05T11:12:16Z"},{"alias_kind":"pith_short_12","alias_value":"WGUX6YAQTO24","created_at":"2026-07-05T11:12:16Z"},{"alias_kind":"pith_short_16","alias_value":"WGUX6YAQTO2453NU","created_at":"2026-07-05T11:12:16Z"},{"alias_kind":"pith_short_8","alias_value":"WGUX6YAQ","created_at":"2026-07-05T11:12:16Z"}],"graph_snapshots":[{"event_id":"sha256:81013c0eb733cc7f84f87f240784ead55908abbad17a8eb1653aaa7fe84b8c82","target":"graph","created_at":"2026-07-05T11:12:16Z","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/2312.02219/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Vision and Language Models have enabled significant advances in fully supervised and zero-shot visual tasks. These large architectures serve as the baseline to what is currently known as Instruction Tuning Large Vision and Language models (IT-LVLMs). IT-LVLMs are general-purpose multi-modal assistants whose responses are modulated by natural language instructions and visual data. Despite this versatility, IT-LVLM effectiveness in fundamental computer vision problems remains unclear, primarily due to the absence of a standardized evaluation benchmark. This paper introduces a Multi-modal E","authors_text":"Alvaro Soto, Andr\\'es Villa, Bernard Ghanem, Juan Carlos Le\\'on Alc\\'azar","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-03T16:39:36Z","title":"Behind the Magic, MERLIM: Multi-modal Evaluation Benchmark for Large Image-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.02219","kind":"arxiv","version":3},"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":"sha256:89d0cf0b9eadc13c4546af6d018c155ac34b5894bd0ff436e6a96284b573aaf6","target":"record","created_at":"2026-07-05T11:12:16Z","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":"c8490fa1a7c9243088f552526f13aab0c6c2befaab7f7236a53c64dade63d977","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-03T16:39:36Z","title_canon_sha256":"d54d2665c9ff8d22d882761c9ad30ab6c1a45099cbec5ccadb6c17554b1aa842"},"schema_version":"1.0","source":{"id":"2312.02219","kind":"arxiv","version":3}},"canonical_sha256":"b1a97f60109bb5ceedb4dc0752f22284881dae4a4e8fafada8d02fa45abe0455","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1a97f60109bb5ceedb4dc0752f22284881dae4a4e8fafada8d02fa45abe0455","first_computed_at":"2026-07-05T11:12:16.179331Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:16.179331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LPkr1uszE+Z3ZtyvGgtjOOt9yhbrZjVnjR+LIXlpR/GgU80z6Brqoy6hQbJsRNuqEnaTxGs5FJpPKp69tOr5Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:16.179847Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.02219","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:89d0cf0b9eadc13c4546af6d018c155ac34b5894bd0ff436e6a96284b573aaf6","sha256:81013c0eb733cc7f84f87f240784ead55908abbad17a8eb1653aaa7fe84b8c82"],"state_sha256":"a37777a646371e11e8b1072d0ad12cd5b11931082f73a73413949fc2d85568fe"}