{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JXIT3OYHDJ4QLGHWP2MPIRJQJ2","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":"1ba1504ef6bdb861c8b995fbf0b7c0bd6e5ca852565ad90dcdad3513c27cf7aa","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-14T02:29:36Z","title_canon_sha256":"b95da4e1e5243d04470b98ecd819b23061795533152606605de7f2d07b35dc8f"},"schema_version":"1.0","source":{"id":"2409.09269","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.09269","created_at":"2026-07-05T09:47:56Z"},{"alias_kind":"arxiv_version","alias_value":"2409.09269v3","created_at":"2026-07-05T09:47:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09269","created_at":"2026-07-05T09:47:56Z"},{"alias_kind":"pith_short_12","alias_value":"JXIT3OYHDJ4Q","created_at":"2026-07-05T09:47:56Z"},{"alias_kind":"pith_short_16","alias_value":"JXIT3OYHDJ4QLGHW","created_at":"2026-07-05T09:47:56Z"},{"alias_kind":"pith_short_8","alias_value":"JXIT3OYH","created_at":"2026-07-05T09:47:56Z"}],"graph_snapshots":[{"event_id":"sha256:293d0a7ad583e0b097eaa3ea7ed6e19f5d44e15acab00f11585f0c4ae7dcb215","target":"graph","created_at":"2026-07-05T09:47:56Z","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/2409.09269/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual Question-Answering (VQA) has become key to user experience, particularly after improved generalization capabilities of Vision-Language Models (VLMs). But evaluating VLMs for an application requirement using a standardized framework in practical settings is still challenging. This paper aims to solve that using an end-to-end framework. We present VQA360 - a novel dataset derived from established VQA benchmarks, annotated with task types, application domains, and knowledge types, for a comprehensive evaluation. We also introduce GoEval, a multimodal evaluation metric developed using GPT-4","authors_text":"Aman Chadha, Neelabh Sinha, Vinija Jain","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-14T02:29:36Z","title":"Guiding Vision-Language Model Selection for Visual Question-Answering Across Tasks, Domains, and Knowledge Types"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09269","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":"sha256:3e3618f45b820c6f4442390075feab1b472d1ae62785490c95462d623dfb43ad","target":"record","created_at":"2026-07-05T09:47:56Z","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":"1ba1504ef6bdb861c8b995fbf0b7c0bd6e5ca852565ad90dcdad3513c27cf7aa","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-14T02:29:36Z","title_canon_sha256":"b95da4e1e5243d04470b98ecd819b23061795533152606605de7f2d07b35dc8f"},"schema_version":"1.0","source":{"id":"2409.09269","kind":"arxiv","version":3}},"canonical_sha256":"4dd13dbb071a790598f67e98f445304e973e2490b2140574f0d8c3ec1371eb2b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4dd13dbb071a790598f67e98f445304e973e2490b2140574f0d8c3ec1371eb2b","first_computed_at":"2026-07-05T09:47:56.397066Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:47:56.397066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vwpqMs0ue9snWAAUOvs0+uaYen3j/jvASIHlDU624fW1p3Yx6+29+s1jRPINBr8wT2uyuiEuiSynGv02C8VzBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:47:56.397882Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.09269","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e3618f45b820c6f4442390075feab1b472d1ae62785490c95462d623dfb43ad","sha256:293d0a7ad583e0b097eaa3ea7ed6e19f5d44e15acab00f11585f0c4ae7dcb215"],"state_sha256":"4245b94f506bebc7621c44cdcff8c9bb164b3601c8cd90f54f479e22b0eb1a1b"}