{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JXIT3OYHDJ4QLGHWP2MPIRJQJ2","short_pith_number":"pith:JXIT3OYH","schema_version":"1.0","canonical_sha256":"4dd13dbb071a790598f67e98f445304e973e2490b2140574f0d8c3ec1371eb2b","source":{"kind":"arxiv","id":"2409.09269","version":3},"attestation_state":"computed","paper":{"title":"Guiding Vision-Language Model Selection for Visual Question-Answering Across Tasks, Domains, and Knowledge Types","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Aman Chadha, Neelabh Sinha, Vinija Jain","submitted_at":"2024-09-14T02:29:36Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2409.09269","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-14T02:29:36Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"b95da4e1e5243d04470b98ecd819b23061795533152606605de7f2d07b35dc8f","abstract_canon_sha256":"1ba1504ef6bdb861c8b995fbf0b7c0bd6e5ca852565ad90dcdad3513c27cf7aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:56.397882Z","signature_b64":"vwpqMs0ue9snWAAUOvs0+uaYen3j/jvASIHlDU624fW1p3Yx6+29+s1jRPINBr8wT2uyuiEuiSynGv02C8VzBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4dd13dbb071a790598f67e98f445304e973e2490b2140574f0d8c3ec1371eb2b","last_reissued_at":"2026-07-05T09:47:56.397066Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:56.397066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Guiding Vision-Language Model Selection for Visual Question-Answering Across Tasks, Domains, and Knowledge Types","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Aman Chadha, Neelabh Sinha, Vinija Jain","submitted_at":"2024-09-14T02:29:36Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09269","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2409.09269/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2409.09269","created_at":"2026-07-05T09:47:56.397446+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.09269v3","created_at":"2026-07-05T09:47:56.397446+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09269","created_at":"2026-07-05T09:47:56.397446+00:00"},{"alias_kind":"pith_short_12","alias_value":"JXIT3OYHDJ4Q","created_at":"2026-07-05T09:47:56.397446+00:00"},{"alias_kind":"pith_short_16","alias_value":"JXIT3OYHDJ4QLGHW","created_at":"2026-07-05T09:47:56.397446+00:00"},{"alias_kind":"pith_short_8","alias_value":"JXIT3OYH","created_at":"2026-07-05T09:47:56.397446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.04714","citing_title":"ThumbnailTruth: A Multi-Modal LLM Approach for Detecting Misleading YouTube Thumbnails Across Diverse Cultural Settings","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JXIT3OYHDJ4QLGHWP2MPIRJQJ2","json":"https://pith.science/pith/JXIT3OYHDJ4QLGHWP2MPIRJQJ2.json","graph_json":"https://pith.science/api/pith-number/JXIT3OYHDJ4QLGHWP2MPIRJQJ2/graph.json","events_json":"https://pith.science/api/pith-number/JXIT3OYHDJ4QLGHWP2MPIRJQJ2/events.json","paper":"https://pith.science/paper/JXIT3OYH"},"agent_actions":{"view_html":"https://pith.science/pith/JXIT3OYHDJ4QLGHWP2MPIRJQJ2","download_json":"https://pith.science/pith/JXIT3OYHDJ4QLGHWP2MPIRJQJ2.json","view_paper":"https://pith.science/paper/JXIT3OYH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.09269&json=true","fetch_graph":"https://pith.science/api/pith-number/JXIT3OYHDJ4QLGHWP2MPIRJQJ2/graph.json","fetch_events":"https://pith.science/api/pith-number/JXIT3OYHDJ4QLGHWP2MPIRJQJ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JXIT3OYHDJ4QLGHWP2MPIRJQJ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JXIT3OYHDJ4QLGHWP2MPIRJQJ2/action/storage_attestation","attest_author":"https://pith.science/pith/JXIT3OYHDJ4QLGHWP2MPIRJQJ2/action/author_attestation","sign_citation":"https://pith.science/pith/JXIT3OYHDJ4QLGHWP2MPIRJQJ2/action/citation_signature","submit_replication":"https://pith.science/pith/JXIT3OYHDJ4QLGHWP2MPIRJQJ2/action/replication_record"}},"created_at":"2026-07-05T09:47:56.397446+00:00","updated_at":"2026-07-05T09:47:56.397446+00:00"}