{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:WHXO2I2PDFMRSZCQAIBGWGGHUL","short_pith_number":"pith:WHXO2I2P","schema_version":"1.0","canonical_sha256":"b1eeed234f195919645002026b18c7a2e49e13b06d416af51a3c3354fb394274","source":{"kind":"arxiv","id":"2002.08325","version":2},"attestation_state":"computed","paper":{"title":"VQA-LOL: Visual Question Answering under the Lens of Logic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chitta Baral, Pratyay Banerjee, Tejas Gokhale, Yezhou Yang","submitted_at":"2020-02-19T17:57:46Z","abstract_excerpt":"Logical connectives and their implications on the meaning of a natural language sentence are a fundamental aspect of understanding. In this paper, we investigate whether visual question answering (VQA) systems trained to answer a question about an image, are able to answer the logical composition of multiple such questions. When put under this \\textit{Lens of Logic}, state-of-the-art VQA models have difficulty in correctly answering these logically composed questions. We construct an augmentation of the VQA dataset as a benchmark, with questions containing logical compositions and linguistic t"},"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":"2002.08325","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-19T17:57:46Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f3f2843a9a3e741ba4608b42fed2ce20dd661f12b6c359f1f08c777df779d380","abstract_canon_sha256":"0fa4b01bf4008ed2cde191f430934baa45d0a30b8cad1fc420edd33f8ed9eec7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:19:38.175610Z","signature_b64":"mMpVCgp204kqJ5ra3feio9pfbAeh7rnh7bkL9cOWZBZ2I9YUYqV5ywudoWBNgSGKuP74hPa1NYT0YqReRuzeAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1eeed234f195919645002026b18c7a2e49e13b06d416af51a3c3354fb394274","last_reissued_at":"2026-07-05T01:19:38.175096Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:19:38.175096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VQA-LOL: Visual Question Answering under the Lens of Logic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chitta Baral, Pratyay Banerjee, Tejas Gokhale, Yezhou Yang","submitted_at":"2020-02-19T17:57:46Z","abstract_excerpt":"Logical connectives and their implications on the meaning of a natural language sentence are a fundamental aspect of understanding. In this paper, we investigate whether visual question answering (VQA) systems trained to answer a question about an image, are able to answer the logical composition of multiple such questions. When put under this \\textit{Lens of Logic}, state-of-the-art VQA models have difficulty in correctly answering these logically composed questions. We construct an augmentation of the VQA dataset as a benchmark, with questions containing logical compositions and linguistic t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.08325","kind":"arxiv","version":2},"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/2002.08325/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":"2002.08325","created_at":"2026-07-05T01:19:38.175154+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.08325v2","created_at":"2026-07-05T01:19:38.175154+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.08325","created_at":"2026-07-05T01:19:38.175154+00:00"},{"alias_kind":"pith_short_12","alias_value":"WHXO2I2PDFMR","created_at":"2026-07-05T01:19:38.175154+00:00"},{"alias_kind":"pith_short_16","alias_value":"WHXO2I2PDFMRSZCQ","created_at":"2026-07-05T01:19:38.175154+00:00"},{"alias_kind":"pith_short_8","alias_value":"WHXO2I2P","created_at":"2026-07-05T01:19:38.175154+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07919","citing_title":"MedVIGIL: Evaluating Trustworthy Medical VLMs Under Broken Visual Evidence","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07919","citing_title":"MedVIGIL: Evaluating Trustworthy Medical VLMs Under Broken Visual Evidence","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WHXO2I2PDFMRSZCQAIBGWGGHUL","json":"https://pith.science/pith/WHXO2I2PDFMRSZCQAIBGWGGHUL.json","graph_json":"https://pith.science/api/pith-number/WHXO2I2PDFMRSZCQAIBGWGGHUL/graph.json","events_json":"https://pith.science/api/pith-number/WHXO2I2PDFMRSZCQAIBGWGGHUL/events.json","paper":"https://pith.science/paper/WHXO2I2P"},"agent_actions":{"view_html":"https://pith.science/pith/WHXO2I2PDFMRSZCQAIBGWGGHUL","download_json":"https://pith.science/pith/WHXO2I2PDFMRSZCQAIBGWGGHUL.json","view_paper":"https://pith.science/paper/WHXO2I2P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.08325&json=true","fetch_graph":"https://pith.science/api/pith-number/WHXO2I2PDFMRSZCQAIBGWGGHUL/graph.json","fetch_events":"https://pith.science/api/pith-number/WHXO2I2PDFMRSZCQAIBGWGGHUL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WHXO2I2PDFMRSZCQAIBGWGGHUL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WHXO2I2PDFMRSZCQAIBGWGGHUL/action/storage_attestation","attest_author":"https://pith.science/pith/WHXO2I2PDFMRSZCQAIBGWGGHUL/action/author_attestation","sign_citation":"https://pith.science/pith/WHXO2I2PDFMRSZCQAIBGWGGHUL/action/citation_signature","submit_replication":"https://pith.science/pith/WHXO2I2PDFMRSZCQAIBGWGGHUL/action/replication_record"}},"created_at":"2026-07-05T01:19:38.175154+00:00","updated_at":"2026-07-05T01:19:38.175154+00:00"}