{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:A7BSINFZSLLSWXGCGTDXMIP4AO","short_pith_number":"pith:A7BSINFZ","schema_version":"1.0","canonical_sha256":"07c32434b992d72b5cc234c77621fc03a3fb7c5843b751b077e104a56eca1067","source":{"kind":"arxiv","id":"1809.04344","version":1},"attestation_state":"computed","paper":{"title":"The Wisdom of MaSSeS: Majority, Subjectivity, and Semantic Similarity in the Evaluation of VQA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Andreas Dengel, Moin Nabi, Sandro Pezzelle, Shailza Jolly, Tassilo Klein","submitted_at":"2018-09-12T10:11:39Z","abstract_excerpt":"We introduce MASSES, a simple evaluation metric for the task of Visual Question Answering (VQA). In its standard form, the VQA task is operationalized as follows: Given an image and an open-ended question in natural language, systems are required to provide a suitable answer. Currently, model performance is evaluated by means of a somehow simplistic metric: If the predicted answer is chosen by at least 3 human annotators out of 10, then it is 100% correct. Though intuitively valuable, this metric has some important limitations. First, it ignores whether the predicted answer is the one selected"},"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":"1809.04344","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-12T10:11:39Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"d72e4f51b33389badab4d8b0a719d163fbb07e3ba82886b74c281a1aad676b69","abstract_canon_sha256":"285066d301b4873347e5e47223e8c9fc302bfeed5e596855c0b9f9c6e0675e9d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:52.667887Z","signature_b64":"nzPPrPhxiGyH+PHXWazwQDdgW/jkzu0VJ2VP1BCyZW2VRIx7q0mPQtMSJImHyaY2LQ7ZULAf/pTX3n+pSNctBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07c32434b992d72b5cc234c77621fc03a3fb7c5843b751b077e104a56eca1067","last_reissued_at":"2026-05-18T00:05:52.667233Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:52.667233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Wisdom of MaSSeS: Majority, Subjectivity, and Semantic Similarity in the Evaluation of VQA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Andreas Dengel, Moin Nabi, Sandro Pezzelle, Shailza Jolly, Tassilo Klein","submitted_at":"2018-09-12T10:11:39Z","abstract_excerpt":"We introduce MASSES, a simple evaluation metric for the task of Visual Question Answering (VQA). In its standard form, the VQA task is operationalized as follows: Given an image and an open-ended question in natural language, systems are required to provide a suitable answer. Currently, model performance is evaluated by means of a somehow simplistic metric: If the predicted answer is chosen by at least 3 human annotators out of 10, then it is 100% correct. Though intuitively valuable, this metric has some important limitations. First, it ignores whether the predicted answer is the one selected"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.04344","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1809.04344","created_at":"2026-05-18T00:05:52.667336+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.04344v1","created_at":"2026-05-18T00:05:52.667336+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.04344","created_at":"2026-05-18T00:05:52.667336+00:00"},{"alias_kind":"pith_short_12","alias_value":"A7BSINFZSLLS","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"A7BSINFZSLLSWXGC","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"A7BSINFZ","created_at":"2026-05-18T12:32:13.499390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A7BSINFZSLLSWXGCGTDXMIP4AO","json":"https://pith.science/pith/A7BSINFZSLLSWXGCGTDXMIP4AO.json","graph_json":"https://pith.science/api/pith-number/A7BSINFZSLLSWXGCGTDXMIP4AO/graph.json","events_json":"https://pith.science/api/pith-number/A7BSINFZSLLSWXGCGTDXMIP4AO/events.json","paper":"https://pith.science/paper/A7BSINFZ"},"agent_actions":{"view_html":"https://pith.science/pith/A7BSINFZSLLSWXGCGTDXMIP4AO","download_json":"https://pith.science/pith/A7BSINFZSLLSWXGCGTDXMIP4AO.json","view_paper":"https://pith.science/paper/A7BSINFZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.04344&json=true","fetch_graph":"https://pith.science/api/pith-number/A7BSINFZSLLSWXGCGTDXMIP4AO/graph.json","fetch_events":"https://pith.science/api/pith-number/A7BSINFZSLLSWXGCGTDXMIP4AO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A7BSINFZSLLSWXGCGTDXMIP4AO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A7BSINFZSLLSWXGCGTDXMIP4AO/action/storage_attestation","attest_author":"https://pith.science/pith/A7BSINFZSLLSWXGCGTDXMIP4AO/action/author_attestation","sign_citation":"https://pith.science/pith/A7BSINFZSLLSWXGCGTDXMIP4AO/action/citation_signature","submit_replication":"https://pith.science/pith/A7BSINFZSLLSWXGCGTDXMIP4AO/action/replication_record"}},"created_at":"2026-05-18T00:05:52.667336+00:00","updated_at":"2026-05-18T00:05:52.667336+00:00"}