{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:NZOVURNEIBP3E2FOVDMVA5X7TN","short_pith_number":"pith:NZOVURNE","schema_version":"1.0","canonical_sha256":"6e5d5a45a4405fb268aea8d95076ff9b6eee9562c304d032f821c47522fd76e9","source":{"kind":"arxiv","id":"1606.07356","version":2},"attestation_state":"computed","paper":{"title":"Analyzing the Behavior of Visual Question Answering Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aishwarya Agrawal, Devi Parikh, Dhruv Batra","submitted_at":"2016-06-23T16:05:16Z","abstract_excerpt":"Recently, a number of deep-learning based models have been proposed for the task of Visual Question Answering (VQA). The performance of most models is clustered around 60-70%. In this paper we propose systematic methods to analyze the behavior of these models as a first step towards recognizing their strengths and weaknesses, and identifying the most fruitful directions for progress. We analyze two models, one each from two major classes of VQA models -- with-attention and without-attention and show the similarities and differences in the behavior of these models. We also analyze the winning e"},"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":"1606.07356","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-23T16:05:16Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"0198fd86c072631f2e875485a9c0cd207ec9db7c3a813277295922d78ffb14bc","abstract_canon_sha256":"3ffbe0764b282b5d122b313b9a633e940ea8c966bc31f7bfa947ee4c98a25989"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:03:18.407268Z","signature_b64":"Fe74B7wO4O90PmhE3N5cYCDGgPkgYshKKtItQgU1WlOA9avOt2/60A85JMf8RSs/HKeU523HONq6HbTC52b7BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e5d5a45a4405fb268aea8d95076ff9b6eee9562c304d032f821c47522fd76e9","last_reissued_at":"2026-05-18T01:03:18.406552Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:03:18.406552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Analyzing the Behavior of Visual Question Answering Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aishwarya Agrawal, Devi Parikh, Dhruv Batra","submitted_at":"2016-06-23T16:05:16Z","abstract_excerpt":"Recently, a number of deep-learning based models have been proposed for the task of Visual Question Answering (VQA). The performance of most models is clustered around 60-70%. In this paper we propose systematic methods to analyze the behavior of these models as a first step towards recognizing their strengths and weaknesses, and identifying the most fruitful directions for progress. We analyze two models, one each from two major classes of VQA models -- with-attention and without-attention and show the similarities and differences in the behavior of these models. We also analyze the winning e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.07356","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":""},"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":"1606.07356","created_at":"2026-05-18T01:03:18.406671+00:00"},{"alias_kind":"arxiv_version","alias_value":"1606.07356v2","created_at":"2026-05-18T01:03:18.406671+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.07356","created_at":"2026-05-18T01:03:18.406671+00:00"},{"alias_kind":"pith_short_12","alias_value":"NZOVURNEIBP3","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_16","alias_value":"NZOVURNEIBP3E2FO","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_8","alias_value":"NZOVURNE","created_at":"2026-05-18T12:30:36.002864+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/NZOVURNEIBP3E2FOVDMVA5X7TN","json":"https://pith.science/pith/NZOVURNEIBP3E2FOVDMVA5X7TN.json","graph_json":"https://pith.science/api/pith-number/NZOVURNEIBP3E2FOVDMVA5X7TN/graph.json","events_json":"https://pith.science/api/pith-number/NZOVURNEIBP3E2FOVDMVA5X7TN/events.json","paper":"https://pith.science/paper/NZOVURNE"},"agent_actions":{"view_html":"https://pith.science/pith/NZOVURNEIBP3E2FOVDMVA5X7TN","download_json":"https://pith.science/pith/NZOVURNEIBP3E2FOVDMVA5X7TN.json","view_paper":"https://pith.science/paper/NZOVURNE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1606.07356&json=true","fetch_graph":"https://pith.science/api/pith-number/NZOVURNEIBP3E2FOVDMVA5X7TN/graph.json","fetch_events":"https://pith.science/api/pith-number/NZOVURNEIBP3E2FOVDMVA5X7TN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NZOVURNEIBP3E2FOVDMVA5X7TN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NZOVURNEIBP3E2FOVDMVA5X7TN/action/storage_attestation","attest_author":"https://pith.science/pith/NZOVURNEIBP3E2FOVDMVA5X7TN/action/author_attestation","sign_citation":"https://pith.science/pith/NZOVURNEIBP3E2FOVDMVA5X7TN/action/citation_signature","submit_replication":"https://pith.science/pith/NZOVURNEIBP3E2FOVDMVA5X7TN/action/replication_record"}},"created_at":"2026-05-18T01:03:18.406671+00:00","updated_at":"2026-05-18T01:03:18.406671+00:00"}