{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:NZOVURNEIBP3E2FOVDMVA5X7TN","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":"3ffbe0764b282b5d122b313b9a633e940ea8c966bc31f7bfa947ee4c98a25989","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-23T16:05:16Z","title_canon_sha256":"0198fd86c072631f2e875485a9c0cd207ec9db7c3a813277295922d78ffb14bc"},"schema_version":"1.0","source":{"id":"1606.07356","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.07356","created_at":"2026-05-18T01:03:18Z"},{"alias_kind":"arxiv_version","alias_value":"1606.07356v2","created_at":"2026-05-18T01:03:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.07356","created_at":"2026-05-18T01:03:18Z"},{"alias_kind":"pith_short_12","alias_value":"NZOVURNEIBP3","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"NZOVURNEIBP3E2FO","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"NZOVURNE","created_at":"2026-05-18T12:30:36Z"}],"graph_snapshots":[{"event_id":"sha256:166e6edbd00926ae79d63790c40f5b44e54b3d1405a9e1afc4ce08a274d3a408","target":"graph","created_at":"2026-05-18T01:03:18Z","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"},"paper":{"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","authors_text":"Aishwarya Agrawal, Devi Parikh, Dhruv Batra","cross_cats":["cs.AI","cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-23T16:05:16Z","title":"Analyzing the Behavior of Visual Question Answering Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.07356","kind":"arxiv","version":2},"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:ee308fe3281042735f155afdacc0573e867995cdfa9ea085afd0fd07c21e5d62","target":"record","created_at":"2026-05-18T01:03:18Z","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":"3ffbe0764b282b5d122b313b9a633e940ea8c966bc31f7bfa947ee4c98a25989","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-23T16:05:16Z","title_canon_sha256":"0198fd86c072631f2e875485a9c0cd207ec9db7c3a813277295922d78ffb14bc"},"schema_version":"1.0","source":{"id":"1606.07356","kind":"arxiv","version":2}},"canonical_sha256":"6e5d5a45a4405fb268aea8d95076ff9b6eee9562c304d032f821c47522fd76e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e5d5a45a4405fb268aea8d95076ff9b6eee9562c304d032f821c47522fd76e9","first_computed_at":"2026-05-18T01:03:18.406552Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:03:18.406552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fe74B7wO4O90PmhE3N5cYCDGgPkgYshKKtItQgU1WlOA9avOt2/60A85JMf8RSs/HKeU523HONq6HbTC52b7BA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:03:18.407268Z","signed_message":"canonical_sha256_bytes"},"source_id":"1606.07356","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee308fe3281042735f155afdacc0573e867995cdfa9ea085afd0fd07c21e5d62","sha256:166e6edbd00926ae79d63790c40f5b44e54b3d1405a9e1afc4ce08a274d3a408"],"state_sha256":"7a26a75be31b13791c88da6bcda9aaafa08f7468c3a620c6e9e009fa887d1323"}