{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:VPNBVWXL4X3YVNHATJZQNWFR2M","short_pith_number":"pith:VPNBVWXL","canonical_record":{"source":{"id":"1803.06936","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-16T07:58:21Z","cross_cats_sorted":[],"title_canon_sha256":"d8e1548b98b6d3bd070ace7bfe0757c0238275c738169ce8c70ea4767d6bfcc6","abstract_canon_sha256":"f2e0f31392d142da0d07cfc84016a9a64be4c1ba603bbcfa07e7cafb1300bfb7"},"schema_version":"1.0"},"canonical_sha256":"abda1adaebe5f78ab4e09a7306d8b1d30c4a6b76458b98d7dc8d8461c9117c14","source":{"kind":"arxiv","id":"1803.06936","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.06936","created_at":"2026-05-18T00:20:40Z"},{"alias_kind":"arxiv_version","alias_value":"1803.06936v1","created_at":"2026-05-18T00:20:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.06936","created_at":"2026-05-18T00:20:40Z"},{"alias_kind":"pith_short_12","alias_value":"VPNBVWXL4X3Y","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VPNBVWXL4X3YVNHA","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VPNBVWXL","created_at":"2026-05-18T12:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:VPNBVWXL4X3YVNHATJZQNWFR2M","target":"record","payload":{"canonical_record":{"source":{"id":"1803.06936","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-16T07:58:21Z","cross_cats_sorted":[],"title_canon_sha256":"d8e1548b98b6d3bd070ace7bfe0757c0238275c738169ce8c70ea4767d6bfcc6","abstract_canon_sha256":"f2e0f31392d142da0d07cfc84016a9a64be4c1ba603bbcfa07e7cafb1300bfb7"},"schema_version":"1.0"},"canonical_sha256":"abda1adaebe5f78ab4e09a7306d8b1d30c4a6b76458b98d7dc8d8461c9117c14","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:40.792764Z","signature_b64":"IEwW7gEt4w09Da3S1G0Z7E1hMFa5Ry1MyZsYhB2e5xbpxIvnwfP12pUGa+JISJQECm7zF4G43AGBDKjnnazbBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abda1adaebe5f78ab4e09a7306d8b1d30c4a6b76458b98d7dc8d8461c9117c14","last_reissued_at":"2026-05-18T00:20:40.792103Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:40.792103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.06936","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:20:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z9VZaPDtur8BikxT/Q3t8Ng0TtU0v1C2aYEQgAwmxsSl1iEqidYiNZzjGScjWDATSR3UiPHxhrlISYx2lcFeDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T10:24:39.431445Z"},"content_sha256":"ba96827236461d83c498670ff37df5953a15951ed0a48e54f96bbcf8f672f0c3","schema_version":"1.0","event_id":"sha256:ba96827236461d83c498670ff37df5953a15951ed0a48e54f96bbcf8f672f0c3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:VPNBVWXL4X3YVNHATJZQNWFR2M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Inverse Visual Question Answering: A New Benchmark and VQA Diagnosis Tool","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changyin Sun, Feng Liu, Tao Xiang, Timothy M. Hospedales, Wankou Yang","submitted_at":"2018-03-16T07:58:21Z","abstract_excerpt":"In recent years, visual question answering (VQA) has become topical. The premise of VQA's significance as a benchmark in AI, is that both the image and textual question need to be well understood and mutually grounded in order to infer the correct answer. However, current VQA models perhaps `understand' less than initially hoped, and instead master the easier task of exploiting cues given away in the question and biases in the answer distribution. In this paper we propose the inverse problem of VQA (iVQA). The iVQA task is to generate a question that corresponds to a given image and answer pai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.06936","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:20:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ymB17N/i2LiDpzu8p2hSa8UBEV/5ULKYmEKD9xRtomeHm70O4G3tft1BFNznPVprhePAqiKhNj6YPcKNZ9UNCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T10:24:39.431962Z"},"content_sha256":"a93808630e999187baa331eddc545e0b8508942727e45b3258ee3cf0c5f9f8b1","schema_version":"1.0","event_id":"sha256:a93808630e999187baa331eddc545e0b8508942727e45b3258ee3cf0c5f9f8b1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VPNBVWXL4X3YVNHATJZQNWFR2M/bundle.json","state_url":"https://pith.science/pith/VPNBVWXL4X3YVNHATJZQNWFR2M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VPNBVWXL4X3YVNHATJZQNWFR2M/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-31T10:24:39Z","links":{"resolver":"https://pith.science/pith/VPNBVWXL4X3YVNHATJZQNWFR2M","bundle":"https://pith.science/pith/VPNBVWXL4X3YVNHATJZQNWFR2M/bundle.json","state":"https://pith.science/pith/VPNBVWXL4X3YVNHATJZQNWFR2M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VPNBVWXL4X3YVNHATJZQNWFR2M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:VPNBVWXL4X3YVNHATJZQNWFR2M","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":"f2e0f31392d142da0d07cfc84016a9a64be4c1ba603bbcfa07e7cafb1300bfb7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-16T07:58:21Z","title_canon_sha256":"d8e1548b98b6d3bd070ace7bfe0757c0238275c738169ce8c70ea4767d6bfcc6"},"schema_version":"1.0","source":{"id":"1803.06936","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.06936","created_at":"2026-05-18T00:20:40Z"},{"alias_kind":"arxiv_version","alias_value":"1803.06936v1","created_at":"2026-05-18T00:20:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.06936","created_at":"2026-05-18T00:20:40Z"},{"alias_kind":"pith_short_12","alias_value":"VPNBVWXL4X3Y","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VPNBVWXL4X3YVNHA","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VPNBVWXL","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:a93808630e999187baa331eddc545e0b8508942727e45b3258ee3cf0c5f9f8b1","target":"graph","created_at":"2026-05-18T00:20:40Z","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":"In recent years, visual question answering (VQA) has become topical. The premise of VQA's significance as a benchmark in AI, is that both the image and textual question need to be well understood and mutually grounded in order to infer the correct answer. However, current VQA models perhaps `understand' less than initially hoped, and instead master the easier task of exploiting cues given away in the question and biases in the answer distribution. In this paper we propose the inverse problem of VQA (iVQA). The iVQA task is to generate a question that corresponds to a given image and answer pai","authors_text":"Changyin Sun, Feng Liu, Tao Xiang, Timothy M. Hospedales, Wankou Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-16T07:58:21Z","title":"Inverse Visual Question Answering: A New Benchmark and VQA Diagnosis Tool"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.06936","kind":"arxiv","version":1},"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:ba96827236461d83c498670ff37df5953a15951ed0a48e54f96bbcf8f672f0c3","target":"record","created_at":"2026-05-18T00:20:40Z","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":"f2e0f31392d142da0d07cfc84016a9a64be4c1ba603bbcfa07e7cafb1300bfb7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-16T07:58:21Z","title_canon_sha256":"d8e1548b98b6d3bd070ace7bfe0757c0238275c738169ce8c70ea4767d6bfcc6"},"schema_version":"1.0","source":{"id":"1803.06936","kind":"arxiv","version":1}},"canonical_sha256":"abda1adaebe5f78ab4e09a7306d8b1d30c4a6b76458b98d7dc8d8461c9117c14","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"abda1adaebe5f78ab4e09a7306d8b1d30c4a6b76458b98d7dc8d8461c9117c14","first_computed_at":"2026-05-18T00:20:40.792103Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:20:40.792103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IEwW7gEt4w09Da3S1G0Z7E1hMFa5Ry1MyZsYhB2e5xbpxIvnwfP12pUGa+JISJQECm7zF4G43AGBDKjnnazbBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:20:40.792764Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.06936","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba96827236461d83c498670ff37df5953a15951ed0a48e54f96bbcf8f672f0c3","sha256:a93808630e999187baa331eddc545e0b8508942727e45b3258ee3cf0c5f9f8b1"],"state_sha256":"cdf0fcea3b9597cbedf009cec675b9deff3e1ab4402c084dee93a5601f29cff5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mduu7HW3TzFLXD+mOmFY1nyl2gdItuoV0an/ddoEsb9sKGekErdxE7LJIHHQqqtb0Js7be25SXzmNFsoiJahCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T10:24:39.435266Z","bundle_sha256":"103b2065ec1b8b9d946a0785fca7b7bdb2debf80c4066dc2e79d0b7d196a7536"}}