{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:LC2ILO2IS2HQPZ2BINBRYJZKIK","short_pith_number":"pith:LC2ILO2I","canonical_record":{"source":{"id":"1806.00857","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-03T19:31:47Z","cross_cats_sorted":[],"title_canon_sha256":"d4ac6b1ca55f8d494691d8323dd3810d914cd3d7ab87d420d0a209ebcf91ea8a","abstract_canon_sha256":"4ee4e3b8c05ef045028df03acc64c23e333cca24181d10ff9af64a7a8f2265be"},"schema_version":"1.0"},"canonical_sha256":"58b485bb48968f07e74143431c272a42acf72af48e24e3c9c4807f9c5cedeed1","source":{"kind":"arxiv","id":"1806.00857","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.00857","created_at":"2026-05-18T00:09:58Z"},{"alias_kind":"arxiv_version","alias_value":"1806.00857v3","created_at":"2026-05-18T00:09:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.00857","created_at":"2026-05-18T00:09:58Z"},{"alias_kind":"pith_short_12","alias_value":"LC2ILO2IS2HQ","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"LC2ILO2IS2HQPZ2B","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"LC2ILO2I","created_at":"2026-05-18T12:32:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:LC2ILO2IS2HQPZ2BINBRYJZKIK","target":"record","payload":{"canonical_record":{"source":{"id":"1806.00857","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-03T19:31:47Z","cross_cats_sorted":[],"title_canon_sha256":"d4ac6b1ca55f8d494691d8323dd3810d914cd3d7ab87d420d0a209ebcf91ea8a","abstract_canon_sha256":"4ee4e3b8c05ef045028df03acc64c23e333cca24181d10ff9af64a7a8f2265be"},"schema_version":"1.0"},"canonical_sha256":"58b485bb48968f07e74143431c272a42acf72af48e24e3c9c4807f9c5cedeed1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:58.820669Z","signature_b64":"iolWX4dU6mYy4e/wm2hlk3UlDQQYwlCul4GGsBuI12EfykQyuW0WvQkgtMIashMG2Jr5TpEkjSnsag5NIm9uCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58b485bb48968f07e74143431c272a42acf72af48e24e3c9c4807f9c5cedeed1","last_reissued_at":"2026-05-18T00:09:58.819967Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:58.819967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.00857","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:09:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FeOStkMYthazq5SL/0WfYKv7gihqWeKQK1NJ3pxBXWHSeALYvyD2hOuSTY9enEph16f5Vajrei9ZLacBamuSDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T03:10:29.463419Z"},"content_sha256":"eafeebedc1a2e87c735d17b007feee244aef1e4d7559c25ed4922970fe7ba6dc","schema_version":"1.0","event_id":"sha256:eafeebedc1a2e87c735d17b007feee244aef1e4d7559c25ed4922970fe7ba6dc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:LC2ILO2IS2HQPZ2BINBRYJZKIK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Flip Side: Identifying Counterexamples in Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Rush, Aron Szanto, Gabriel Grand, Yoon Kim","submitted_at":"2018-06-03T19:31:47Z","abstract_excerpt":"Visual question answering (VQA) models respond to open-ended natural language questions about images. While VQA is an increasingly popular area of research, it is unclear to what extent current VQA architectures learn key semantic distinctions between visually-similar images. To investigate this question, we explore a reformulation of the VQA task that challenges models to identify counterexamples: images that result in a different answer to the original question. We introduce two methods for evaluating existing VQA models against a supervised counterexample prediction task, VQA-CX. While our "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.00857","kind":"arxiv","version":3},"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":"2026-05-18T00:09:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aNpIR3Pri3p8jKnVGUFEUJLiX+H/0CxRD6ZP5JVIVzk3j5u5GQojw6g+v+I4LSvJovoUfay9FwZObiap9R2JDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T03:10:29.463773Z"},"content_sha256":"9922cd5563736d54b8ada7de1b15ec7acab506dbc3f1f4694ab3b605395eeb17","schema_version":"1.0","event_id":"sha256:9922cd5563736d54b8ada7de1b15ec7acab506dbc3f1f4694ab3b605395eeb17"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LC2ILO2IS2HQPZ2BINBRYJZKIK/bundle.json","state_url":"https://pith.science/pith/LC2ILO2IS2HQPZ2BINBRYJZKIK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LC2ILO2IS2HQPZ2BINBRYJZKIK/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":"2026-06-03T03:10:29Z","links":{"resolver":"https://pith.science/pith/LC2ILO2IS2HQPZ2BINBRYJZKIK","bundle":"https://pith.science/pith/LC2ILO2IS2HQPZ2BINBRYJZKIK/bundle.json","state":"https://pith.science/pith/LC2ILO2IS2HQPZ2BINBRYJZKIK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LC2ILO2IS2HQPZ2BINBRYJZKIK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:LC2ILO2IS2HQPZ2BINBRYJZKIK","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":"4ee4e3b8c05ef045028df03acc64c23e333cca24181d10ff9af64a7a8f2265be","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-03T19:31:47Z","title_canon_sha256":"d4ac6b1ca55f8d494691d8323dd3810d914cd3d7ab87d420d0a209ebcf91ea8a"},"schema_version":"1.0","source":{"id":"1806.00857","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.00857","created_at":"2026-05-18T00:09:58Z"},{"alias_kind":"arxiv_version","alias_value":"1806.00857v3","created_at":"2026-05-18T00:09:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.00857","created_at":"2026-05-18T00:09:58Z"},{"alias_kind":"pith_short_12","alias_value":"LC2ILO2IS2HQ","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"LC2ILO2IS2HQPZ2B","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"LC2ILO2I","created_at":"2026-05-18T12:32:33Z"}],"graph_snapshots":[{"event_id":"sha256:9922cd5563736d54b8ada7de1b15ec7acab506dbc3f1f4694ab3b605395eeb17","target":"graph","created_at":"2026-05-18T00:09:58Z","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":"Visual question answering (VQA) models respond to open-ended natural language questions about images. While VQA is an increasingly popular area of research, it is unclear to what extent current VQA architectures learn key semantic distinctions between visually-similar images. To investigate this question, we explore a reformulation of the VQA task that challenges models to identify counterexamples: images that result in a different answer to the original question. We introduce two methods for evaluating existing VQA models against a supervised counterexample prediction task, VQA-CX. While our ","authors_text":"Alexander Rush, Aron Szanto, Gabriel Grand, Yoon Kim","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-03T19:31:47Z","title":"On the Flip Side: Identifying Counterexamples in Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.00857","kind":"arxiv","version":3},"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:eafeebedc1a2e87c735d17b007feee244aef1e4d7559c25ed4922970fe7ba6dc","target":"record","created_at":"2026-05-18T00:09:58Z","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":"4ee4e3b8c05ef045028df03acc64c23e333cca24181d10ff9af64a7a8f2265be","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-03T19:31:47Z","title_canon_sha256":"d4ac6b1ca55f8d494691d8323dd3810d914cd3d7ab87d420d0a209ebcf91ea8a"},"schema_version":"1.0","source":{"id":"1806.00857","kind":"arxiv","version":3}},"canonical_sha256":"58b485bb48968f07e74143431c272a42acf72af48e24e3c9c4807f9c5cedeed1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"58b485bb48968f07e74143431c272a42acf72af48e24e3c9c4807f9c5cedeed1","first_computed_at":"2026-05-18T00:09:58.819967Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:09:58.819967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iolWX4dU6mYy4e/wm2hlk3UlDQQYwlCul4GGsBuI12EfykQyuW0WvQkgtMIashMG2Jr5TpEkjSnsag5NIm9uCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:09:58.820669Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.00857","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eafeebedc1a2e87c735d17b007feee244aef1e4d7559c25ed4922970fe7ba6dc","sha256:9922cd5563736d54b8ada7de1b15ec7acab506dbc3f1f4694ab3b605395eeb17"],"state_sha256":"c885dfb7a2b34e8efdf8325761a8cc462e79456f7b910df28f127e47122657a1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wwjW0YWQc2MTkQT5ItiWSVBkHzcOC23QjMUcieoGh5BCqY4nRmnoNgdy+PU3FmME0Vh2yt7316Y5/Qx58AyMAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T03:10:29.466102Z","bundle_sha256":"ec9a50ffaeab87cb1e4f6e1452d6247938f013d7cd76746a712fdad4ceff3c44"}}