{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:IMGFGIOFMHK7P4NFWVHWHYSU4Y","short_pith_number":"pith:IMGFGIOF","canonical_record":{"source":{"id":"1703.09684","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-28T17:48:07Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"29ceb629dd78b21571e5a7ccd3d83652f7bee5118815815ebe6c87af60370b98","abstract_canon_sha256":"c1b63d7a6cc11202027698ce6832361c857b0df8c65ec4e79a34a50941c584f1"},"schema_version":"1.0"},"canonical_sha256":"430c5321c561d5f7f1a5b54f63e254e61c62ced409c84554cee01d9799a66a4d","source":{"kind":"arxiv","id":"1703.09684","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.09684","created_at":"2026-05-18T00:35:13Z"},{"alias_kind":"arxiv_version","alias_value":"1703.09684v2","created_at":"2026-05-18T00:35:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.09684","created_at":"2026-05-18T00:35:13Z"},{"alias_kind":"pith_short_12","alias_value":"IMGFGIOFMHK7","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"IMGFGIOFMHK7P4NF","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"IMGFGIOF","created_at":"2026-05-18T12:31:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:IMGFGIOFMHK7P4NFWVHWHYSU4Y","target":"record","payload":{"canonical_record":{"source":{"id":"1703.09684","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-28T17:48:07Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"29ceb629dd78b21571e5a7ccd3d83652f7bee5118815815ebe6c87af60370b98","abstract_canon_sha256":"c1b63d7a6cc11202027698ce6832361c857b0df8c65ec4e79a34a50941c584f1"},"schema_version":"1.0"},"canonical_sha256":"430c5321c561d5f7f1a5b54f63e254e61c62ced409c84554cee01d9799a66a4d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:13.760442Z","signature_b64":"Zz7N4X3r769ci65/FIS/v6XpAqS2+FjoLKYrtjh4YFm6sM7poCs0OCxxdwl770cvx4m2U+WMZ1IiaRPvzUTPDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"430c5321c561d5f7f1a5b54f63e254e61c62ced409c84554cee01d9799a66a4d","last_reissued_at":"2026-05-18T00:35:13.759952Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:13.759952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.09684","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:35:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6FtMk2NCiWyfo1YnKpclkzYa3v9BF1nwD9IpES38PaxTnusQsxKs51D6mZukLy9pfJ68r8esQwGqm/95CrsHAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T08:36:02.695688Z"},"content_sha256":"bfb434f4a229e46d806e170ea869c04dbbcc3845fa97e5aab2da743a30135ea8","schema_version":"1.0","event_id":"sha256:bfb434f4a229e46d806e170ea869c04dbbcc3845fa97e5aab2da743a30135ea8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:IMGFGIOFMHK7P4NFWVHWHYSU4Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Analysis of Visual Question Answering Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Christopher Kanan, Kushal Kafle","submitted_at":"2017-03-28T17:48:07Z","abstract_excerpt":"In visual question answering (VQA), an algorithm must answer text-based questions about images. While multiple datasets for VQA have been created since late 2014, they all have flaws in both their content and the way algorithms are evaluated on them. As a result, evaluation scores are inflated and predominantly determined by answering easier questions, making it difficult to compare different methods. In this paper, we analyze existing VQA algorithms using a new dataset. It contains over 1.6 million questions organized into 12 different categories. We also introduce questions that are meaningl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.09684","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:35:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wDm5UYKZSz3KKKTuQ9YPbIZKaTFp9RjvlU3BGD/dZSMqLfBvJUGG2Jwz/+pVQgrb8AAcsp8tJ0fe33kBEFa8Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T08:36:02.696553Z"},"content_sha256":"c8ef591eb6bb21c97462c4512f7526a194dd268204b52dceae6ef63bf9e9fdfd","schema_version":"1.0","event_id":"sha256:c8ef591eb6bb21c97462c4512f7526a194dd268204b52dceae6ef63bf9e9fdfd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IMGFGIOFMHK7P4NFWVHWHYSU4Y/bundle.json","state_url":"https://pith.science/pith/IMGFGIOFMHK7P4NFWVHWHYSU4Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IMGFGIOFMHK7P4NFWVHWHYSU4Y/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":"2026-08-12T08:36:02Z","links":{"resolver":"https://pith.science/pith/IMGFGIOFMHK7P4NFWVHWHYSU4Y","bundle":"https://pith.science/pith/IMGFGIOFMHK7P4NFWVHWHYSU4Y/bundle.json","state":"https://pith.science/pith/IMGFGIOFMHK7P4NFWVHWHYSU4Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IMGFGIOFMHK7P4NFWVHWHYSU4Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:IMGFGIOFMHK7P4NFWVHWHYSU4Y","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":"c1b63d7a6cc11202027698ce6832361c857b0df8c65ec4e79a34a50941c584f1","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-28T17:48:07Z","title_canon_sha256":"29ceb629dd78b21571e5a7ccd3d83652f7bee5118815815ebe6c87af60370b98"},"schema_version":"1.0","source":{"id":"1703.09684","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.09684","created_at":"2026-05-18T00:35:13Z"},{"alias_kind":"arxiv_version","alias_value":"1703.09684v2","created_at":"2026-05-18T00:35:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.09684","created_at":"2026-05-18T00:35:13Z"},{"alias_kind":"pith_short_12","alias_value":"IMGFGIOFMHK7","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"IMGFGIOFMHK7P4NF","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"IMGFGIOF","created_at":"2026-05-18T12:31:21Z"}],"graph_snapshots":[{"event_id":"sha256:c8ef591eb6bb21c97462c4512f7526a194dd268204b52dceae6ef63bf9e9fdfd","target":"graph","created_at":"2026-05-18T00:35:13Z","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 visual question answering (VQA), an algorithm must answer text-based questions about images. While multiple datasets for VQA have been created since late 2014, they all have flaws in both their content and the way algorithms are evaluated on them. As a result, evaluation scores are inflated and predominantly determined by answering easier questions, making it difficult to compare different methods. In this paper, we analyze existing VQA algorithms using a new dataset. It contains over 1.6 million questions organized into 12 different categories. We also introduce questions that are meaningl","authors_text":"Christopher Kanan, Kushal Kafle","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-28T17:48:07Z","title":"An Analysis of Visual Question Answering Algorithms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.09684","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:bfb434f4a229e46d806e170ea869c04dbbcc3845fa97e5aab2da743a30135ea8","target":"record","created_at":"2026-05-18T00:35:13Z","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":"c1b63d7a6cc11202027698ce6832361c857b0df8c65ec4e79a34a50941c584f1","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-28T17:48:07Z","title_canon_sha256":"29ceb629dd78b21571e5a7ccd3d83652f7bee5118815815ebe6c87af60370b98"},"schema_version":"1.0","source":{"id":"1703.09684","kind":"arxiv","version":2}},"canonical_sha256":"430c5321c561d5f7f1a5b54f63e254e61c62ced409c84554cee01d9799a66a4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"430c5321c561d5f7f1a5b54f63e254e61c62ced409c84554cee01d9799a66a4d","first_computed_at":"2026-05-18T00:35:13.759952Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:35:13.759952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zz7N4X3r769ci65/FIS/v6XpAqS2+FjoLKYrtjh4YFm6sM7poCs0OCxxdwl770cvx4m2U+WMZ1IiaRPvzUTPDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:35:13.760442Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.09684","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bfb434f4a229e46d806e170ea869c04dbbcc3845fa97e5aab2da743a30135ea8","sha256:c8ef591eb6bb21c97462c4512f7526a194dd268204b52dceae6ef63bf9e9fdfd"],"state_sha256":"35b374efda0d9df24ded52b9fc6d1670eaf115f77d22fe2a42ece69698e63438"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EKB2XCpSVZdqNl7kVUy5z5L0SakOG/kw01xt9bm2xkDkJa9KH/fa1wr/Ak2tpVYWVPVGUmLp99PmN0T6xsEHCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T08:36:02.701627Z","bundle_sha256":"fcc0ba799933165a80187a2365dec9b9fa7f9fb1174012c7efa1c9c4c1f4b2aa"}}