{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:NYFA3ZHN5JO7RRXQQZO7DHOZFT","short_pith_number":"pith:NYFA3ZHN","canonical_record":{"source":{"id":"1511.05099","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-11-16T19:38:14Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"22901dffc2b29bb32ee9f9407c8f728a8ef009568efa8aad83b8bc9581041a95","abstract_canon_sha256":"f04007a2a2f7d9ab7d999f16f050ed2ea80d6ad57e41c6720a8106d04defb113"},"schema_version":"1.0"},"canonical_sha256":"6e0a0de4edea5df8c6f0865df19dd92ccbb241f9fb50243cea0b4fef135334ee","source":{"kind":"arxiv","id":"1511.05099","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.05099","created_at":"2026-05-18T01:16:45Z"},{"alias_kind":"arxiv_version","alias_value":"1511.05099v5","created_at":"2026-05-18T01:16:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.05099","created_at":"2026-05-18T01:16:45Z"},{"alias_kind":"pith_short_12","alias_value":"NYFA3ZHN5JO7","created_at":"2026-05-18T12:29:34Z"},{"alias_kind":"pith_short_16","alias_value":"NYFA3ZHN5JO7RRXQ","created_at":"2026-05-18T12:29:34Z"},{"alias_kind":"pith_short_8","alias_value":"NYFA3ZHN","created_at":"2026-05-18T12:29:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:NYFA3ZHN5JO7RRXQQZO7DHOZFT","target":"record","payload":{"canonical_record":{"source":{"id":"1511.05099","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-11-16T19:38:14Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"22901dffc2b29bb32ee9f9407c8f728a8ef009568efa8aad83b8bc9581041a95","abstract_canon_sha256":"f04007a2a2f7d9ab7d999f16f050ed2ea80d6ad57e41c6720a8106d04defb113"},"schema_version":"1.0"},"canonical_sha256":"6e0a0de4edea5df8c6f0865df19dd92ccbb241f9fb50243cea0b4fef135334ee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:16:45.471359Z","signature_b64":"uBNEX46Nr+rc5+RqRAGeDYvXPDkAxMKEp3K+ZXuWJPjSK2HO4OhXBA8jaD4XzVLjIoHv+qDObsYvyS8KadiADA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e0a0de4edea5df8c6f0865df19dd92ccbb241f9fb50243cea0b4fef135334ee","last_reissued_at":"2026-05-18T01:16:45.470601Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:16:45.470601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1511.05099","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:16:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k8Z/oOVcweAJZ/QMbwVeSa1Xk5QNZLjs+Q6IwLWsX1u6GBVP54FYRXUdrnXqvJn2IbIeIoxCqGMhEC7QSWNuDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T03:41:54.503338Z"},"content_sha256":"3b558ba6d8504360e5ac7320170aeca520c987661423f21ca08a0c2ed3d39956","schema_version":"1.0","event_id":"sha256:3b558ba6d8504360e5ac7320170aeca520c987661423f21ca08a0c2ed3d39956"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:NYFA3ZHN5JO7RRXQQZO7DHOZFT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Yin and Yang: Balancing and Answering Binary Visual Questions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Devi Parikh, Dhruv Batra, Douglas Summers-Stay, Peng Zhang, Yash Goyal","submitted_at":"2015-11-16T19:38:14Z","abstract_excerpt":"The complex compositional structure of language makes problems at the intersection of vision and language challenging. But language also provides a strong prior that can result in good superficial performance, without the underlying models truly understanding the visual content. This can hinder progress in pushing state of art in the computer vision aspects of multi-modal AI. In this paper, we address binary Visual Question Answering (VQA) on abstract scenes. We formulate this problem as visual verification of concepts inquired in the questions. Specifically, we convert the question to a tuple"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.05099","kind":"arxiv","version":5},"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":"2026-05-18T01:16:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0uhc9Z8gTvYKBo1SHot0BrCIrEVLj4pXifM55UOVVRBaNaC5rxspZ9xbxGftGEzBPzvUE+ZtvZhQcvrMk/HZCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T03:41:54.504004Z"},"content_sha256":"d04bff22c22748006ad33bceae33b1d802447e498563c7ae9262b194a428fc7e","schema_version":"1.0","event_id":"sha256:d04bff22c22748006ad33bceae33b1d802447e498563c7ae9262b194a428fc7e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NYFA3ZHN5JO7RRXQQZO7DHOZFT/bundle.json","state_url":"https://pith.science/pith/NYFA3ZHN5JO7RRXQQZO7DHOZFT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NYFA3ZHN5JO7RRXQQZO7DHOZFT/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":"2026-05-31T03:41:54Z","links":{"resolver":"https://pith.science/pith/NYFA3ZHN5JO7RRXQQZO7DHOZFT","bundle":"https://pith.science/pith/NYFA3ZHN5JO7RRXQQZO7DHOZFT/bundle.json","state":"https://pith.science/pith/NYFA3ZHN5JO7RRXQQZO7DHOZFT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NYFA3ZHN5JO7RRXQQZO7DHOZFT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:NYFA3ZHN5JO7RRXQQZO7DHOZFT","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":"f04007a2a2f7d9ab7d999f16f050ed2ea80d6ad57e41c6720a8106d04defb113","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-11-16T19:38:14Z","title_canon_sha256":"22901dffc2b29bb32ee9f9407c8f728a8ef009568efa8aad83b8bc9581041a95"},"schema_version":"1.0","source":{"id":"1511.05099","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.05099","created_at":"2026-05-18T01:16:45Z"},{"alias_kind":"arxiv_version","alias_value":"1511.05099v5","created_at":"2026-05-18T01:16:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.05099","created_at":"2026-05-18T01:16:45Z"},{"alias_kind":"pith_short_12","alias_value":"NYFA3ZHN5JO7","created_at":"2026-05-18T12:29:34Z"},{"alias_kind":"pith_short_16","alias_value":"NYFA3ZHN5JO7RRXQ","created_at":"2026-05-18T12:29:34Z"},{"alias_kind":"pith_short_8","alias_value":"NYFA3ZHN","created_at":"2026-05-18T12:29:34Z"}],"graph_snapshots":[{"event_id":"sha256:d04bff22c22748006ad33bceae33b1d802447e498563c7ae9262b194a428fc7e","target":"graph","created_at":"2026-05-18T01:16:45Z","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":"The complex compositional structure of language makes problems at the intersection of vision and language challenging. But language also provides a strong prior that can result in good superficial performance, without the underlying models truly understanding the visual content. This can hinder progress in pushing state of art in the computer vision aspects of multi-modal AI. In this paper, we address binary Visual Question Answering (VQA) on abstract scenes. We formulate this problem as visual verification of concepts inquired in the questions. Specifically, we convert the question to a tuple","authors_text":"Devi Parikh, Dhruv Batra, Douglas Summers-Stay, Peng Zhang, Yash Goyal","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-11-16T19:38:14Z","title":"Yin and Yang: Balancing and Answering Binary Visual Questions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.05099","kind":"arxiv","version":5},"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":"sha256:3b558ba6d8504360e5ac7320170aeca520c987661423f21ca08a0c2ed3d39956","target":"record","created_at":"2026-05-18T01:16:45Z","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":"f04007a2a2f7d9ab7d999f16f050ed2ea80d6ad57e41c6720a8106d04defb113","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-11-16T19:38:14Z","title_canon_sha256":"22901dffc2b29bb32ee9f9407c8f728a8ef009568efa8aad83b8bc9581041a95"},"schema_version":"1.0","source":{"id":"1511.05099","kind":"arxiv","version":5}},"canonical_sha256":"6e0a0de4edea5df8c6f0865df19dd92ccbb241f9fb50243cea0b4fef135334ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e0a0de4edea5df8c6f0865df19dd92ccbb241f9fb50243cea0b4fef135334ee","first_computed_at":"2026-05-18T01:16:45.470601Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:16:45.470601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uBNEX46Nr+rc5+RqRAGeDYvXPDkAxMKEp3K+ZXuWJPjSK2HO4OhXBA8jaD4XzVLjIoHv+qDObsYvyS8KadiADA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:16:45.471359Z","signed_message":"canonical_sha256_bytes"},"source_id":"1511.05099","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b558ba6d8504360e5ac7320170aeca520c987661423f21ca08a0c2ed3d39956","sha256:d04bff22c22748006ad33bceae33b1d802447e498563c7ae9262b194a428fc7e"],"state_sha256":"f9d1d45a6f0b0852eb1a24e199fa70df2ec12dad3bfb2c1c4036452c81eb9afc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w+XRqW0Q+6LTeTIwrv7ZPYNQiR5JCfMIwg7wThqaMo0y5n7UNDMCZQVtj7LqF2m64U5VY/LpNdwiKEz+PZ6LAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T03:41:54.507185Z","bundle_sha256":"25c0b14ca386434810e4da1e43e714565c8eb5a212009f45b6cc442336f95099"}}