{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:YL73JPKXWGULTLS3EUPKO2JHOA","short_pith_number":"pith:YL73JPKX","canonical_record":{"source":{"id":"1805.08389","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-22T04:41:37Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"43b270479da20916f0b44e7321bae7be2d4aa81f85c9b42f2c5659a59f5c435f","abstract_canon_sha256":"c78484ee8ced273c7113b3c1df7d99a9b644ac9b52d1ac5b0bb456cac97a64e8"},"schema_version":"1.0"},"canonical_sha256":"c2ffb4bd57b1a8b9ae5b251ea7692770128cb1646f1c40df16e221f397f5b3d3","source":{"kind":"arxiv","id":"1805.08389","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.08389","created_at":"2026-05-18T00:15:26Z"},{"alias_kind":"arxiv_version","alias_value":"1805.08389v1","created_at":"2026-05-18T00:15:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08389","created_at":"2026-05-18T00:15:26Z"},{"alias_kind":"pith_short_12","alias_value":"YL73JPKXWGUL","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"YL73JPKXWGULTLS3","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"YL73JPKX","created_at":"2026-05-18T12:33:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:YL73JPKXWGULTLS3EUPKO2JHOA","target":"record","payload":{"canonical_record":{"source":{"id":"1805.08389","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-22T04:41:37Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"43b270479da20916f0b44e7321bae7be2d4aa81f85c9b42f2c5659a59f5c435f","abstract_canon_sha256":"c78484ee8ced273c7113b3c1df7d99a9b644ac9b52d1ac5b0bb456cac97a64e8"},"schema_version":"1.0"},"canonical_sha256":"c2ffb4bd57b1a8b9ae5b251ea7692770128cb1646f1c40df16e221f397f5b3d3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:26.681129Z","signature_b64":"d5Z50t7TYrNAnkAUV4bDQFLiQK+abmyKxWWIxBQnPANoMn8iN72RIbaiGJqkEXlbLf1ijlYxUGmaCe7xMUwKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2ffb4bd57b1a8b9ae5b251ea7692770128cb1646f1c40df16e221f397f5b3d3","last_reissued_at":"2026-05-18T00:15:26.680224Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:26.680224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.08389","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":"2026-05-18T00:15:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DnJZEkwIRIDlf67E4zxEHK9SQ0zQmEBy9onJ6JH5CSo/peX6RmfNvnv5eRC4KawUTYaVZ1QGkRjQTc/auoweCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T17:45:41.970172Z"},"content_sha256":"0beb306da0c5bbeaf75391f32a70fa74eb2922281105e34d30dd3bfb80a20d3e","schema_version":"1.0","event_id":"sha256:0beb306da0c5bbeaf75391f32a70fa74eb2922281105e34d30dd3bfb80a20d3e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:YL73JPKXWGULTLS3EUPKO2JHOA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Joint Image Captioning and Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Jialin Wu, Raymond J. Mooney, Zeyuan Hu","submitted_at":"2018-05-22T04:41:37Z","abstract_excerpt":"Answering visual questions need acquire daily common knowledge and model the semantic connection among different parts in images, which is too difficult for VQA systems to learn from images with the only supervision from answers. Meanwhile, image captioning systems with beam search strategy tend to generate similar captions and fail to diversely describe images. To address the aforementioned issues, we present a system to have these two tasks compensate with each other, which is capable of jointly producing image captions and answering visual questions. In particular, we utilize question and i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08389","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":"2026-05-18T00:15:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kxJ1F2IzfwRpnd/tZev0gPO+1qCdotUFp9YWkGWeF5qNnY8z2C+I1oIOg5WBaDqXl7xM97f6DUsDCwOoQp5FBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T17:45:41.970533Z"},"content_sha256":"a12ef7a8caee41e9d735269dd85f541e1df8df278977fcecc15f0c37198cae0f","schema_version":"1.0","event_id":"sha256:a12ef7a8caee41e9d735269dd85f541e1df8df278977fcecc15f0c37198cae0f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YL73JPKXWGULTLS3EUPKO2JHOA/bundle.json","state_url":"https://pith.science/pith/YL73JPKXWGULTLS3EUPKO2JHOA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YL73JPKXWGULTLS3EUPKO2JHOA/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":"2026-06-04T17:45:41Z","links":{"resolver":"https://pith.science/pith/YL73JPKXWGULTLS3EUPKO2JHOA","bundle":"https://pith.science/pith/YL73JPKXWGULTLS3EUPKO2JHOA/bundle.json","state":"https://pith.science/pith/YL73JPKXWGULTLS3EUPKO2JHOA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YL73JPKXWGULTLS3EUPKO2JHOA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:YL73JPKXWGULTLS3EUPKO2JHOA","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":"c78484ee8ced273c7113b3c1df7d99a9b644ac9b52d1ac5b0bb456cac97a64e8","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-22T04:41:37Z","title_canon_sha256":"43b270479da20916f0b44e7321bae7be2d4aa81f85c9b42f2c5659a59f5c435f"},"schema_version":"1.0","source":{"id":"1805.08389","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.08389","created_at":"2026-05-18T00:15:26Z"},{"alias_kind":"arxiv_version","alias_value":"1805.08389v1","created_at":"2026-05-18T00:15:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08389","created_at":"2026-05-18T00:15:26Z"},{"alias_kind":"pith_short_12","alias_value":"YL73JPKXWGUL","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"YL73JPKXWGULTLS3","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"YL73JPKX","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:a12ef7a8caee41e9d735269dd85f541e1df8df278977fcecc15f0c37198cae0f","target":"graph","created_at":"2026-05-18T00:15:26Z","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":"Answering visual questions need acquire daily common knowledge and model the semantic connection among different parts in images, which is too difficult for VQA systems to learn from images with the only supervision from answers. Meanwhile, image captioning systems with beam search strategy tend to generate similar captions and fail to diversely describe images. To address the aforementioned issues, we present a system to have these two tasks compensate with each other, which is capable of jointly producing image captions and answering visual questions. In particular, we utilize question and i","authors_text":"Jialin Wu, Raymond J. Mooney, Zeyuan Hu","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-22T04:41:37Z","title":"Joint Image Captioning and Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08389","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":"sha256:0beb306da0c5bbeaf75391f32a70fa74eb2922281105e34d30dd3bfb80a20d3e","target":"record","created_at":"2026-05-18T00:15:26Z","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":"c78484ee8ced273c7113b3c1df7d99a9b644ac9b52d1ac5b0bb456cac97a64e8","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-22T04:41:37Z","title_canon_sha256":"43b270479da20916f0b44e7321bae7be2d4aa81f85c9b42f2c5659a59f5c435f"},"schema_version":"1.0","source":{"id":"1805.08389","kind":"arxiv","version":1}},"canonical_sha256":"c2ffb4bd57b1a8b9ae5b251ea7692770128cb1646f1c40df16e221f397f5b3d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c2ffb4bd57b1a8b9ae5b251ea7692770128cb1646f1c40df16e221f397f5b3d3","first_computed_at":"2026-05-18T00:15:26.680224Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:26.680224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d5Z50t7TYrNAnkAUV4bDQFLiQK+abmyKxWWIxBQnPANoMn8iN72RIbaiGJqkEXlbLf1ijlYxUGmaCe7xMUwKCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:26.681129Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.08389","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0beb306da0c5bbeaf75391f32a70fa74eb2922281105e34d30dd3bfb80a20d3e","sha256:a12ef7a8caee41e9d735269dd85f541e1df8df278977fcecc15f0c37198cae0f"],"state_sha256":"98671e27a90d7e320c2a223359c6992413d652d0d091d0cf8a857757e3ea9091"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FadjCFblRkfKYGiOXhGHS3dCBeVIUQvTAGmzMRrU94HTr/S9iPfznJbGny8g+4HbBJUnT6zzFtdeuODVRtR2Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T17:45:41.972492Z","bundle_sha256":"87454ce00bc97c3752c105fbddb73a55c232f2139cf452e55359d5606db57d0d"}}