{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:X6RYEI6227ZMDLDLGCU2IE35GO","short_pith_number":"pith:X6RYEI62","canonical_record":{"source":{"id":"1812.02664","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-06T17:00:16Z","cross_cats_sorted":[],"title_canon_sha256":"797cefb9bdab4651937ae5a1cfe3dece2011ea03dbf2f1951bcc034bc01247bb","abstract_canon_sha256":"1c0d978960986da97cb226536b4c1a2b5c13ec5920cee0fa6555ee318be5e9a4"},"schema_version":"1.0"},"canonical_sha256":"bfa38223dad7f2c1ac6b30a9a4137d33b63ce1f3f82b7f7f200957858bb46936","source":{"kind":"arxiv","id":"1812.02664","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.02664","created_at":"2026-05-17T23:49:16Z"},{"alias_kind":"arxiv_version","alias_value":"1812.02664v2","created_at":"2026-05-17T23:49:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.02664","created_at":"2026-05-17T23:49:16Z"},{"alias_kind":"pith_short_12","alias_value":"X6RYEI6227ZM","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"X6RYEI6227ZMDLDL","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"X6RYEI62","created_at":"2026-05-18T12:33:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:X6RYEI6227ZMDLDLGCU2IE35GO","target":"record","payload":{"canonical_record":{"source":{"id":"1812.02664","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-06T17:00:16Z","cross_cats_sorted":[],"title_canon_sha256":"797cefb9bdab4651937ae5a1cfe3dece2011ea03dbf2f1951bcc034bc01247bb","abstract_canon_sha256":"1c0d978960986da97cb226536b4c1a2b5c13ec5920cee0fa6555ee318be5e9a4"},"schema_version":"1.0"},"canonical_sha256":"bfa38223dad7f2c1ac6b30a9a4137d33b63ce1f3f82b7f7f200957858bb46936","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:16.938311Z","signature_b64":"uTl6rZ94gFfm9DaIJm3rdKM71i0rh6s2LRleBF2ucGi7BSqxur42N0lOlRzkZa86BNd9uWfjclg3Ku+EnEKfAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfa38223dad7f2c1ac6b30a9a4137d33b63ce1f3f82b7f7f200957858bb46936","last_reissued_at":"2026-05-17T23:49:16.937718Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:16.937718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.02664","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":"2026-05-17T23:49:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S3vGCSLpUtm38SWJbMPCffi6uGUsI55qtTYMk3WKtp4nJ0ZVsYNS0f79oKNOQllHy26NSVzezTORJmLMGkB7DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T03:40:16.786600Z"},"content_sha256":"be25d7fad204e146cac7a70296a47921efd9e9477478272c6b3df5167d6e4b8b","schema_version":"1.0","event_id":"sha256:be25d7fad204e146cac7a70296a47921efd9e9477478272c6b3df5167d6e4b8b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:X6RYEI6227ZMDLDLGCU2IE35GO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Recursive Visual Attention in Visual Dialog","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanwang Zhang, Jianhong Zhang, Ji-Rong Wen, Manli Zhang, Yulei Niu, Zhiwu Lu","submitted_at":"2018-12-06T17:00:16Z","abstract_excerpt":"Visual dialog is a challenging vision-language task, which requires the agent to answer multi-round questions about an image. It typically needs to address two major problems: (1) How to answer visually-grounded questions, which is the core challenge in visual question answering (VQA); (2) How to infer the co-reference between questions and the dialog history. An example of visual co-reference is: pronouns (\\eg, ``they'') in the question (\\eg, ``Are they on or off?'') are linked with nouns (\\eg, ``lamps'') appearing in the dialog history (\\eg, ``How many lamps are there?'') and the object grou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.02664","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":"2026-05-17T23:49:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v8aP+hxHD18hcGB+hEpnspmLIiEbr4ssbC+t2kTUR6biqiW/I6VGSq/D68ETtp/GPABZroKWjVTOtHPgJO5iAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T03:40:16.787264Z"},"content_sha256":"c1adc60cb5851b4cff1cf48265f4c3f5498a80fd161d89e1878690cab1ae8ee8","schema_version":"1.0","event_id":"sha256:c1adc60cb5851b4cff1cf48265f4c3f5498a80fd161d89e1878690cab1ae8ee8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X6RYEI6227ZMDLDLGCU2IE35GO/bundle.json","state_url":"https://pith.science/pith/X6RYEI6227ZMDLDLGCU2IE35GO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X6RYEI6227ZMDLDLGCU2IE35GO/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":"2026-05-26T03:40:16Z","links":{"resolver":"https://pith.science/pith/X6RYEI6227ZMDLDLGCU2IE35GO","bundle":"https://pith.science/pith/X6RYEI6227ZMDLDLGCU2IE35GO/bundle.json","state":"https://pith.science/pith/X6RYEI6227ZMDLDLGCU2IE35GO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X6RYEI6227ZMDLDLGCU2IE35GO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:X6RYEI6227ZMDLDLGCU2IE35GO","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":"1c0d978960986da97cb226536b4c1a2b5c13ec5920cee0fa6555ee318be5e9a4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-06T17:00:16Z","title_canon_sha256":"797cefb9bdab4651937ae5a1cfe3dece2011ea03dbf2f1951bcc034bc01247bb"},"schema_version":"1.0","source":{"id":"1812.02664","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.02664","created_at":"2026-05-17T23:49:16Z"},{"alias_kind":"arxiv_version","alias_value":"1812.02664v2","created_at":"2026-05-17T23:49:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.02664","created_at":"2026-05-17T23:49:16Z"},{"alias_kind":"pith_short_12","alias_value":"X6RYEI6227ZM","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"X6RYEI6227ZMDLDL","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"X6RYEI62","created_at":"2026-05-18T12:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:c1adc60cb5851b4cff1cf48265f4c3f5498a80fd161d89e1878690cab1ae8ee8","target":"graph","created_at":"2026-05-17T23:49:16Z","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 dialog is a challenging vision-language task, which requires the agent to answer multi-round questions about an image. It typically needs to address two major problems: (1) How to answer visually-grounded questions, which is the core challenge in visual question answering (VQA); (2) How to infer the co-reference between questions and the dialog history. An example of visual co-reference is: pronouns (\\eg, ``they'') in the question (\\eg, ``Are they on or off?'') are linked with nouns (\\eg, ``lamps'') appearing in the dialog history (\\eg, ``How many lamps are there?'') and the object grou","authors_text":"Hanwang Zhang, Jianhong Zhang, Ji-Rong Wen, Manli Zhang, Yulei Niu, Zhiwu Lu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-06T17:00:16Z","title":"Recursive Visual Attention in Visual Dialog"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.02664","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:be25d7fad204e146cac7a70296a47921efd9e9477478272c6b3df5167d6e4b8b","target":"record","created_at":"2026-05-17T23:49:16Z","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":"1c0d978960986da97cb226536b4c1a2b5c13ec5920cee0fa6555ee318be5e9a4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-06T17:00:16Z","title_canon_sha256":"797cefb9bdab4651937ae5a1cfe3dece2011ea03dbf2f1951bcc034bc01247bb"},"schema_version":"1.0","source":{"id":"1812.02664","kind":"arxiv","version":2}},"canonical_sha256":"bfa38223dad7f2c1ac6b30a9a4137d33b63ce1f3f82b7f7f200957858bb46936","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bfa38223dad7f2c1ac6b30a9a4137d33b63ce1f3f82b7f7f200957858bb46936","first_computed_at":"2026-05-17T23:49:16.937718Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:49:16.937718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uTl6rZ94gFfm9DaIJm3rdKM71i0rh6s2LRleBF2ucGi7BSqxur42N0lOlRzkZa86BNd9uWfjclg3Ku+EnEKfAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:49:16.938311Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.02664","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be25d7fad204e146cac7a70296a47921efd9e9477478272c6b3df5167d6e4b8b","sha256:c1adc60cb5851b4cff1cf48265f4c3f5498a80fd161d89e1878690cab1ae8ee8"],"state_sha256":"a0253e99a1ab6bd2492eb72a29811a555c1dbe36342aeccad7039981e0c88755"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SsmEmwBgTpPL7ptWTzHGJh3Bfq847vHXKelQjkO4/kJO7BorBBQ742tXjuPFHILZAUKuqSD8q+6VR9w9lGGYAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T03:40:16.790853Z","bundle_sha256":"5483b352cf9e1615f3b7c00c0805869407c3222c44ea153ca697e4e9fa79c4d0"}}