{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:GGJAEUXJH4KF6JYV74TNWNEXUN","short_pith_number":"pith:GGJAEUXJ","canonical_record":{"source":{"id":"1803.06152","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-16T10:32:25Z","cross_cats_sorted":[],"title_canon_sha256":"315bae8b7b5e6ac2a4a363979ef3ee301388d199ac52c6a1c95755a559b4de7e","abstract_canon_sha256":"5f8026e0e7470a90d02d39ee78d01f8c87454164d5985cecdcb13d6b5de7b20b"},"schema_version":"1.0"},"canonical_sha256":"31920252e93f145f2715ff26db3497a36bf31bc5180a7a93c26f32aabb07cc8d","source":{"kind":"arxiv","id":"1803.06152","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.06152","created_at":"2026-05-18T00:20:50Z"},{"alias_kind":"arxiv_version","alias_value":"1803.06152v1","created_at":"2026-05-18T00:20:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.06152","created_at":"2026-05-18T00:20:50Z"},{"alias_kind":"pith_short_12","alias_value":"GGJAEUXJH4KF","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"GGJAEUXJH4KF6JYV","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"GGJAEUXJ","created_at":"2026-05-18T12:32:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:GGJAEUXJH4KF6JYV74TNWNEXUN","target":"record","payload":{"canonical_record":{"source":{"id":"1803.06152","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-16T10:32:25Z","cross_cats_sorted":[],"title_canon_sha256":"315bae8b7b5e6ac2a4a363979ef3ee301388d199ac52c6a1c95755a559b4de7e","abstract_canon_sha256":"5f8026e0e7470a90d02d39ee78d01f8c87454164d5985cecdcb13d6b5de7b20b"},"schema_version":"1.0"},"canonical_sha256":"31920252e93f145f2715ff26db3497a36bf31bc5180a7a93c26f32aabb07cc8d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:50.419686Z","signature_b64":"+wuQoMpg23L4cCyqxnLMBra90DT/WeqrGRnzOXchcEtNBdKWxSOx6qjEsV6cPQpeHKYOW+WcowVrkDy1sxTwCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31920252e93f145f2715ff26db3497a36bf31bc5180a7a93c26f32aabb07cc8d","last_reissued_at":"2026-05-18T00:20:50.419122Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:50.419122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.06152","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":"2026-05-18T00:20:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q8NQvGS9HBI+kLnGgbX/3vYNbVZE7QbRU1E9YiO7VhaA8npdNZA/3SBTP5PAhqr/IWx9RpA28n32MGvUUVzkCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T14:28:11.278787Z"},"content_sha256":"5412b5ef74b6b65e370d692a3e9e2a4eafe0c97de791597cc288a546585e6015","schema_version":"1.0","event_id":"sha256:5412b5ef74b6b65e370d692a3e9e2a4eafe0c97de791597cc288a546585e6015"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:GGJAEUXJH4KF6JYV74TNWNEXUN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Object Captioning and Retrieval with Natural Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anh Nguyen, Darwin G. Caldwell, Ian Reid, Nikos G. Tsagarakis, Thanh-Toan Do","submitted_at":"2018-03-16T10:32:25Z","abstract_excerpt":"We address the problem of jointly learning vision and language to understand the object in a fine-grained manner. The key idea of our approach is the use of object descriptions to provide the detailed understanding of an object. Based on this idea, we propose two new architectures to solve two related problems: object captioning and natural language-based object retrieval. The goal of the object captioning task is to simultaneously detect the object and generate its associated description, while in the object retrieval task, the goal is to localize an object given an input query. We demonstrat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.06152","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":"2026-05-18T00:20:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nNL7xOKIjsvj8xwxthv8QVU81v+nB6y7LA/c2hqZkdU3k1VKYaT1FO1ASP5iZxwsPwOQrFB9SiD9PwNuZC5aCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T14:28:11.279157Z"},"content_sha256":"de1dab7c1f9794ab7703f3e56c25a81bf4f85523049f74b5cfe2a4079dfa35d3","schema_version":"1.0","event_id":"sha256:de1dab7c1f9794ab7703f3e56c25a81bf4f85523049f74b5cfe2a4079dfa35d3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GGJAEUXJH4KF6JYV74TNWNEXUN/bundle.json","state_url":"https://pith.science/pith/GGJAEUXJH4KF6JYV74TNWNEXUN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GGJAEUXJH4KF6JYV74TNWNEXUN/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":"2026-05-31T14:28:11Z","links":{"resolver":"https://pith.science/pith/GGJAEUXJH4KF6JYV74TNWNEXUN","bundle":"https://pith.science/pith/GGJAEUXJH4KF6JYV74TNWNEXUN/bundle.json","state":"https://pith.science/pith/GGJAEUXJH4KF6JYV74TNWNEXUN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GGJAEUXJH4KF6JYV74TNWNEXUN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:GGJAEUXJH4KF6JYV74TNWNEXUN","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":"5f8026e0e7470a90d02d39ee78d01f8c87454164d5985cecdcb13d6b5de7b20b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-16T10:32:25Z","title_canon_sha256":"315bae8b7b5e6ac2a4a363979ef3ee301388d199ac52c6a1c95755a559b4de7e"},"schema_version":"1.0","source":{"id":"1803.06152","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.06152","created_at":"2026-05-18T00:20:50Z"},{"alias_kind":"arxiv_version","alias_value":"1803.06152v1","created_at":"2026-05-18T00:20:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.06152","created_at":"2026-05-18T00:20:50Z"},{"alias_kind":"pith_short_12","alias_value":"GGJAEUXJH4KF","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"GGJAEUXJH4KF6JYV","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"GGJAEUXJ","created_at":"2026-05-18T12:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:de1dab7c1f9794ab7703f3e56c25a81bf4f85523049f74b5cfe2a4079dfa35d3","target":"graph","created_at":"2026-05-18T00:20:50Z","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":"We address the problem of jointly learning vision and language to understand the object in a fine-grained manner. The key idea of our approach is the use of object descriptions to provide the detailed understanding of an object. Based on this idea, we propose two new architectures to solve two related problems: object captioning and natural language-based object retrieval. The goal of the object captioning task is to simultaneously detect the object and generate its associated description, while in the object retrieval task, the goal is to localize an object given an input query. We demonstrat","authors_text":"Anh Nguyen, Darwin G. Caldwell, Ian Reid, Nikos G. Tsagarakis, Thanh-Toan Do","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-16T10:32:25Z","title":"Object Captioning and Retrieval with Natural Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.06152","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":"sha256:5412b5ef74b6b65e370d692a3e9e2a4eafe0c97de791597cc288a546585e6015","target":"record","created_at":"2026-05-18T00:20:50Z","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":"5f8026e0e7470a90d02d39ee78d01f8c87454164d5985cecdcb13d6b5de7b20b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-16T10:32:25Z","title_canon_sha256":"315bae8b7b5e6ac2a4a363979ef3ee301388d199ac52c6a1c95755a559b4de7e"},"schema_version":"1.0","source":{"id":"1803.06152","kind":"arxiv","version":1}},"canonical_sha256":"31920252e93f145f2715ff26db3497a36bf31bc5180a7a93c26f32aabb07cc8d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31920252e93f145f2715ff26db3497a36bf31bc5180a7a93c26f32aabb07cc8d","first_computed_at":"2026-05-18T00:20:50.419122Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:20:50.419122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+wuQoMpg23L4cCyqxnLMBra90DT/WeqrGRnzOXchcEtNBdKWxSOx6qjEsV6cPQpeHKYOW+WcowVrkDy1sxTwCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:20:50.419686Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.06152","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5412b5ef74b6b65e370d692a3e9e2a4eafe0c97de791597cc288a546585e6015","sha256:de1dab7c1f9794ab7703f3e56c25a81bf4f85523049f74b5cfe2a4079dfa35d3"],"state_sha256":"1382ba74ffdb09d2900945214ebce21603427ca2fffd624b2d5a6a48d330a6e1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ajyG6v+VIGoXPgk4NPK/k/u+KrBaLMREeTZbabJDhz8zZ3yU0AhcJNd2DpS58MFgOXLELpGI6k57VYDFLeUBBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T14:28:11.281623Z","bundle_sha256":"47f7690260d651f6125b1f4d86cb5fa927cf6ed80326091f356215ebfb65f7b0"}}