{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:XLGTUPN57H357SAZB3QENMMI6X","short_pith_number":"pith:XLGTUPN5","canonical_record":{"source":{"id":"1706.02430","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-08T02:23:33Z","cross_cats_sorted":[],"title_canon_sha256":"f1894f9a0130b083bb466cc9082dd2f89b02cbc2831868bbd4ca5d00bf1950d8","abstract_canon_sha256":"0b33b1494cee88e1fb5c25119b8a97c0c205259e962a65d54151965a851ad081"},"schema_version":"1.0"},"canonical_sha256":"bacd3a3dbdf9f7dfc8190ee046b188f5d213688b5672d760061ea9a3c9192f65","source":{"kind":"arxiv","id":"1706.02430","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.02430","created_at":"2026-05-18T00:42:45Z"},{"alias_kind":"arxiv_version","alias_value":"1706.02430v1","created_at":"2026-05-18T00:42:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.02430","created_at":"2026-05-18T00:42:45Z"},{"alias_kind":"pith_short_12","alias_value":"XLGTUPN57H35","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_16","alias_value":"XLGTUPN57H357SAZ","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_8","alias_value":"XLGTUPN5","created_at":"2026-05-18T12:31:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:XLGTUPN57H357SAZB3QENMMI6X","target":"record","payload":{"canonical_record":{"source":{"id":"1706.02430","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-08T02:23:33Z","cross_cats_sorted":[],"title_canon_sha256":"f1894f9a0130b083bb466cc9082dd2f89b02cbc2831868bbd4ca5d00bf1950d8","abstract_canon_sha256":"0b33b1494cee88e1fb5c25119b8a97c0c205259e962a65d54151965a851ad081"},"schema_version":"1.0"},"canonical_sha256":"bacd3a3dbdf9f7dfc8190ee046b188f5d213688b5672d760061ea9a3c9192f65","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:45.477220Z","signature_b64":"ihyDXIaY3IPHIEasDGnFSX3phij+vGo+GCse3vDUJPmSYeazaEzp85xhiweThlrw8dq+YiL2khAQOKCdNGjXBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bacd3a3dbdf9f7dfc8190ee046b188f5d213688b5672d760061ea9a3c9192f65","last_reissued_at":"2026-05-18T00:42:45.476732Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:45.476732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1706.02430","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":"2026-05-18T00:42:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VEc2K6E3b7A18GcDz28D7bHkk58GXpdoXoao1tK+kuVwHZVCVnWSL4w3qdEvlxhIz3xMq9wfKMZYZ58EWLA1CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T09:07:15.141247Z"},"content_sha256":"1aa52d5569ca295fc92d08d34b403d0256cffd071aecbd2a7116229c6072742c","schema_version":"1.0","event_id":"sha256:1aa52d5569ca295fc92d08d34b403d0256cffd071aecbd2a7116229c6072742c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:XLGTUPN57H357SAZB3QENMMI6X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Image Captioning with Object Detection and Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Sadaqat Ur Rehman, Yongfeng Huang, Yu-Jin Zhang, Zhongliang Yang","submitted_at":"2017-06-08T02:23:33Z","abstract_excerpt":"Automatically generating a natural language description of an image is a task close to the heart of image understanding. In this paper, we present a multi-model neural network method closely related to the human visual system that automatically learns to describe the content of images. Our model consists of two sub-models: an object detection and localization model, which extract the information of objects and their spatial relationship in images respectively; Besides, a deep recurrent neural network (RNN) based on long short-term memory (LSTM) units with attention mechanism for sentences gene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.02430","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":"2026-05-18T00:42:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S/FFV3cprat6bJAtIJSEWarFj0vnUIydQzAPPYc4t7u9pBUiMvWkOYnw5ek/yjOFvVQl82t0KOmwDGUuel/nDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T09:07:15.141637Z"},"content_sha256":"06f7d5e032a22e92af8033cd61d821a117ced9868f9b5bc86d5a84cc14e223f7","schema_version":"1.0","event_id":"sha256:06f7d5e032a22e92af8033cd61d821a117ced9868f9b5bc86d5a84cc14e223f7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XLGTUPN57H357SAZB3QENMMI6X/bundle.json","state_url":"https://pith.science/pith/XLGTUPN57H357SAZB3QENMMI6X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XLGTUPN57H357SAZB3QENMMI6X/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":"2026-06-07T09:07:15Z","links":{"resolver":"https://pith.science/pith/XLGTUPN57H357SAZB3QENMMI6X","bundle":"https://pith.science/pith/XLGTUPN57H357SAZB3QENMMI6X/bundle.json","state":"https://pith.science/pith/XLGTUPN57H357SAZB3QENMMI6X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XLGTUPN57H357SAZB3QENMMI6X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:XLGTUPN57H357SAZB3QENMMI6X","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":"0b33b1494cee88e1fb5c25119b8a97c0c205259e962a65d54151965a851ad081","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-08T02:23:33Z","title_canon_sha256":"f1894f9a0130b083bb466cc9082dd2f89b02cbc2831868bbd4ca5d00bf1950d8"},"schema_version":"1.0","source":{"id":"1706.02430","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.02430","created_at":"2026-05-18T00:42:45Z"},{"alias_kind":"arxiv_version","alias_value":"1706.02430v1","created_at":"2026-05-18T00:42:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.02430","created_at":"2026-05-18T00:42:45Z"},{"alias_kind":"pith_short_12","alias_value":"XLGTUPN57H35","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_16","alias_value":"XLGTUPN57H357SAZ","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_8","alias_value":"XLGTUPN5","created_at":"2026-05-18T12:31:56Z"}],"graph_snapshots":[{"event_id":"sha256:06f7d5e032a22e92af8033cd61d821a117ced9868f9b5bc86d5a84cc14e223f7","target":"graph","created_at":"2026-05-18T00:42:45Z","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":"Automatically generating a natural language description of an image is a task close to the heart of image understanding. In this paper, we present a multi-model neural network method closely related to the human visual system that automatically learns to describe the content of images. Our model consists of two sub-models: an object detection and localization model, which extract the information of objects and their spatial relationship in images respectively; Besides, a deep recurrent neural network (RNN) based on long short-term memory (LSTM) units with attention mechanism for sentences gene","authors_text":"Sadaqat Ur Rehman, Yongfeng Huang, Yu-Jin Zhang, Zhongliang Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-08T02:23:33Z","title":"Image Captioning with Object Detection and Localization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.02430","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":"sha256:1aa52d5569ca295fc92d08d34b403d0256cffd071aecbd2a7116229c6072742c","target":"record","created_at":"2026-05-18T00:42:45Z","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":"0b33b1494cee88e1fb5c25119b8a97c0c205259e962a65d54151965a851ad081","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-06-08T02:23:33Z","title_canon_sha256":"f1894f9a0130b083bb466cc9082dd2f89b02cbc2831868bbd4ca5d00bf1950d8"},"schema_version":"1.0","source":{"id":"1706.02430","kind":"arxiv","version":1}},"canonical_sha256":"bacd3a3dbdf9f7dfc8190ee046b188f5d213688b5672d760061ea9a3c9192f65","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bacd3a3dbdf9f7dfc8190ee046b188f5d213688b5672d760061ea9a3c9192f65","first_computed_at":"2026-05-18T00:42:45.476732Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:42:45.476732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ihyDXIaY3IPHIEasDGnFSX3phij+vGo+GCse3vDUJPmSYeazaEzp85xhiweThlrw8dq+YiL2khAQOKCdNGjXBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:42:45.477220Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.02430","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1aa52d5569ca295fc92d08d34b403d0256cffd071aecbd2a7116229c6072742c","sha256:06f7d5e032a22e92af8033cd61d821a117ced9868f9b5bc86d5a84cc14e223f7"],"state_sha256":"d7cdf39b415f54679740919ca9076e222434e97cef9a6344ea0c4a84d441445e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"REjBicosBbWDlYvwnL8HotDlx+0W3Yf6vQwA7TIr5SHaZEPH4dAonFCbDslwUqZhaw6vu+cwEJhGLBZQqcSnDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T09:07:15.143657Z","bundle_sha256":"1b9c71eac83a5ecc845a7207114eb4816b3adcbfe57c6f081088c69a1049295d"}}