{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:RVT44RGGLX2ZUWDD47J6VRXQEX","short_pith_number":"pith:RVT44RGG","canonical_record":{"source":{"id":"1612.03557","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-12T06:52:36Z","cross_cats_sorted":[],"title_canon_sha256":"cdfe31f1b9c489233c4ef47b1507151e7b480ac812e9bac8908de4f39109e7d4","abstract_canon_sha256":"6e593531e4052816e4d9e0c1ca286b7a691a3eb001edd27b7bccc641a555ff23"},"schema_version":"1.0"},"canonical_sha256":"8d67ce44c65df59a5863e7d3eac6f025c8dab115644ea112bcb80f2582e73c26","source":{"kind":"arxiv","id":"1612.03557","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.03557","created_at":"2026-05-18T00:55:18Z"},{"alias_kind":"arxiv_version","alias_value":"1612.03557v1","created_at":"2026-05-18T00:55:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.03557","created_at":"2026-05-18T00:55:18Z"},{"alias_kind":"pith_short_12","alias_value":"RVT44RGGLX2Z","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"RVT44RGGLX2ZUWDD","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"RVT44RGG","created_at":"2026-05-18T12:30:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:RVT44RGGLX2ZUWDD47J6VRXQEX","target":"record","payload":{"canonical_record":{"source":{"id":"1612.03557","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-12T06:52:36Z","cross_cats_sorted":[],"title_canon_sha256":"cdfe31f1b9c489233c4ef47b1507151e7b480ac812e9bac8908de4f39109e7d4","abstract_canon_sha256":"6e593531e4052816e4d9e0c1ca286b7a691a3eb001edd27b7bccc641a555ff23"},"schema_version":"1.0"},"canonical_sha256":"8d67ce44c65df59a5863e7d3eac6f025c8dab115644ea112bcb80f2582e73c26","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:55:18.955381Z","signature_b64":"Q/w1yv+Ay3O00+YZShYvwIpFMPwcsk8JzAY3xhcI2q6YOJjQCBATR3cKAMSQUe2OExUCPke3DPAOJaiCgYFcAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d67ce44c65df59a5863e7d3eac6f025c8dab115644ea112bcb80f2582e73c26","last_reissued_at":"2026-05-18T00:55:18.954686Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:55:18.954686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1612.03557","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":"2026-05-18T00:55:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7R/teXYmyScNOR8rt9uBl16wrQk4o4H1J2V7rsKJA9dxjwGJNuOxOApDFh9A8dEf5BwWd8BSwb0if3YmpYBTAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:21:06.247868Z"},"content_sha256":"7056fca89db4563c666bc96a725e06ff9c5e45d79dc2ef53aedbb397adc01fa7","schema_version":"1.0","event_id":"sha256:7056fca89db4563c666bc96a725e06ff9c5e45d79dc2ef53aedbb397adc01fa7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:RVT44RGGLX2ZUWDD47J6VRXQEX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Text-guided Attention Model for Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohyung Han, Jonghwan Mun, Minsu Cho","submitted_at":"2016-12-12T06:52:36Z","abstract_excerpt":"Visual attention plays an important role to understand images and demonstrates its effectiveness in generating natural language descriptions of images. On the other hand, recent studies show that language associated with an image can steer visual attention in the scene during our cognitive process. Inspired by this, we introduce a text-guided attention model for image captioning, which learns to drive visual attention using associated captions. For this model, we propose an exemplar-based learning approach that retrieves from training data associated captions with each image, and use them to l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.03557","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":"2026-05-18T00:55:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sJSlAms/wBVgsrIvcU9sr0070wpywVziOeJKbcgqvffB43nX7UJDznvD4ZCsnL8o2ahD7fSQ7es6w2Cvw5CfAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:21:06.248219Z"},"content_sha256":"bb9f6ea63f1c5c36d773878243b3ec19e9156ecb6a8a8397c83ca5082ff78438","schema_version":"1.0","event_id":"sha256:bb9f6ea63f1c5c36d773878243b3ec19e9156ecb6a8a8397c83ca5082ff78438"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RVT44RGGLX2ZUWDD47J6VRXQEX/bundle.json","state_url":"https://pith.science/pith/RVT44RGGLX2ZUWDD47J6VRXQEX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RVT44RGGLX2ZUWDD47J6VRXQEX/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":"2026-07-06T19:21:06Z","links":{"resolver":"https://pith.science/pith/RVT44RGGLX2ZUWDD47J6VRXQEX","bundle":"https://pith.science/pith/RVT44RGGLX2ZUWDD47J6VRXQEX/bundle.json","state":"https://pith.science/pith/RVT44RGGLX2ZUWDD47J6VRXQEX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RVT44RGGLX2ZUWDD47J6VRXQEX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:RVT44RGGLX2ZUWDD47J6VRXQEX","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":"6e593531e4052816e4d9e0c1ca286b7a691a3eb001edd27b7bccc641a555ff23","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-12T06:52:36Z","title_canon_sha256":"cdfe31f1b9c489233c4ef47b1507151e7b480ac812e9bac8908de4f39109e7d4"},"schema_version":"1.0","source":{"id":"1612.03557","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.03557","created_at":"2026-05-18T00:55:18Z"},{"alias_kind":"arxiv_version","alias_value":"1612.03557v1","created_at":"2026-05-18T00:55:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.03557","created_at":"2026-05-18T00:55:18Z"},{"alias_kind":"pith_short_12","alias_value":"RVT44RGGLX2Z","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"RVT44RGGLX2ZUWDD","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"RVT44RGG","created_at":"2026-05-18T12:30:41Z"}],"graph_snapshots":[{"event_id":"sha256:bb9f6ea63f1c5c36d773878243b3ec19e9156ecb6a8a8397c83ca5082ff78438","target":"graph","created_at":"2026-05-18T00:55:18Z","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 attention plays an important role to understand images and demonstrates its effectiveness in generating natural language descriptions of images. On the other hand, recent studies show that language associated with an image can steer visual attention in the scene during our cognitive process. Inspired by this, we introduce a text-guided attention model for image captioning, which learns to drive visual attention using associated captions. For this model, we propose an exemplar-based learning approach that retrieves from training data associated captions with each image, and use them to l","authors_text":"Bohyung Han, Jonghwan Mun, Minsu Cho","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-12T06:52:36Z","title":"Text-guided Attention Model for Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.03557","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":"sha256:7056fca89db4563c666bc96a725e06ff9c5e45d79dc2ef53aedbb397adc01fa7","target":"record","created_at":"2026-05-18T00:55:18Z","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":"6e593531e4052816e4d9e0c1ca286b7a691a3eb001edd27b7bccc641a555ff23","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-12T06:52:36Z","title_canon_sha256":"cdfe31f1b9c489233c4ef47b1507151e7b480ac812e9bac8908de4f39109e7d4"},"schema_version":"1.0","source":{"id":"1612.03557","kind":"arxiv","version":1}},"canonical_sha256":"8d67ce44c65df59a5863e7d3eac6f025c8dab115644ea112bcb80f2582e73c26","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d67ce44c65df59a5863e7d3eac6f025c8dab115644ea112bcb80f2582e73c26","first_computed_at":"2026-05-18T00:55:18.954686Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:55:18.954686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q/w1yv+Ay3O00+YZShYvwIpFMPwcsk8JzAY3xhcI2q6YOJjQCBATR3cKAMSQUe2OExUCPke3DPAOJaiCgYFcAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:55:18.955381Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.03557","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7056fca89db4563c666bc96a725e06ff9c5e45d79dc2ef53aedbb397adc01fa7","sha256:bb9f6ea63f1c5c36d773878243b3ec19e9156ecb6a8a8397c83ca5082ff78438"],"state_sha256":"3a606c29703f68a6e55fbc458d50d8fd3bcfd8698e2200627a4a2918c061930f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vGJlvRncOxcYjk0nEWmd1gCOiwyN/FwGHuDyz31F3fTZDXrFMFeaIsBT5tIDWdvE0DaInMVNTHVbM5g4rAbxCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:21:06.250066Z","bundle_sha256":"2ad4f4b7c00cb31734f44f13a7ba2356a625d707f55426a82da66ec016e9f42a"}}