{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:PHE45N55NK7FR5T7XECBIEOE63","short_pith_number":"pith:PHE45N55","canonical_record":{"source":{"id":"1904.00767","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-18T15:59:44Z","cross_cats_sorted":[],"title_canon_sha256":"fae8d6b50c09b22ea52fdd1e595b5325b31bc08ecbb57da7b055e49660005f0c","abstract_canon_sha256":"86f6eab4ae3c03524f43d52e95fea3a0b8ce6fd094943e8f39f4524c11073fe5"},"schema_version":"1.0"},"canonical_sha256":"79c9ceb7bd6abe58f67fb9041411c4f6fd881dbe5403a1a3b49d6fb669b64ae9","source":{"kind":"arxiv","id":"1904.00767","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.00767","created_at":"2026-05-17T23:49:45Z"},{"alias_kind":"arxiv_version","alias_value":"1904.00767v1","created_at":"2026-05-17T23:49:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.00767","created_at":"2026-05-17T23:49:45Z"},{"alias_kind":"pith_short_12","alias_value":"PHE45N55NK7F","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"PHE45N55NK7FR5T7","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"PHE45N55","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:PHE45N55NK7FR5T7XECBIEOE63","target":"record","payload":{"canonical_record":{"source":{"id":"1904.00767","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-18T15:59:44Z","cross_cats_sorted":[],"title_canon_sha256":"fae8d6b50c09b22ea52fdd1e595b5325b31bc08ecbb57da7b055e49660005f0c","abstract_canon_sha256":"86f6eab4ae3c03524f43d52e95fea3a0b8ce6fd094943e8f39f4524c11073fe5"},"schema_version":"1.0"},"canonical_sha256":"79c9ceb7bd6abe58f67fb9041411c4f6fd881dbe5403a1a3b49d6fb669b64ae9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:45.513491Z","signature_b64":"r3P9qVgdk+lDae9j/uXnxPxlJ5dr08gKWPEXJRrNdNaHBAh+0pcoJ0UHshJEFuprR5ERsbFIZEuE7exEbVGyBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79c9ceb7bd6abe58f67fb9041411c4f6fd881dbe5403a1a3b49d6fb669b64ae9","last_reissued_at":"2026-05-17T23:49:45.512598Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:45.512598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.00767","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":"2026-05-17T23:49:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TrY+amqMx+cds00AdLl3F53JXwrEQTK5QFxSo1Ns0fTtu7NdiUjXSEesPs5j0T1fB8ACF5wQNdM+g1A5ZioKDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T04:47:32.593388Z"},"content_sha256":"8d77cf0591641ef1fa6543a179486ab717a11cc245cf16e8f596ff0e39a5bc31","schema_version":"1.0","event_id":"sha256:8d77cf0591641ef1fa6543a179486ab717a11cc245cf16e8f596ff0e39a5bc31"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:PHE45N55NK7FR5T7XECBIEOE63","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Boosted Attention: Leveraging Human Attention for Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qi Zhao, Shi Chen","submitted_at":"2019-03-18T15:59:44Z","abstract_excerpt":"Visual attention has shown usefulness in image captioning, with the goal of enabling a caption model to selectively focus on regions of interest. Existing models typically rely on top-down language information and learn attention implicitly by optimizing the captioning objectives. While somewhat effective, the learned top-down attention can fail to focus on correct regions of interest without direct supervision of attention. Inspired by the human visual system which is driven by not only the task-specific top-down signals but also the visual stimuli, we in this work propose to use both types o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.00767","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":"2026-05-17T23:49:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A2OhhtWR+MZwSJ12h1DVbyytzy3ZnQQuUkYe36xJgNOHY26uKvADwmxkSH6IEOEAu0pi1LhiKZpLF6zHnhPzDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T04:47:32.593745Z"},"content_sha256":"2723b7a3a45a83f036fd3a8aaaec56c3c35a1755f7f71bb11476b48ae49f811b","schema_version":"1.0","event_id":"sha256:2723b7a3a45a83f036fd3a8aaaec56c3c35a1755f7f71bb11476b48ae49f811b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PHE45N55NK7FR5T7XECBIEOE63/bundle.json","state_url":"https://pith.science/pith/PHE45N55NK7FR5T7XECBIEOE63/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PHE45N55NK7FR5T7XECBIEOE63/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":"2026-06-04T04:47:32Z","links":{"resolver":"https://pith.science/pith/PHE45N55NK7FR5T7XECBIEOE63","bundle":"https://pith.science/pith/PHE45N55NK7FR5T7XECBIEOE63/bundle.json","state":"https://pith.science/pith/PHE45N55NK7FR5T7XECBIEOE63/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PHE45N55NK7FR5T7XECBIEOE63/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:PHE45N55NK7FR5T7XECBIEOE63","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":"86f6eab4ae3c03524f43d52e95fea3a0b8ce6fd094943e8f39f4524c11073fe5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-18T15:59:44Z","title_canon_sha256":"fae8d6b50c09b22ea52fdd1e595b5325b31bc08ecbb57da7b055e49660005f0c"},"schema_version":"1.0","source":{"id":"1904.00767","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.00767","created_at":"2026-05-17T23:49:45Z"},{"alias_kind":"arxiv_version","alias_value":"1904.00767v1","created_at":"2026-05-17T23:49:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.00767","created_at":"2026-05-17T23:49:45Z"},{"alias_kind":"pith_short_12","alias_value":"PHE45N55NK7F","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"PHE45N55NK7FR5T7","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"PHE45N55","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:2723b7a3a45a83f036fd3a8aaaec56c3c35a1755f7f71bb11476b48ae49f811b","target":"graph","created_at":"2026-05-17T23:49:45Z","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":"Visual attention has shown usefulness in image captioning, with the goal of enabling a caption model to selectively focus on regions of interest. Existing models typically rely on top-down language information and learn attention implicitly by optimizing the captioning objectives. While somewhat effective, the learned top-down attention can fail to focus on correct regions of interest without direct supervision of attention. Inspired by the human visual system which is driven by not only the task-specific top-down signals but also the visual stimuli, we in this work propose to use both types o","authors_text":"Qi Zhao, Shi Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-18T15:59:44Z","title":"Boosted Attention: Leveraging Human Attention for Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.00767","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":"sha256:8d77cf0591641ef1fa6543a179486ab717a11cc245cf16e8f596ff0e39a5bc31","target":"record","created_at":"2026-05-17T23:49:45Z","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":"86f6eab4ae3c03524f43d52e95fea3a0b8ce6fd094943e8f39f4524c11073fe5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-18T15:59:44Z","title_canon_sha256":"fae8d6b50c09b22ea52fdd1e595b5325b31bc08ecbb57da7b055e49660005f0c"},"schema_version":"1.0","source":{"id":"1904.00767","kind":"arxiv","version":1}},"canonical_sha256":"79c9ceb7bd6abe58f67fb9041411c4f6fd881dbe5403a1a3b49d6fb669b64ae9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"79c9ceb7bd6abe58f67fb9041411c4f6fd881dbe5403a1a3b49d6fb669b64ae9","first_computed_at":"2026-05-17T23:49:45.512598Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:49:45.512598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r3P9qVgdk+lDae9j/uXnxPxlJ5dr08gKWPEXJRrNdNaHBAh+0pcoJ0UHshJEFuprR5ERsbFIZEuE7exEbVGyBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:49:45.513491Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.00767","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d77cf0591641ef1fa6543a179486ab717a11cc245cf16e8f596ff0e39a5bc31","sha256:2723b7a3a45a83f036fd3a8aaaec56c3c35a1755f7f71bb11476b48ae49f811b"],"state_sha256":"32527f62504d0937150feba91503e3b71204347be9e9289e2a94ac7bec86c8dd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C8aZVv/M2hUg1R1R2tAwcKE3gmo2w9L7l9OiARe1FHlSdfz7u4kb5RsI+n+2ZtKGRxhVoJiVBs0gLWxVALuBAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T04:47:32.595740Z","bundle_sha256":"3c46eb077254047a6ea3cfb2929a24ebd7d2ac117e929949614bd53ffbbbbd08"}}