{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:HZ6RLZT32HQUYASZFPIPMJDFZM","short_pith_number":"pith:HZ6RLZT3","schema_version":"1.0","canonical_sha256":"3e7d15e67bd1e14c02592bd0f62465cb37c98eb1aeaa8d5bcc57e76857fdb33f","source":{"kind":"arxiv","id":"1804.07889","version":2},"attestation_state":"computed","paper":{"title":"Entity-aware Image Caption Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Di Lu, Heng Ji, Lifu Huang, Shih-Fu Chang, Spencer Whitehead","submitted_at":"2018-04-21T04:40:10Z","abstract_excerpt":"Current image captioning approaches generate descriptions which lack specific information, such as named entities that are involved in the images. In this paper we propose a new task which aims to generate informative image captions, given images and hashtags as input. We propose a simple but effective approach to tackle this problem. We first train a convolutional neural networks - long short term memory networks (CNN-LSTM) model to generate a template caption based on the input image. Then we use a knowledge graph based collective inference algorithm to fill in the template with specific nam"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1804.07889","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-21T04:40:10Z","cross_cats_sorted":[],"title_canon_sha256":"82e8278794c5239e4486042ee9908160a1e05a69945f02e3993cb70c3ddd9470","abstract_canon_sha256":"07faa72cb42b68c847150dc16da0e88f066b4906506d862cf3a0f6894b28ae51"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:23.387574Z","signature_b64":"lQ85INXrgR9rcVCOC7O8jseuBIHU++X65QM/2ZRTcpga+spSFinRZnIxR2Iqv6caUp3VkIDnOB0soHu/wvxdAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e7d15e67bd1e14c02592bd0f62465cb37c98eb1aeaa8d5bcc57e76857fdb33f","last_reissued_at":"2026-05-18T00:01:23.387097Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:23.387097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Entity-aware Image Caption Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Di Lu, Heng Ji, Lifu Huang, Shih-Fu Chang, Spencer Whitehead","submitted_at":"2018-04-21T04:40:10Z","abstract_excerpt":"Current image captioning approaches generate descriptions which lack specific information, such as named entities that are involved in the images. In this paper we propose a new task which aims to generate informative image captions, given images and hashtags as input. We propose a simple but effective approach to tackle this problem. We first train a convolutional neural networks - long short term memory networks (CNN-LSTM) model to generate a template caption based on the input image. Then we use a knowledge graph based collective inference algorithm to fill in the template with specific nam"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.07889","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1804.07889","created_at":"2026-05-18T00:01:23.387164+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.07889v2","created_at":"2026-05-18T00:01:23.387164+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.07889","created_at":"2026-05-18T00:01:23.387164+00:00"},{"alias_kind":"pith_short_12","alias_value":"HZ6RLZT32HQU","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_16","alias_value":"HZ6RLZT32HQUYASZ","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_8","alias_value":"HZ6RLZT3","created_at":"2026-05-18T12:32:28.185984+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.08876","citing_title":"Informative Image Captioning with External Sources of Information","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HZ6RLZT32HQUYASZFPIPMJDFZM","json":"https://pith.science/pith/HZ6RLZT32HQUYASZFPIPMJDFZM.json","graph_json":"https://pith.science/api/pith-number/HZ6RLZT32HQUYASZFPIPMJDFZM/graph.json","events_json":"https://pith.science/api/pith-number/HZ6RLZT32HQUYASZFPIPMJDFZM/events.json","paper":"https://pith.science/paper/HZ6RLZT3"},"agent_actions":{"view_html":"https://pith.science/pith/HZ6RLZT32HQUYASZFPIPMJDFZM","download_json":"https://pith.science/pith/HZ6RLZT32HQUYASZFPIPMJDFZM.json","view_paper":"https://pith.science/paper/HZ6RLZT3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.07889&json=true","fetch_graph":"https://pith.science/api/pith-number/HZ6RLZT32HQUYASZFPIPMJDFZM/graph.json","fetch_events":"https://pith.science/api/pith-number/HZ6RLZT32HQUYASZFPIPMJDFZM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HZ6RLZT32HQUYASZFPIPMJDFZM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HZ6RLZT32HQUYASZFPIPMJDFZM/action/storage_attestation","attest_author":"https://pith.science/pith/HZ6RLZT32HQUYASZFPIPMJDFZM/action/author_attestation","sign_citation":"https://pith.science/pith/HZ6RLZT32HQUYASZFPIPMJDFZM/action/citation_signature","submit_replication":"https://pith.science/pith/HZ6RLZT32HQUYASZFPIPMJDFZM/action/replication_record"}},"created_at":"2026-05-18T00:01:23.387164+00:00","updated_at":"2026-05-18T00:01:23.387164+00:00"}