{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:CKKRCHCTOAIVZMDERZOHWPW6LX","short_pith_number":"pith:CKKRCHCT","schema_version":"1.0","canonical_sha256":"1295111c5370115cb0648e5c7b3ede5deda10c7ced4ffd4c2dc03ced73181775","source":{"kind":"arxiv","id":"1411.4555","version":2},"attestation_state":"computed","paper":{"title":"Show and Tell: A Neural Image Caption Generator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Toshev, Dumitru Erhan, Oriol Vinyals, Samy Bengio","submitted_at":"2014-11-17T17:15:41Z","abstract_excerpt":"Automatically describing the content of an image is a fundamental problem in artificial intelligence that connects computer vision and natural language processing. In this paper, we present a generative model based on a deep recurrent architecture that combines recent advances in computer vision and machine translation and that can be used to generate natural sentences describing an image. The model is trained to maximize the likelihood of the target description sentence given the training image. Experiments on several datasets show the accuracy of the model and the fluency of the language it "},"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":"1411.4555","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-11-17T17:15:41Z","cross_cats_sorted":[],"title_canon_sha256":"a6742de2dd4413059a9489d943f4d76e837f56cf27a3351e12c4a09e9a87befa","abstract_canon_sha256":"cd25a28ebd021b234503984a42c9869b7af00e0996315c84d8a4ad89144dc860"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:18:21.726576Z","signature_b64":"Sct80XhCzcse1tiBXDZg+j6rsi9kL8b4ZG6/bvaFfv2+GwJ1c6kiK9SDHPO/Mr7Jh1CDADejtCQeSaAtEt66Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1295111c5370115cb0648e5c7b3ede5deda10c7ced4ffd4c2dc03ced73181775","last_reissued_at":"2026-05-18T02:18:21.725938Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:18:21.725938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Show and Tell: A Neural Image Caption Generator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Toshev, Dumitru Erhan, Oriol Vinyals, Samy Bengio","submitted_at":"2014-11-17T17:15:41Z","abstract_excerpt":"Automatically describing the content of an image is a fundamental problem in artificial intelligence that connects computer vision and natural language processing. In this paper, we present a generative model based on a deep recurrent architecture that combines recent advances in computer vision and machine translation and that can be used to generate natural sentences describing an image. The model is trained to maximize the likelihood of the target description sentence given the training image. Experiments on several datasets show the accuracy of the model and the fluency of the language it "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1411.4555","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":"1411.4555","created_at":"2026-05-18T02:18:21.726028+00:00"},{"alias_kind":"arxiv_version","alias_value":"1411.4555v2","created_at":"2026-05-18T02:18:21.726028+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1411.4555","created_at":"2026-05-18T02:18:21.726028+00:00"},{"alias_kind":"pith_short_12","alias_value":"CKKRCHCTOAIV","created_at":"2026-05-18T12:28:22.404517+00:00"},{"alias_kind":"pith_short_16","alias_value":"CKKRCHCTOAIVZMDE","created_at":"2026-05-18T12:28:22.404517+00:00"},{"alias_kind":"pith_short_8","alias_value":"CKKRCHCT","created_at":"2026-05-18T12:28:22.404517+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1907.09085","citing_title":"Automatic Radiology Report Generation based on Multi-view Image Fusion and Medical Concept Enrichment","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2201.03546","citing_title":"Language-driven Semantic Segmentation","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"1504.00325","citing_title":"Microsoft COCO Captions: Data Collection and Evaluation Server","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02202","citing_title":"CBV: Clean-label Backdoor Attacks on Vision Language Models via Diffusion Models","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CKKRCHCTOAIVZMDERZOHWPW6LX","json":"https://pith.science/pith/CKKRCHCTOAIVZMDERZOHWPW6LX.json","graph_json":"https://pith.science/api/pith-number/CKKRCHCTOAIVZMDERZOHWPW6LX/graph.json","events_json":"https://pith.science/api/pith-number/CKKRCHCTOAIVZMDERZOHWPW6LX/events.json","paper":"https://pith.science/paper/CKKRCHCT"},"agent_actions":{"view_html":"https://pith.science/pith/CKKRCHCTOAIVZMDERZOHWPW6LX","download_json":"https://pith.science/pith/CKKRCHCTOAIVZMDERZOHWPW6LX.json","view_paper":"https://pith.science/paper/CKKRCHCT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1411.4555&json=true","fetch_graph":"https://pith.science/api/pith-number/CKKRCHCTOAIVZMDERZOHWPW6LX/graph.json","fetch_events":"https://pith.science/api/pith-number/CKKRCHCTOAIVZMDERZOHWPW6LX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CKKRCHCTOAIVZMDERZOHWPW6LX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CKKRCHCTOAIVZMDERZOHWPW6LX/action/storage_attestation","attest_author":"https://pith.science/pith/CKKRCHCTOAIVZMDERZOHWPW6LX/action/author_attestation","sign_citation":"https://pith.science/pith/CKKRCHCTOAIVZMDERZOHWPW6LX/action/citation_signature","submit_replication":"https://pith.science/pith/CKKRCHCTOAIVZMDERZOHWPW6LX/action/replication_record"}},"created_at":"2026-05-18T02:18:21.726028+00:00","updated_at":"2026-05-18T02:18:21.726028+00:00"}