{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:DADAHXMWDHGZ3UYQKO7TOOSUHO","short_pith_number":"pith:DADAHXMW","schema_version":"1.0","canonical_sha256":"180603dd9619cd9dd31053bf373a543b800737f05f013fce9a95c0edae1a4e28","source":{"kind":"arxiv","id":"1410.1090","version":1},"attestation_state":"computed","paper":{"title":"Explain Images with Multimodal Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alan L. Yuille, Jiang Wang, Junhua Mao, Wei Xu, Yi Yang","submitted_at":"2014-10-04T20:24:34Z","abstract_excerpt":"In this paper, we present a multimodal Recurrent Neural Network (m-RNN) model for generating novel sentence descriptions to explain the content of images. It directly models the probability distribution of generating a word given previous words and the image. Image descriptions are generated by sampling from this distribution. The model consists of two sub-networks: a deep recurrent neural network for sentences and a deep convolutional network for images. These two sub-networks interact with each other in a multimodal layer to form the whole m-RNN model. The effectiveness of our model is valid"},"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":"1410.1090","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-10-04T20:24:34Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"8ba28afb5483680953bb74812e89542769a488519461a076a4f0ce494bdd8805","abstract_canon_sha256":"8c412975aaa4afea484e86c9e670f77e9f12e89bbba34c06d52fcc8d033bc184"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:41:02.796568Z","signature_b64":"m0h4lnbvUiji2S+gLv82jnODWnG1moRvZDncg6GJRYw4a74mu1MpESPBPYR/bvVOJUoegEbqUQVeDsBfAoeXAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"180603dd9619cd9dd31053bf373a543b800737f05f013fce9a95c0edae1a4e28","last_reissued_at":"2026-05-18T02:41:02.796018Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:41:02.796018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explain Images with Multimodal Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alan L. Yuille, Jiang Wang, Junhua Mao, Wei Xu, Yi Yang","submitted_at":"2014-10-04T20:24:34Z","abstract_excerpt":"In this paper, we present a multimodal Recurrent Neural Network (m-RNN) model for generating novel sentence descriptions to explain the content of images. It directly models the probability distribution of generating a word given previous words and the image. Image descriptions are generated by sampling from this distribution. The model consists of two sub-networks: a deep recurrent neural network for sentences and a deep convolutional network for images. These two sub-networks interact with each other in a multimodal layer to form the whole m-RNN model. The effectiveness of our model is valid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1410.1090","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1410.1090","created_at":"2026-05-18T02:41:02.796098+00:00"},{"alias_kind":"arxiv_version","alias_value":"1410.1090v1","created_at":"2026-05-18T02:41:02.796098+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1410.1090","created_at":"2026-05-18T02:41:02.796098+00:00"},{"alias_kind":"pith_short_12","alias_value":"DADAHXMWDHGZ","created_at":"2026-05-18T12:28:25.294606+00:00"},{"alias_kind":"pith_short_16","alias_value":"DADAHXMWDHGZ3UYQ","created_at":"2026-05-18T12:28:25.294606+00:00"},{"alias_kind":"pith_short_8","alias_value":"DADAHXMW","created_at":"2026-05-18T12:28:25.294606+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1504.00325","citing_title":"Microsoft COCO Captions: Data Collection and Evaluation Server","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DADAHXMWDHGZ3UYQKO7TOOSUHO","json":"https://pith.science/pith/DADAHXMWDHGZ3UYQKO7TOOSUHO.json","graph_json":"https://pith.science/api/pith-number/DADAHXMWDHGZ3UYQKO7TOOSUHO/graph.json","events_json":"https://pith.science/api/pith-number/DADAHXMWDHGZ3UYQKO7TOOSUHO/events.json","paper":"https://pith.science/paper/DADAHXMW"},"agent_actions":{"view_html":"https://pith.science/pith/DADAHXMWDHGZ3UYQKO7TOOSUHO","download_json":"https://pith.science/pith/DADAHXMWDHGZ3UYQKO7TOOSUHO.json","view_paper":"https://pith.science/paper/DADAHXMW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1410.1090&json=true","fetch_graph":"https://pith.science/api/pith-number/DADAHXMWDHGZ3UYQKO7TOOSUHO/graph.json","fetch_events":"https://pith.science/api/pith-number/DADAHXMWDHGZ3UYQKO7TOOSUHO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DADAHXMWDHGZ3UYQKO7TOOSUHO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DADAHXMWDHGZ3UYQKO7TOOSUHO/action/storage_attestation","attest_author":"https://pith.science/pith/DADAHXMWDHGZ3UYQKO7TOOSUHO/action/author_attestation","sign_citation":"https://pith.science/pith/DADAHXMWDHGZ3UYQKO7TOOSUHO/action/citation_signature","submit_replication":"https://pith.science/pith/DADAHXMWDHGZ3UYQKO7TOOSUHO/action/replication_record"}},"created_at":"2026-05-18T02:41:02.796098+00:00","updated_at":"2026-05-18T02:41:02.796098+00:00"}