{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:655ERAI43W4NCXEYW6NIKWCQMQ","short_pith_number":"pith:655ERAI4","schema_version":"1.0","canonical_sha256":"f77a48811cddb8d15c98b79a8558506421f2c29bebb86e5580ad1ae053df6bcd","source":{"kind":"arxiv","id":"1411.2539","version":1},"attestation_state":"computed","paper":{"title":"Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Richard S. Zemel, Ruslan Salakhutdinov, Ryan Kiros","submitted_at":"2014-11-10T19:09:41Z","abstract_excerpt":"Inspired by recent advances in multimodal learning and machine translation, we introduce an encoder-decoder pipeline that learns (a): a multimodal joint embedding space with images and text and (b): a novel language model for decoding distributed representations from our space. Our pipeline effectively unifies joint image-text embedding models with multimodal neural language models. We introduce the structure-content neural language model that disentangles the structure of a sentence to its content, conditioned on representations produced by the encoder. The encoder allows one to rank images a"},"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":"1411.2539","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-11-10T19:09:41Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"7173d9662dd2857c3423a09ae2f70aa5017ffb06554fbf188bdec070fb09bfe7","abstract_canon_sha256":"05f8dec0c5ba01aa6d905cadd1f0b0db24e9ea4becf01d28e4d3fe67e893dcd3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:38:01.191631Z","signature_b64":"mEUldZxoMdKpBv+F+U9ArRs1qTvskzhXaplsezLwgUysoA+t3Hc5yMq/gkPmjNu/MxuVlCv5rgQ286F4Xay+AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f77a48811cddb8d15c98b79a8558506421f2c29bebb86e5580ad1ae053df6bcd","last_reissued_at":"2026-05-18T02:38:01.191124Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:38:01.191124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Richard S. Zemel, Ruslan Salakhutdinov, Ryan Kiros","submitted_at":"2014-11-10T19:09:41Z","abstract_excerpt":"Inspired by recent advances in multimodal learning and machine translation, we introduce an encoder-decoder pipeline that learns (a): a multimodal joint embedding space with images and text and (b): a novel language model for decoding distributed representations from our space. Our pipeline effectively unifies joint image-text embedding models with multimodal neural language models. We introduce the structure-content neural language model that disentangles the structure of a sentence to its content, conditioned on representations produced by the encoder. The encoder allows one to rank images a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1411.2539","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":"1411.2539","created_at":"2026-05-18T02:38:01.191205+00:00"},{"alias_kind":"arxiv_version","alias_value":"1411.2539v1","created_at":"2026-05-18T02:38:01.191205+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1411.2539","created_at":"2026-05-18T02:38:01.191205+00:00"},{"alias_kind":"pith_short_12","alias_value":"655ERAI43W4N","created_at":"2026-05-18T12:28:16.859392+00:00"},{"alias_kind":"pith_short_16","alias_value":"655ERAI43W4NCXEY","created_at":"2026-05-18T12:28:16.859392+00:00"},{"alias_kind":"pith_short_8","alias_value":"655ERAI4","created_at":"2026-05-18T12:28:16.859392+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":7,"sample":[{"citing_arxiv_id":"1906.10996","citing_title":"Learning Soft-Attention Models for Tempo-invariant Audio-Sheet Music Retrieval","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20838","citing_title":"USV: Towards Understanding the User-generated Short-form Videos","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2505.20291","citing_title":"VisRet: Visualization Improves Knowledge-Intensive Text-to-Image Retrieval","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2511.06452","citing_title":"MULTIBENCH++: A Unified and Comprehensive Multimodal Fusion Benchmarking Across Specialized Domains","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"1910.07467","citing_title":"Root Mean Square Layer Normalization","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2309.16671","citing_title":"Demystifying CLIP Data","ref_index":139,"is_internal_anchor":true},{"citing_arxiv_id":"1908.03557","citing_title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","ref_index":83,"is_internal_anchor":true},{"citing_arxiv_id":"1504.00325","citing_title":"Microsoft COCO Captions: Data Collection and Evaluation Server","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23950","citing_title":"LearnPruner: Rethinking Attention-based Token Pruning in Vision Language Models","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15628","citing_title":"SIMMER: Cross-Modal Food Image--Recipe Retrieval via MLLM-Based Embedding","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/655ERAI43W4NCXEYW6NIKWCQMQ","json":"https://pith.science/pith/655ERAI43W4NCXEYW6NIKWCQMQ.json","graph_json":"https://pith.science/api/pith-number/655ERAI43W4NCXEYW6NIKWCQMQ/graph.json","events_json":"https://pith.science/api/pith-number/655ERAI43W4NCXEYW6NIKWCQMQ/events.json","paper":"https://pith.science/paper/655ERAI4"},"agent_actions":{"view_html":"https://pith.science/pith/655ERAI43W4NCXEYW6NIKWCQMQ","download_json":"https://pith.science/pith/655ERAI43W4NCXEYW6NIKWCQMQ.json","view_paper":"https://pith.science/paper/655ERAI4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1411.2539&json=true","fetch_graph":"https://pith.science/api/pith-number/655ERAI43W4NCXEYW6NIKWCQMQ/graph.json","fetch_events":"https://pith.science/api/pith-number/655ERAI43W4NCXEYW6NIKWCQMQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/655ERAI43W4NCXEYW6NIKWCQMQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/655ERAI43W4NCXEYW6NIKWCQMQ/action/storage_attestation","attest_author":"https://pith.science/pith/655ERAI43W4NCXEYW6NIKWCQMQ/action/author_attestation","sign_citation":"https://pith.science/pith/655ERAI43W4NCXEYW6NIKWCQMQ/action/citation_signature","submit_replication":"https://pith.science/pith/655ERAI43W4NCXEYW6NIKWCQMQ/action/replication_record"}},"created_at":"2026-05-18T02:38:01.191205+00:00","updated_at":"2026-05-18T02:38:01.191205+00:00"}