{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:655ERAI43W4NCXEYW6NIKWCQMQ","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":"05f8dec0c5ba01aa6d905cadd1f0b0db24e9ea4becf01d28e4d3fe67e893dcd3","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-11-10T19:09:41Z","title_canon_sha256":"7173d9662dd2857c3423a09ae2f70aa5017ffb06554fbf188bdec070fb09bfe7"},"schema_version":"1.0","source":{"id":"1411.2539","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1411.2539","created_at":"2026-05-18T02:38:01Z"},{"alias_kind":"arxiv_version","alias_value":"1411.2539v1","created_at":"2026-05-18T02:38:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1411.2539","created_at":"2026-05-18T02:38:01Z"},{"alias_kind":"pith_short_12","alias_value":"655ERAI43W4N","created_at":"2026-05-18T12:28:16Z"},{"alias_kind":"pith_short_16","alias_value":"655ERAI43W4NCXEY","created_at":"2026-05-18T12:28:16Z"},{"alias_kind":"pith_short_8","alias_value":"655ERAI4","created_at":"2026-05-18T12:28:16Z"}],"graph_snapshots":[{"event_id":"sha256:4a381a6fcc03bdfb0b419759a4f889b58bb6f1b8b81c47ee40758c73223e45fd","target":"graph","created_at":"2026-05-18T02:38:01Z","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":"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","authors_text":"Richard S. Zemel, Ruslan Salakhutdinov, Ryan Kiros","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-11-10T19:09:41Z","title":"Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1411.2539","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:e186be572e715c16b4a71416f3d3925a9a869e81db1fc5339ac7c182c6a08f94","target":"record","created_at":"2026-05-18T02:38:01Z","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":"05f8dec0c5ba01aa6d905cadd1f0b0db24e9ea4becf01d28e4d3fe67e893dcd3","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-11-10T19:09:41Z","title_canon_sha256":"7173d9662dd2857c3423a09ae2f70aa5017ffb06554fbf188bdec070fb09bfe7"},"schema_version":"1.0","source":{"id":"1411.2539","kind":"arxiv","version":1}},"canonical_sha256":"f77a48811cddb8d15c98b79a8558506421f2c29bebb86e5580ad1ae053df6bcd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f77a48811cddb8d15c98b79a8558506421f2c29bebb86e5580ad1ae053df6bcd","first_computed_at":"2026-05-18T02:38:01.191124Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:38:01.191124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mEUldZxoMdKpBv+F+U9ArRs1qTvskzhXaplsezLwgUysoA+t3Hc5yMq/gkPmjNu/MxuVlCv5rgQ286F4Xay+AQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:38:01.191631Z","signed_message":"canonical_sha256_bytes"},"source_id":"1411.2539","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e186be572e715c16b4a71416f3d3925a9a869e81db1fc5339ac7c182c6a08f94","sha256:4a381a6fcc03bdfb0b419759a4f889b58bb6f1b8b81c47ee40758c73223e45fd"],"state_sha256":"d8776d4959f30ec6d556512a01cb12987cf9e4b3dfb4b73c1fcc65d537a870ad"}