{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:X2HS26AZ2BEFZPKMDOFROHLAGV","short_pith_number":"pith:X2HS26AZ","schema_version":"1.0","canonical_sha256":"be8f2d7819d0485cbd4c1b8b171d603561fcff5420b37b828ab885ad323d06ea","source":{"kind":"arxiv","id":"1511.06361","version":6},"attestation_state":"computed","paper":{"title":"Order-Embeddings of Images and Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Ivan Vendrov, Raquel Urtasun, Ryan Kiros, Sanja Fidler","submitted_at":"2015-11-19T20:56:14Z","abstract_excerpt":"Hypernymy, textual entailment, and image captioning can be seen as special cases of a single visual-semantic hierarchy over words, sentences, and images. In this paper we advocate for explicitly modeling the partial order structure of this hierarchy. Towards this goal, we introduce a general method for learning ordered representations, and show how it can be applied to a variety of tasks involving images and language. We show that the resulting representations improve performance over current approaches for hypernym prediction and image-caption retrieval."},"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":"1511.06361","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-19T20:56:14Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"9aa6ca2eb2186b170809fcab124b0babca780078a8e4d2f2ecef77780ce46042","abstract_canon_sha256":"b9f7be34a4ed4ac1c77016aa56eef48b51bf579dc9b073a0ff51cff5cac31281"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:19:49.475464Z","signature_b64":"6APHfdT5aVN2dLcrUP8K06xlRpwjF+FX+5mKQf1Qt3k1i7K5DrNObGaslKsmmqho+Sfo/8/6AY6VxO2je23zBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be8f2d7819d0485cbd4c1b8b171d603561fcff5420b37b828ab885ad323d06ea","last_reissued_at":"2026-05-18T01:19:49.474876Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:19:49.474876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Order-Embeddings of Images and Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Ivan Vendrov, Raquel Urtasun, Ryan Kiros, Sanja Fidler","submitted_at":"2015-11-19T20:56:14Z","abstract_excerpt":"Hypernymy, textual entailment, and image captioning can be seen as special cases of a single visual-semantic hierarchy over words, sentences, and images. In this paper we advocate for explicitly modeling the partial order structure of this hierarchy. Towards this goal, we introduce a general method for learning ordered representations, and show how it can be applied to a variety of tasks involving images and language. We show that the resulting representations improve performance over current approaches for hypernym prediction and image-caption retrieval."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.06361","kind":"arxiv","version":6},"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":"1511.06361","created_at":"2026-05-18T01:19:49.474958+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.06361v6","created_at":"2026-05-18T01:19:49.474958+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.06361","created_at":"2026-05-18T01:19:49.474958+00:00"},{"alias_kind":"pith_short_12","alias_value":"X2HS26AZ2BEF","created_at":"2026-05-18T12:29:47.479230+00:00"},{"alias_kind":"pith_short_16","alias_value":"X2HS26AZ2BEFZPKM","created_at":"2026-05-18T12:29:47.479230+00:00"},{"alias_kind":"pith_short_8","alias_value":"X2HS26AZ","created_at":"2026-05-18T12:29:47.479230+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2412.08110","citing_title":"The ART of Composition: Attention-Regularized Training for Compositional Visual Grounding","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"2501.17518","citing_title":"RegD: Hierarchical Embeddings via Dissimilarity between Arbitrary Euclidean Regions","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"1910.07467","citing_title":"Root Mean Square Layer Normalization","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09392","citing_title":"HyNeuralMap: Hyperbolic Mapping of Visual Semantics to Neural Hierarchies","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06976","citing_title":"A Differentiable Bayesian Relaxation for Latent Partial-Order Inference","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16836","citing_title":"Lorentz Framework for Semantic Segmentation","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17454","citing_title":"HSG: Hyperbolic Scene Graph","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X2HS26AZ2BEFZPKMDOFROHLAGV","json":"https://pith.science/pith/X2HS26AZ2BEFZPKMDOFROHLAGV.json","graph_json":"https://pith.science/api/pith-number/X2HS26AZ2BEFZPKMDOFROHLAGV/graph.json","events_json":"https://pith.science/api/pith-number/X2HS26AZ2BEFZPKMDOFROHLAGV/events.json","paper":"https://pith.science/paper/X2HS26AZ"},"agent_actions":{"view_html":"https://pith.science/pith/X2HS26AZ2BEFZPKMDOFROHLAGV","download_json":"https://pith.science/pith/X2HS26AZ2BEFZPKMDOFROHLAGV.json","view_paper":"https://pith.science/paper/X2HS26AZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.06361&json=true","fetch_graph":"https://pith.science/api/pith-number/X2HS26AZ2BEFZPKMDOFROHLAGV/graph.json","fetch_events":"https://pith.science/api/pith-number/X2HS26AZ2BEFZPKMDOFROHLAGV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X2HS26AZ2BEFZPKMDOFROHLAGV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X2HS26AZ2BEFZPKMDOFROHLAGV/action/storage_attestation","attest_author":"https://pith.science/pith/X2HS26AZ2BEFZPKMDOFROHLAGV/action/author_attestation","sign_citation":"https://pith.science/pith/X2HS26AZ2BEFZPKMDOFROHLAGV/action/citation_signature","submit_replication":"https://pith.science/pith/X2HS26AZ2BEFZPKMDOFROHLAGV/action/replication_record"}},"created_at":"2026-05-18T01:19:49.474958+00:00","updated_at":"2026-05-18T01:19:49.474958+00:00"}