{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UT5XUVUS5RJKWRYUSUTUT4ON7O","short_pith_number":"pith:UT5XUVUS","schema_version":"1.0","canonical_sha256":"a4fb7a5692ec52ab4714952749f1cdfb97be02e24a25f18826995e3a15a0e7de","source":{"kind":"arxiv","id":"1911.05978","version":1},"attestation_state":"computed","paper":{"title":"HUSE: Hierarchical Universal Semantic Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Abishek Krishnamoorthy, Aniket Pednekar, Kazoo Sone, Pradyumna Narayana, Sugato Basu","submitted_at":"2019-11-14T07:45:32Z","abstract_excerpt":"There is a recent surge of interest in cross-modal representation learning corresponding to images and text. The main challenge lies in mapping images and text to a shared latent space where the embeddings corresponding to a similar semantic concept lie closer to each other than the embeddings corresponding to different semantic concepts, irrespective of the modality. Ranking losses are commonly used to create such shared latent space -- however, they do not impose any constraints on inter-class relationships resulting in neighboring clusters to be completely unrelated. The works in the domain"},"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":"1911.05978","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-14T07:45:32Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"f0c5cf191b4e1019399b182e0df3249b129c664f91a77510dbc4895fdac3b230","abstract_canon_sha256":"7c1a47145e6bb4bcb4d829c2f03f549049d0fda87dd275b0c6375b3bf38a0d9a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:19:14.480265Z","signature_b64":"USITngQvQSt0Hz+V3USUHdM7DdKsWIT46J9m9xP8lEfna5JeOd8WhjNWz2QdCJhc9L5b5Z3Ib1IB6dQ7jceQCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4fb7a5692ec52ab4714952749f1cdfb97be02e24a25f18826995e3a15a0e7de","last_reissued_at":"2026-07-05T00:19:14.479866Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:19:14.479866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HUSE: Hierarchical Universal Semantic Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Abishek Krishnamoorthy, Aniket Pednekar, Kazoo Sone, Pradyumna Narayana, Sugato Basu","submitted_at":"2019-11-14T07:45:32Z","abstract_excerpt":"There is a recent surge of interest in cross-modal representation learning corresponding to images and text. The main challenge lies in mapping images and text to a shared latent space where the embeddings corresponding to a similar semantic concept lie closer to each other than the embeddings corresponding to different semantic concepts, irrespective of the modality. Ranking losses are commonly used to create such shared latent space -- however, they do not impose any constraints on inter-class relationships resulting in neighboring clusters to be completely unrelated. The works in the domain"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.05978","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1911.05978/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1911.05978","created_at":"2026-07-05T00:19:14.479920+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.05978v1","created_at":"2026-07-05T00:19:14.479920+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.05978","created_at":"2026-07-05T00:19:14.479920+00:00"},{"alias_kind":"pith_short_12","alias_value":"UT5XUVUS5RJK","created_at":"2026-07-05T00:19:14.479920+00:00"},{"alias_kind":"pith_short_16","alias_value":"UT5XUVUS5RJKWRYU","created_at":"2026-07-05T00:19:14.479920+00:00"},{"alias_kind":"pith_short_8","alias_value":"UT5XUVUS","created_at":"2026-07-05T00:19:14.479920+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.07415","citing_title":"EPIC: Efficient Prompt Interaction for Text-Image Classification","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UT5XUVUS5RJKWRYUSUTUT4ON7O","json":"https://pith.science/pith/UT5XUVUS5RJKWRYUSUTUT4ON7O.json","graph_json":"https://pith.science/api/pith-number/UT5XUVUS5RJKWRYUSUTUT4ON7O/graph.json","events_json":"https://pith.science/api/pith-number/UT5XUVUS5RJKWRYUSUTUT4ON7O/events.json","paper":"https://pith.science/paper/UT5XUVUS"},"agent_actions":{"view_html":"https://pith.science/pith/UT5XUVUS5RJKWRYUSUTUT4ON7O","download_json":"https://pith.science/pith/UT5XUVUS5RJKWRYUSUTUT4ON7O.json","view_paper":"https://pith.science/paper/UT5XUVUS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.05978&json=true","fetch_graph":"https://pith.science/api/pith-number/UT5XUVUS5RJKWRYUSUTUT4ON7O/graph.json","fetch_events":"https://pith.science/api/pith-number/UT5XUVUS5RJKWRYUSUTUT4ON7O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UT5XUVUS5RJKWRYUSUTUT4ON7O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UT5XUVUS5RJKWRYUSUTUT4ON7O/action/storage_attestation","attest_author":"https://pith.science/pith/UT5XUVUS5RJKWRYUSUTUT4ON7O/action/author_attestation","sign_citation":"https://pith.science/pith/UT5XUVUS5RJKWRYUSUTUT4ON7O/action/citation_signature","submit_replication":"https://pith.science/pith/UT5XUVUS5RJKWRYUSUTUT4ON7O/action/replication_record"}},"created_at":"2026-07-05T00:19:14.479920+00:00","updated_at":"2026-07-05T00:19:14.479920+00:00"}