{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:IGVFJYB6CEDUTLKKE3GYARVXSS","short_pith_number":"pith:IGVFJYB6","schema_version":"1.0","canonical_sha256":"41aa54e03e110749ad4a26cd8046b794bbbbfc3ab8cf61e28946c222bfbe3d30","source":{"kind":"arxiv","id":"1901.01860","version":3},"attestation_state":"computed","paper":{"title":"JECL: Joint Embedding and Cluster Learning for Image-Text Pairs","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bill Howe, Kuan-Hao Huang, Sean T. Yang","submitted_at":"2019-01-04T18:14:37Z","abstract_excerpt":"We propose JECL, a method for clustering image-caption pairs by training parallel encoders with regularized clustering and alignment objectives, simultaneously learning both representations and cluster assignments. These image-caption pairs arise frequently in high-value applications where structured training data is expensive to produce, but free-text descriptions are common. JECL trains by minimizing the Kullback-Leibler divergence between the distribution of the images and text to that of a combined joint target distribution and optimizing the Jensen-Shannon divergence between the soft clus"},"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":"1901.01860","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-04T18:14:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0fc470cbff24c93a4d87d96238b4160b5ceec161c07f388b274ed937f8b02550","abstract_canon_sha256":"22dfcf1a2f984a2e7c204187a1aacd317c87e0ffea19bc184dec64eb8e83044d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:43:36.918393Z","signature_b64":"b3tA57839dRMSDUCy20yLHcO+lfBPhIg/cZgaUC6i0J/ePjxfIwDtaZ8y7G8rUpYTBirYTfca8yfK+QBfQcNCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41aa54e03e110749ad4a26cd8046b794bbbbfc3ab8cf61e28946c222bfbe3d30","last_reissued_at":"2026-07-05T01:43:36.917958Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:43:36.917958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"JECL: Joint Embedding and Cluster Learning for Image-Text Pairs","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bill Howe, Kuan-Hao Huang, Sean T. Yang","submitted_at":"2019-01-04T18:14:37Z","abstract_excerpt":"We propose JECL, a method for clustering image-caption pairs by training parallel encoders with regularized clustering and alignment objectives, simultaneously learning both representations and cluster assignments. These image-caption pairs arise frequently in high-value applications where structured training data is expensive to produce, but free-text descriptions are common. JECL trains by minimizing the Kullback-Leibler divergence between the distribution of the images and text to that of a combined joint target distribution and optimizing the Jensen-Shannon divergence between the soft clus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.01860","kind":"arxiv","version":3},"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/1901.01860/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":"1901.01860","created_at":"2026-07-05T01:43:36.918027+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.01860v3","created_at":"2026-07-05T01:43:36.918027+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.01860","created_at":"2026-07-05T01:43:36.918027+00:00"},{"alias_kind":"pith_short_12","alias_value":"IGVFJYB6CEDU","created_at":"2026-07-05T01:43:36.918027+00:00"},{"alias_kind":"pith_short_16","alias_value":"IGVFJYB6CEDUTLKK","created_at":"2026-07-05T01:43:36.918027+00:00"},{"alias_kind":"pith_short_8","alias_value":"IGVFJYB6","created_at":"2026-07-05T01:43:36.918027+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.07465","citing_title":"Delineating Knowledge Domains in the Scientific Literature Using Visual Information","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IGVFJYB6CEDUTLKKE3GYARVXSS","json":"https://pith.science/pith/IGVFJYB6CEDUTLKKE3GYARVXSS.json","graph_json":"https://pith.science/api/pith-number/IGVFJYB6CEDUTLKKE3GYARVXSS/graph.json","events_json":"https://pith.science/api/pith-number/IGVFJYB6CEDUTLKKE3GYARVXSS/events.json","paper":"https://pith.science/paper/IGVFJYB6"},"agent_actions":{"view_html":"https://pith.science/pith/IGVFJYB6CEDUTLKKE3GYARVXSS","download_json":"https://pith.science/pith/IGVFJYB6CEDUTLKKE3GYARVXSS.json","view_paper":"https://pith.science/paper/IGVFJYB6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.01860&json=true","fetch_graph":"https://pith.science/api/pith-number/IGVFJYB6CEDUTLKKE3GYARVXSS/graph.json","fetch_events":"https://pith.science/api/pith-number/IGVFJYB6CEDUTLKKE3GYARVXSS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IGVFJYB6CEDUTLKKE3GYARVXSS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IGVFJYB6CEDUTLKKE3GYARVXSS/action/storage_attestation","attest_author":"https://pith.science/pith/IGVFJYB6CEDUTLKKE3GYARVXSS/action/author_attestation","sign_citation":"https://pith.science/pith/IGVFJYB6CEDUTLKKE3GYARVXSS/action/citation_signature","submit_replication":"https://pith.science/pith/IGVFJYB6CEDUTLKKE3GYARVXSS/action/replication_record"}},"created_at":"2026-07-05T01:43:36.918027+00:00","updated_at":"2026-07-05T01:43:36.918027+00:00"}