{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6PDSIA4JWD5KCLJNQC57T7WOXN","short_pith_number":"pith:6PDSIA4J","schema_version":"1.0","canonical_sha256":"f3c7240389b0faa12d2d80bbf9fecebb55855984c7f7bea7252bafe3d5052951","source":{"kind":"arxiv","id":"2204.03610","version":1},"attestation_state":"computed","paper":{"title":"Unified Contrastive Learning in Image-Text-Label Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bin Xiao, Ce Liu, Chunyuan Li, Jianfeng Gao, Jianwei Yang, Lu Yuan, Pengchuan Zhang","submitted_at":"2022-04-07T17:34:51Z","abstract_excerpt":"Visual recognition is recently learned via either supervised learning on human-annotated image-label data or language-image contrastive learning with webly-crawled image-text pairs. While supervised learning may result in a more discriminative representation, language-image pretraining shows unprecedented zero-shot recognition capability, largely due to the different properties of data sources and learning objectives. In this work, we introduce a new formulation by combining the two data sources into a common image-text-label space. In this space, we propose a new learning paradigm, called Uni"},"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":"2204.03610","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-07T17:34:51Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5fd55f6af71409eca74aeee7bf482481f88e1ea40641de321bba57f99ca9c19e","abstract_canon_sha256":"44d8a9f92b39c048c5a801feb67e86c919248ae2bcb1a3a7271958ab7461658a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:12:32.187295Z","signature_b64":"s5nW7DMH+4XJucDERCZ1hUuwPCKMdH6z0ao8t9OAUwdMiKkdT4BUrqwivCDsEc8dXlS0E7KWLPqtBifg02g7Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3c7240389b0faa12d2d80bbf9fecebb55855984c7f7bea7252bafe3d5052951","last_reissued_at":"2026-07-05T04:12:32.186938Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:12:32.186938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unified Contrastive Learning in Image-Text-Label Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bin Xiao, Ce Liu, Chunyuan Li, Jianfeng Gao, Jianwei Yang, Lu Yuan, Pengchuan Zhang","submitted_at":"2022-04-07T17:34:51Z","abstract_excerpt":"Visual recognition is recently learned via either supervised learning on human-annotated image-label data or language-image contrastive learning with webly-crawled image-text pairs. While supervised learning may result in a more discriminative representation, language-image pretraining shows unprecedented zero-shot recognition capability, largely due to the different properties of data sources and learning objectives. In this work, we introduce a new formulation by combining the two data sources into a common image-text-label space. In this space, we propose a new learning paradigm, called Uni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.03610","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/2204.03610/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":"2204.03610","created_at":"2026-07-05T04:12:32.187002+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.03610v1","created_at":"2026-07-05T04:12:32.187002+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.03610","created_at":"2026-07-05T04:12:32.187002+00:00"},{"alias_kind":"pith_short_12","alias_value":"6PDSIA4JWD5K","created_at":"2026-07-05T04:12:32.187002+00:00"},{"alias_kind":"pith_short_16","alias_value":"6PDSIA4JWD5KCLJN","created_at":"2026-07-05T04:12:32.187002+00:00"},{"alias_kind":"pith_short_8","alias_value":"6PDSIA4J","created_at":"2026-07-05T04:12:32.187002+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6PDSIA4JWD5KCLJNQC57T7WOXN","json":"https://pith.science/pith/6PDSIA4JWD5KCLJNQC57T7WOXN.json","graph_json":"https://pith.science/api/pith-number/6PDSIA4JWD5KCLJNQC57T7WOXN/graph.json","events_json":"https://pith.science/api/pith-number/6PDSIA4JWD5KCLJNQC57T7WOXN/events.json","paper":"https://pith.science/paper/6PDSIA4J"},"agent_actions":{"view_html":"https://pith.science/pith/6PDSIA4JWD5KCLJNQC57T7WOXN","download_json":"https://pith.science/pith/6PDSIA4JWD5KCLJNQC57T7WOXN.json","view_paper":"https://pith.science/paper/6PDSIA4J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.03610&json=true","fetch_graph":"https://pith.science/api/pith-number/6PDSIA4JWD5KCLJNQC57T7WOXN/graph.json","fetch_events":"https://pith.science/api/pith-number/6PDSIA4JWD5KCLJNQC57T7WOXN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6PDSIA4JWD5KCLJNQC57T7WOXN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6PDSIA4JWD5KCLJNQC57T7WOXN/action/storage_attestation","attest_author":"https://pith.science/pith/6PDSIA4JWD5KCLJNQC57T7WOXN/action/author_attestation","sign_citation":"https://pith.science/pith/6PDSIA4JWD5KCLJNQC57T7WOXN/action/citation_signature","submit_replication":"https://pith.science/pith/6PDSIA4JWD5KCLJNQC57T7WOXN/action/replication_record"}},"created_at":"2026-07-05T04:12:32.187002+00:00","updated_at":"2026-07-05T04:12:32.187002+00:00"}