{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:6PDSIA4JWD5KCLJNQC57T7WOXN","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":"44d8a9f92b39c048c5a801feb67e86c919248ae2bcb1a3a7271958ab7461658a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-07T17:34:51Z","title_canon_sha256":"5fd55f6af71409eca74aeee7bf482481f88e1ea40641de321bba57f99ca9c19e"},"schema_version":"1.0","source":{"id":"2204.03610","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.03610","created_at":"2026-07-05T04:12:32Z"},{"alias_kind":"arxiv_version","alias_value":"2204.03610v1","created_at":"2026-07-05T04:12:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.03610","created_at":"2026-07-05T04:12:32Z"},{"alias_kind":"pith_short_12","alias_value":"6PDSIA4JWD5K","created_at":"2026-07-05T04:12:32Z"},{"alias_kind":"pith_short_16","alias_value":"6PDSIA4JWD5KCLJN","created_at":"2026-07-05T04:12:32Z"},{"alias_kind":"pith_short_8","alias_value":"6PDSIA4J","created_at":"2026-07-05T04:12:32Z"}],"graph_snapshots":[{"event_id":"sha256:825c49f413e6a66f4b49ab068903ba0f9f0472a37feec4d6e603cc7de11acb6c","target":"graph","created_at":"2026-07-05T04:12:32Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2204.03610/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bin Xiao, Ce Liu, Chunyuan Li, Jianfeng Gao, Jianwei Yang, Lu Yuan, Pengchuan Zhang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-07T17:34:51Z","title":"Unified Contrastive Learning in Image-Text-Label Space"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.03610","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":"sha256:6f8a218c7d3ba7c5adb341a2e1f982710ead1b220d6ff45690712eecf2a53d9b","target":"record","created_at":"2026-07-05T04:12:32Z","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":"44d8a9f92b39c048c5a801feb67e86c919248ae2bcb1a3a7271958ab7461658a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-07T17:34:51Z","title_canon_sha256":"5fd55f6af71409eca74aeee7bf482481f88e1ea40641de321bba57f99ca9c19e"},"schema_version":"1.0","source":{"id":"2204.03610","kind":"arxiv","version":1}},"canonical_sha256":"f3c7240389b0faa12d2d80bbf9fecebb55855984c7f7bea7252bafe3d5052951","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f3c7240389b0faa12d2d80bbf9fecebb55855984c7f7bea7252bafe3d5052951","first_computed_at":"2026-07-05T04:12:32.186938Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:12:32.186938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s5nW7DMH+4XJucDERCZ1hUuwPCKMdH6z0ao8t9OAUwdMiKkdT4BUrqwivCDsEc8dXlS0E7KWLPqtBifg02g7Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:12:32.187295Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.03610","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f8a218c7d3ba7c5adb341a2e1f982710ead1b220d6ff45690712eecf2a53d9b","sha256:825c49f413e6a66f4b49ab068903ba0f9f0472a37feec4d6e603cc7de11acb6c"],"state_sha256":"e4ce18fd9d3a1b27f0d0c0bac7ce377c04fc1f0c12651ca8c0b7327caae80484"}