{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:TV7XBSION7JMXII3DP463HYI2W","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":"ad273139c4f389eb4c95742453e47733332bfa7d8e7e6380f9be05e26c482552","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-02T16:12:26Z","title_canon_sha256":"f588632538573771d774fb1326913a77f2a0e201cd2f09c72b2643adad385357"},"schema_version":"1.0","source":{"id":"2206.01125","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.01125","created_at":"2026-07-05T06:10:16Z"},{"alias_kind":"arxiv_version","alias_value":"2206.01125v2","created_at":"2026-07-05T06:10:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.01125","created_at":"2026-07-05T06:10:16Z"},{"alias_kind":"pith_short_12","alias_value":"TV7XBSION7JM","created_at":"2026-07-05T06:10:16Z"},{"alias_kind":"pith_short_16","alias_value":"TV7XBSION7JMXII3","created_at":"2026-07-05T06:10:16Z"},{"alias_kind":"pith_short_8","alias_value":"TV7XBSIO","created_at":"2026-07-05T06:10:16Z"}],"graph_snapshots":[{"event_id":"sha256:01abd3a09c1778fc86eb0ed7fc8787375dbc30e8ef340d9c93e4cc5f510ccf8b","target":"graph","created_at":"2026-07-05T06:10:16Z","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/2206.01125/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image-classification datasets have been used to pretrain image recognition models. Recently, web-scale image-caption datasets have emerged as a source of powerful pretraining alternative. Image-caption datasets are more ``open-domain'', containing a wider variety of scene types and vocabulary words than traditional classification datasets, and models trained on these datasets have demonstrated strong performance on few- and zero-shot recognition tasks. When naively unifying image-classification and -caption dataset, we show that such dataset biases negatively affect pre-training by reducing th","authors_text":"Chen-Yu Lee, Chun-Liang Li, Kate Saenko, Kihyuk Sohn, Kuniaki Saito, Tomas Pfister, Xiang Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-02T16:12:26Z","title":"Prefix Conditioning Unifies Language and Label Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.01125","kind":"arxiv","version":2},"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:abc3f01d935b412404a75e419d30e778043f35dd9f809becd9a5fcb6bd50a48a","target":"record","created_at":"2026-07-05T06:10:16Z","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":"ad273139c4f389eb4c95742453e47733332bfa7d8e7e6380f9be05e26c482552","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-02T16:12:26Z","title_canon_sha256":"f588632538573771d774fb1326913a77f2a0e201cd2f09c72b2643adad385357"},"schema_version":"1.0","source":{"id":"2206.01125","kind":"arxiv","version":2}},"canonical_sha256":"9d7f70c90e6fd2cba11b1bf9ed9f08d5841fe1bbfe009e1b83eec5d5f3cd23c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d7f70c90e6fd2cba11b1bf9ed9f08d5841fe1bbfe009e1b83eec5d5f3cd23c6","first_computed_at":"2026-07-05T06:10:16.508645Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:10:16.508645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cZb4pqhwxUrdMLYLU03TqyC1M1hlw8kTmYxrOcs26EnLR8B+2s30I6ipDUjsQrGM8dJJ8aBeVE/3kAuKeZy1DA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:10:16.509042Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.01125","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:abc3f01d935b412404a75e419d30e778043f35dd9f809becd9a5fcb6bd50a48a","sha256:01abd3a09c1778fc86eb0ed7fc8787375dbc30e8ef340d9c93e4cc5f510ccf8b"],"state_sha256":"c93ce294281f2fbbb53a260db6ccf58f60f05263f3c67a72be49e1aad7397ce1"}