{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:V7B474SP3EI6VV7XGXRSWH7XK4","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":"0b0305dded64f5e636f7d30ff7d30ed0e5cf3dd636383c232cc6420695631395","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-15T17:50:51Z","title_canon_sha256":"6ec100db6356550eb6d0ab6d1ed772beb9ee02e62a04e4d05d6430668606e2fa"},"schema_version":"1.0","source":{"id":"2207.07635","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.07635","created_at":"2026-07-05T04:40:34Z"},{"alias_kind":"arxiv_version","alias_value":"2207.07635v1","created_at":"2026-07-05T04:40:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.07635","created_at":"2026-07-05T04:40:34Z"},{"alias_kind":"pith_short_12","alias_value":"V7B474SP3EI6","created_at":"2026-07-05T04:40:34Z"},{"alias_kind":"pith_short_16","alias_value":"V7B474SP3EI6VV7X","created_at":"2026-07-05T04:40:34Z"},{"alias_kind":"pith_short_8","alias_value":"V7B474SP","created_at":"2026-07-05T04:40:34Z"}],"graph_snapshots":[{"event_id":"sha256:a1aed6eff853d9dc2d2d070d9569a4b213e390a998423cfcc77f9dfb40398081","target":"graph","created_at":"2026-07-05T04:40:34Z","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/2207.07635/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The development of CLIP [Radford et al., 2021] has sparked a debate on whether language supervision can result in vision models with more transferable representations than traditional image-only methods. Our work studies this question through a carefully controlled comparison of two approaches in terms of their ability to learn representations that generalize to downstream classification tasks. We find that when the pre-training dataset meets certain criteria -- it is sufficiently large and contains descriptive captions with low variability -- image-only methods do not match CLIP's transfer pe","authors_text":"Percy Liang, Rohan Taori, Shibani Santurkar, Tatsunori Hashimoto, Yann Dubois","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-15T17:50:51Z","title":"Is a Caption Worth a Thousand Images? A Controlled Study for Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.07635","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:ec51513625e27db100bcde267a590130c4d00b07e3f6452f1456533b00ef0077","target":"record","created_at":"2026-07-05T04:40:34Z","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":"0b0305dded64f5e636f7d30ff7d30ed0e5cf3dd636383c232cc6420695631395","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-15T17:50:51Z","title_canon_sha256":"6ec100db6356550eb6d0ab6d1ed772beb9ee02e62a04e4d05d6430668606e2fa"},"schema_version":"1.0","source":{"id":"2207.07635","kind":"arxiv","version":1}},"canonical_sha256":"afc3cff24fd911ead7f735e32b1ff75709329aec7847135cde4b0de68f216e31","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"afc3cff24fd911ead7f735e32b1ff75709329aec7847135cde4b0de68f216e31","first_computed_at":"2026-07-05T04:40:34.699229Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:40:34.699229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YlPaOxD6iLgQfVj5LyS4EY3ulPKgwAeZwV0/9Swe7AtlvQqtjwmQB++oZWdRW3udYUHYgmkvmX6G+b6g/kqVBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:40:34.699592Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.07635","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec51513625e27db100bcde267a590130c4d00b07e3f6452f1456533b00ef0077","sha256:a1aed6eff853d9dc2d2d070d9569a4b213e390a998423cfcc77f9dfb40398081"],"state_sha256":"7c74c05c3a831d24f3b3f975f03ed3397a5cbddcf6ab8284582a647ccbe7bf67"}