{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:Q36RX6HGW2X6AK3KOTLQMFSSTZ","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":"71ba7909d4a0ed3a0527535fab7450fef50b8c2d495b5f0bdf111962cce42d57","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-02T17:57:31Z","title_canon_sha256":"6c42ea7e7a4948ba7de0e2274544cad22758471f804068c36283f7839520d136"},"schema_version":"1.0","source":{"id":"2109.01134","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.01134","created_at":"2026-07-05T05:03:49Z"},{"alias_kind":"arxiv_version","alias_value":"2109.01134v6","created_at":"2026-07-05T05:03:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.01134","created_at":"2026-07-05T05:03:49Z"},{"alias_kind":"pith_short_12","alias_value":"Q36RX6HGW2X6","created_at":"2026-07-05T05:03:49Z"},{"alias_kind":"pith_short_16","alias_value":"Q36RX6HGW2X6AK3K","created_at":"2026-07-05T05:03:49Z"},{"alias_kind":"pith_short_8","alias_value":"Q36RX6HG","created_at":"2026-07-05T05:03:49Z"}],"graph_snapshots":[{"event_id":"sha256:94455ec9edfb47c2e121e19d70739c05e42794a086c61c84fce2bb6bcca79780","target":"graph","created_at":"2026-07-05T05:03:49Z","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/2109.01134/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large pre-trained vision-language models like CLIP have shown great potential in learning representations that are transferable across a wide range of downstream tasks. Different from the traditional representation learning that is based mostly on discretized labels, vision-language pre-training aligns images and texts in a common feature space, which allows zero-shot transfer to a downstream task via prompting, i.e., classification weights are synthesized from natural language describing classes of interest. In this work, we show that a major challenge for deploying such models in practice is","authors_text":"Chen Change Loy, Jingkang Yang, Kaiyang Zhou, Ziwei Liu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-02T17:57:31Z","title":"Learning to Prompt for Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.01134","kind":"arxiv","version":6},"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:ce5e74db59f11cdb897a7c5c3ad9061ddef6caaa92a93e92d57bd4e3f6f783a9","target":"record","created_at":"2026-07-05T05:03:49Z","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":"71ba7909d4a0ed3a0527535fab7450fef50b8c2d495b5f0bdf111962cce42d57","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-02T17:57:31Z","title_canon_sha256":"6c42ea7e7a4948ba7de0e2274544cad22758471f804068c36283f7839520d136"},"schema_version":"1.0","source":{"id":"2109.01134","kind":"arxiv","version":6}},"canonical_sha256":"86fd1bf8e6b6afe02b6a74d70616529e73e341048a88de09a7bc13f4a80dc198","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"86fd1bf8e6b6afe02b6a74d70616529e73e341048a88de09a7bc13f4a80dc198","first_computed_at":"2026-07-05T05:03:49.609923Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:03:49.609923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BZ3SgnMt84Q5K/Sj/FUvLI6zo2FJBhJvArAoptWSesvglp4us1dFk6BH8aEPRpU0Unk94bWFMZrhlI7mLf7eDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:03:49.610540Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.01134","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce5e74db59f11cdb897a7c5c3ad9061ddef6caaa92a93e92d57bd4e3f6f783a9","sha256:94455ec9edfb47c2e121e19d70739c05e42794a086c61c84fce2bb6bcca79780"],"state_sha256":"4f63513999bfa2d77465438920a25ba0739bd2b4d85f618edc8dd323211152a2"}