{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ELCU4XF562WNZJ5OJHUIHJOPJH","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":"44806c2f7fbed3bb9d542fa4dcc8ab03627f10e22035186d0d5aba065ea29f73","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-25T21:07:09Z","title_canon_sha256":"953a5ecb14c97fc1eac42807e1d98f66d670eaec7744bf3f41fbf0506e6afdd4"},"schema_version":"1.0","source":{"id":"2106.13884","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.13884","created_at":"2026-07-05T02:54:40Z"},{"alias_kind":"arxiv_version","alias_value":"2106.13884v2","created_at":"2026-07-05T02:54:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13884","created_at":"2026-07-05T02:54:40Z"},{"alias_kind":"pith_short_12","alias_value":"ELCU4XF562WN","created_at":"2026-07-05T02:54:40Z"},{"alias_kind":"pith_short_16","alias_value":"ELCU4XF562WNZJ5O","created_at":"2026-07-05T02:54:40Z"},{"alias_kind":"pith_short_8","alias_value":"ELCU4XF5","created_at":"2026-07-05T02:54:40Z"}],"graph_snapshots":[{"event_id":"sha256:68b55d8794789fbd2fbd41c833d87b3929ea2993c87779e9c27913286d272568","target":"graph","created_at":"2026-07-05T02:54:40Z","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/2106.13884/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"When trained at sufficient scale, auto-regressive language models exhibit the notable ability to learn a new language task after being prompted with just a few examples. Here, we present a simple, yet effective, approach for transferring this few-shot learning ability to a multimodal setting (vision and language). Using aligned image and caption data, we train a vision encoder to represent each image as a sequence of continuous embeddings, such that a pre-trained, frozen language model prompted with this prefix generates the appropriate caption. The resulting system is a multimodal few-shot le","authors_text":"Felix Hill, Jacob Menick, Maria Tsimpoukelli, Oriol Vinyals, Serkan Cabi, S. M. Ali Eslami","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-25T21:07:09Z","title":"Multimodal Few-Shot Learning with Frozen Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13884","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":"sha256:6cfe866a213b5f73c81d292e3c35ccb8c6702380f0f2374a8278be73aaa2bb2d","target":"record","created_at":"2026-07-05T02:54:40Z","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":"44806c2f7fbed3bb9d542fa4dcc8ab03627f10e22035186d0d5aba065ea29f73","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-25T21:07:09Z","title_canon_sha256":"953a5ecb14c97fc1eac42807e1d98f66d670eaec7744bf3f41fbf0506e6afdd4"},"schema_version":"1.0","source":{"id":"2106.13884","kind":"arxiv","version":2}},"canonical_sha256":"22c54e5cbdf6acdca7ae49e883a5cf49f07ca56e3010017736ce4371d004ab01","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"22c54e5cbdf6acdca7ae49e883a5cf49f07ca56e3010017736ce4371d004ab01","first_computed_at":"2026-07-05T02:54:40.593048Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:54:40.593048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WT2HpG0AYCPZdbqG5RuzWjDIe3CgTnVgk/9ksmpQLrL5lQ5t20BPP8zky/7BT3vjwUIZ02YEH+IRyIc/aSWJAA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:54:40.593532Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.13884","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6cfe866a213b5f73c81d292e3c35ccb8c6702380f0f2374a8278be73aaa2bb2d","sha256:68b55d8794789fbd2fbd41c833d87b3929ea2993c87779e9c27913286d272568"],"state_sha256":"2ac0880efe6f506055db7da8fc01dcfccc03dda0683edc4baac65be8ee9f74d2"}