{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:WA3SL523UHMPNCX3AA2IGEG5Q4","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":"35adc59ad9d9b7a6464dbf2e7e44551fd52813d0ec82d8e5556ffccf3234f4a9","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-05T13:56:18Z","title_canon_sha256":"0f5f2106a480e0869f41621abeaefcfddb203e30e3af38d65e3f3e90daab722e"},"schema_version":"1.0","source":{"id":"2205.02655","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.02655","created_at":"2026-07-05T04:27:31Z"},{"alias_kind":"arxiv_version","alias_value":"2205.02655v2","created_at":"2026-07-05T04:27:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.02655","created_at":"2026-07-05T04:27:31Z"},{"alias_kind":"pith_short_12","alias_value":"WA3SL523UHMP","created_at":"2026-07-05T04:27:31Z"},{"alias_kind":"pith_short_16","alias_value":"WA3SL523UHMPNCX3","created_at":"2026-07-05T04:27:31Z"},{"alias_kind":"pith_short_8","alias_value":"WA3SL523","created_at":"2026-07-05T04:27:31Z"}],"graph_snapshots":[{"event_id":"sha256:7b4505343bd8f2290126bf966dae1f9f1c04224c3bc6e1b7887ee72b8db6aaaa","target":"graph","created_at":"2026-07-05T04:27:31Z","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/2205.02655/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative language models (LMs) such as GPT-2/3 can be prompted to generate text with remarkable quality. While they are designed for text-prompted generation, it remains an open question how the generation process could be guided by modalities beyond text such as images. In this work, we propose a training-free framework, called MAGIC (iMAge-Guided text generatIon with CLIP), for plugging in visual controls in the generation process and enabling LMs to perform multimodal tasks (e.g., image captioning) in a zero-shot manner. MAGIC is a simple yet efficient plug-and-play framework, which direc","authors_text":"Dani Yogatama, Fangyu Liu, Lingpeng Kong, Nigel Collier, Tian Lan, Yahui Liu, Yan Wang, Yixuan Su","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-05T13:56:18Z","title":"Language Models Can See: Plugging Visual Controls in Text Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.02655","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:fee49528e46ea2b2a2ba3e86fbcc2503b9a9a705e6d86a995277e352edff03a7","target":"record","created_at":"2026-07-05T04:27:31Z","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":"35adc59ad9d9b7a6464dbf2e7e44551fd52813d0ec82d8e5556ffccf3234f4a9","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-05T13:56:18Z","title_canon_sha256":"0f5f2106a480e0869f41621abeaefcfddb203e30e3af38d65e3f3e90daab722e"},"schema_version":"1.0","source":{"id":"2205.02655","kind":"arxiv","version":2}},"canonical_sha256":"b03725f75ba1d8f68afb00348310dd870075e9c8e247dc102acdb515ba124484","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b03725f75ba1d8f68afb00348310dd870075e9c8e247dc102acdb515ba124484","first_computed_at":"2026-07-05T04:27:31.134748Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:27:31.134748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pess32UseUlsu+UaDVupfGACV2T6awFbj8d8ir23ZMvAf8JbNq08LmxQFdPzDQYdbt0vYlefmWRyEfCCwahvDA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:27:31.135227Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.02655","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fee49528e46ea2b2a2ba3e86fbcc2503b9a9a705e6d86a995277e352edff03a7","sha256:7b4505343bd8f2290126bf966dae1f9f1c04224c3bc6e1b7887ee72b8db6aaaa"],"state_sha256":"4cb3787b9805b38c9c08e9d01a8115438666f597aacf7f9684b1697cab2ada6a"}