{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KY3UCKHSK75I2N5ZNERPIJ2NKQ","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":"f9558edbf70034df0310b4be399e932f7f5999859a4fb77bbc2253daadf6c1c7","cross_cats_sorted":["cs.AI","cs.CL","cs.GR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-17T18:58:58Z","title_canon_sha256":"4fbc736e730fba3020dfdfd3c5731787933fe1828fe35dc7309de57198e11a65"},"schema_version":"1.0","source":{"id":"2301.07093","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.07093","created_at":"2026-07-05T06:01:16Z"},{"alias_kind":"arxiv_version","alias_value":"2301.07093v2","created_at":"2026-07-05T06:01:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.07093","created_at":"2026-07-05T06:01:16Z"},{"alias_kind":"pith_short_12","alias_value":"KY3UCKHSK75I","created_at":"2026-07-05T06:01:16Z"},{"alias_kind":"pith_short_16","alias_value":"KY3UCKHSK75I2N5Z","created_at":"2026-07-05T06:01:16Z"},{"alias_kind":"pith_short_8","alias_value":"KY3UCKHS","created_at":"2026-07-05T06:01:16Z"}],"graph_snapshots":[{"event_id":"sha256:8336b59e43890a64a0c6b6d91dcf1cab69b4291f1872cc30e56cd19e1e3afb6e","target":"graph","created_at":"2026-07-05T06:01:16Z","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/2301.07093/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale text-to-image diffusion models have made amazing advances. However, the status quo is to use text input alone, which can impede controllability. In this work, we propose GLIGEN, Grounded-Language-to-Image Generation, a novel approach that builds upon and extends the functionality of existing pre-trained text-to-image diffusion models by enabling them to also be conditioned on grounding inputs. To preserve the vast concept knowledge of the pre-trained model, we freeze all of its weights and inject the grounding information into new trainable layers via a gated mechanism. Our model a","authors_text":"Chunyuan Li, Fangzhou Mu, Haotian Liu, Jianfeng Gao, Jianwei Yang, Qingyang Wu, Yong Jae Lee, Yuheng Li","cross_cats":["cs.AI","cs.CL","cs.GR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-17T18:58:58Z","title":"GLIGEN: Open-Set Grounded Text-to-Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.07093","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:fb4a34aa678219d273a5544e1adf5dc12b069d2999a1101a725e2fad3105b22e","target":"record","created_at":"2026-07-05T06:01:16Z","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":"f9558edbf70034df0310b4be399e932f7f5999859a4fb77bbc2253daadf6c1c7","cross_cats_sorted":["cs.AI","cs.CL","cs.GR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-17T18:58:58Z","title_canon_sha256":"4fbc736e730fba3020dfdfd3c5731787933fe1828fe35dc7309de57198e11a65"},"schema_version":"1.0","source":{"id":"2301.07093","kind":"arxiv","version":2}},"canonical_sha256":"56374128f257fa8d37b96922f4274d5418ee11eda9c98d0d7407d8e380b9c3fb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"56374128f257fa8d37b96922f4274d5418ee11eda9c98d0d7407d8e380b9c3fb","first_computed_at":"2026-07-05T06:01:16.315783Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:01:16.315783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L8ACy8eq3ssiNRvuS0TM8qGX1/zOveNbF2ILjoknByAtdb646KT1gYe2Mu3wFu6uct2uVAPN8GI1LBGk5W1HBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:01:16.316353Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.07093","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb4a34aa678219d273a5544e1adf5dc12b069d2999a1101a725e2fad3105b22e","sha256:8336b59e43890a64a0c6b6d91dcf1cab69b4291f1872cc30e56cd19e1e3afb6e"],"state_sha256":"f188b5d51f04de61be114c3a506be3b2818b35d59da511d6ecbff53cf78510e2"}