{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XBBYNHH2DEZA7BDQWX2EC6XXJX","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":"f37fb21951b0abda0e91d1909a750ec09e67b568affc5faa127ee7431ca24a2a","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-04T17:28:44Z","title_canon_sha256":"1c7b8dcd8668b3a097d44f49b7a7d5a41a6343b1d65773748a6a73625177ed5e"},"schema_version":"1.0","source":{"id":"2310.02992","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.02992","created_at":"2026-07-05T08:12:14Z"},{"alias_kind":"arxiv_version","alias_value":"2310.02992v3","created_at":"2026-07-05T08:12:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02992","created_at":"2026-07-05T08:12:14Z"},{"alias_kind":"pith_short_12","alias_value":"XBBYNHH2DEZA","created_at":"2026-07-05T08:12:14Z"},{"alias_kind":"pith_short_16","alias_value":"XBBYNHH2DEZA7BDQ","created_at":"2026-07-05T08:12:14Z"},{"alias_kind":"pith_short_8","alias_value":"XBBYNHH2","created_at":"2026-07-05T08:12:14Z"}],"graph_snapshots":[{"event_id":"sha256:8b4050e94cea843ee30831d372df7200e4cf39fd79c7c4a0bd219d69a6aa609e","target":"graph","created_at":"2026-07-05T08:12:14Z","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/2310.02992/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in subject-driven image generation have made significant strides. However, current methods still fall short in diverse application scenarios, as they require test-time tuning and cannot accept interleaved multi-image and text input. These limitations keep them far from the ultimate goal of \"image as a foreign language in image generation.\" This paper presents Kosmos-G, a model that leverages the advanced multimodal perception capabilities of Multimodal Large Language Models (MLLMs) to tackle the aforementioned challenge. Our approach aligns the output space of MLLM with CLI","authors_text":"Furu Wei, Li Dong, Shaohan Huang, Wenhu Chen, Xichen Pan, Zhiliang Peng","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-04T17:28:44Z","title":"Kosmos-G: Generating Images in Context with Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02992","kind":"arxiv","version":3},"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:cfefc6e481311337a056ebc9af59ed0cf7462fb66c8605c3b8d42bf0273ccea0","target":"record","created_at":"2026-07-05T08:12:14Z","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":"f37fb21951b0abda0e91d1909a750ec09e67b568affc5faa127ee7431ca24a2a","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-04T17:28:44Z","title_canon_sha256":"1c7b8dcd8668b3a097d44f49b7a7d5a41a6343b1d65773748a6a73625177ed5e"},"schema_version":"1.0","source":{"id":"2310.02992","kind":"arxiv","version":3}},"canonical_sha256":"b843869cfa19320f8470b5f4417af74de28a2329d41febaa97cd6bfd98468928","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b843869cfa19320f8470b5f4417af74de28a2329d41febaa97cd6bfd98468928","first_computed_at":"2026-07-05T08:12:14.232123Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:12:14.232123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bBstJV6pxYY/s4P9RycDJ9/OLMRvTILdNJVf+S5uRbjmaLymKLejdDRbsetpIKB02cMRYluE6vnXHGr/R63dBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:12:14.232591Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.02992","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cfefc6e481311337a056ebc9af59ed0cf7462fb66c8605c3b8d42bf0273ccea0","sha256:8b4050e94cea843ee30831d372df7200e4cf39fd79c7c4a0bd219d69a6aa609e"],"state_sha256":"2b2d7b11d3d2502cb9e5b3cc596da7f49ed117e958d2b39500932cbaa638b08e"}