{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CMOVSF53KVRLBAGYCRGSWKBH2X","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":"27e666922803d19b55fd305a2e9a086244dd2fe0e93253e3c6ad6fd5afd9a5f5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-28T15:58:31Z","title_canon_sha256":"3375a8014526db592b439865337ebbbce0d5cd64f211d7693bf66f3086491130"},"schema_version":"1.0","source":{"id":"2405.18304","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18304","created_at":"2026-07-05T08:24:18Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18304v1","created_at":"2026-07-05T08:24:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18304","created_at":"2026-07-05T08:24:18Z"},{"alias_kind":"pith_short_12","alias_value":"CMOVSF53KVRL","created_at":"2026-07-05T08:24:18Z"},{"alias_kind":"pith_short_16","alias_value":"CMOVSF53KVRLBAGY","created_at":"2026-07-05T08:24:18Z"},{"alias_kind":"pith_short_8","alias_value":"CMOVSF53","created_at":"2026-07-05T08:24:18Z"}],"graph_snapshots":[{"event_id":"sha256:637dfa181d9d72e227e5d310786087aad9d5599126122c2c0ed1135d1fd245e5","target":"graph","created_at":"2026-07-05T08:24:18Z","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/2405.18304/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we study the problem of generating novel images from complex multimodal prompt sequences. While existing methods achieve promising results for text-to-image generation, they often struggle to capture fine-grained details from lengthy prompts and maintain contextual coherence within prompt sequences. Moreover, they often result in misaligned image generation for prompt sequences featuring multiple objects. To address this, we propose a Multi-modal Generation via Cross-Modal In-Context Learning (MGCC) method that generates novel images from complex multimodal prompt sequences by le","authors_text":"Amandeep Kumar, Hisham Cholakkal, Muzammal Naseer, Rao Muhammad Anwer, Salman Khan, Sanath Narayan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-28T15:58:31Z","title":"Multi-modal Generation via Cross-Modal In-Context Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18304","kind":"arxiv","version":1},"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":"sha256:42916f896d0c9bac3518706f05dcb27d42320a7fac3bb237ad4b56e6572b6667","target":"record","created_at":"2026-07-05T08:24:18Z","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":"27e666922803d19b55fd305a2e9a086244dd2fe0e93253e3c6ad6fd5afd9a5f5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-28T15:58:31Z","title_canon_sha256":"3375a8014526db592b439865337ebbbce0d5cd64f211d7693bf66f3086491130"},"schema_version":"1.0","source":{"id":"2405.18304","kind":"arxiv","version":1}},"canonical_sha256":"131d5917bb5562b080d8144d2b2827d5f09a570b02265ce7e3a9e13f9c4767d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"131d5917bb5562b080d8144d2b2827d5f09a570b02265ce7e3a9e13f9c4767d2","first_computed_at":"2026-07-05T08:24:18.188687Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:24:18.188687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aPxm3clxIZbsV83odd+EKWM4vL+orWEbDrp3PGlN9ITl5olxmCBQLwBS5+78TyMAYUBrKcs47KwbQ7DFoAgiDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:24:18.189112Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.18304","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42916f896d0c9bac3518706f05dcb27d42320a7fac3bb237ad4b56e6572b6667","sha256:637dfa181d9d72e227e5d310786087aad9d5599126122c2c0ed1135d1fd245e5"],"state_sha256":"38ebdd8ae53415cbe920e11d62bdae4066b40a0e1aad2b282e7f7ae5e3b052a5"}