{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TNWRIT2QQO7MGAH2EQNOMCIUQA","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":"f7d92b92abe9879e3031bb99061ccd51c3f40c0fa686128a3de62051e01b0958","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-04T04:31:39Z","title_canon_sha256":"2663b3ecaa3d8018495bda25390df3f8b938917fdc880eae835328ca35c7f354"},"schema_version":"1.0","source":{"id":"2406.01956","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.01956","created_at":"2026-07-05T09:34:14Z"},{"alias_kind":"arxiv_version","alias_value":"2406.01956v3","created_at":"2026-07-05T09:34:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01956","created_at":"2026-07-05T09:34:14Z"},{"alias_kind":"pith_short_12","alias_value":"TNWRIT2QQO7M","created_at":"2026-07-05T09:34:14Z"},{"alias_kind":"pith_short_16","alias_value":"TNWRIT2QQO7MGAH2","created_at":"2026-07-05T09:34:14Z"},{"alias_kind":"pith_short_8","alias_value":"TNWRIT2Q","created_at":"2026-07-05T09:34:14Z"}],"graph_snapshots":[{"event_id":"sha256:686c9207e207f3e1a7b68e53af9eab92fb50c089a39ea953b2b70b231e0816c7","target":"graph","created_at":"2026-07-05T09:34:14Z","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/2406.01956/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents a novel approach to enhance image-to-image generation by leveraging the multimodal capabilities of the Large Language and Vision Assistant (LLaVA). We propose a framework where LLaVA analyzes input images and generates textual descriptions, hereinafter LLaVA-generated prompts. These prompts, along with the original image, are fed into the image-to-image generation pipeline. This enriched representation guides the generation process towards outputs that exhibit a stronger resemblance to the input image. Extensive experiments demonstrate the effectiveness of LLaVA-generated p","authors_text":"Panfeng Li, Qikai Yang, Siyang Li, Zhicheng Ding","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-04T04:31:39Z","title":"Enhance Image-to-Image Generation with LLaVA-generated Prompts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01956","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:e89d1aee22848db901cb2a421fe117b8f5fb291329654b6e82d9fe184cad6edc","target":"record","created_at":"2026-07-05T09:34:14Z","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":"f7d92b92abe9879e3031bb99061ccd51c3f40c0fa686128a3de62051e01b0958","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-04T04:31:39Z","title_canon_sha256":"2663b3ecaa3d8018495bda25390df3f8b938917fdc880eae835328ca35c7f354"},"schema_version":"1.0","source":{"id":"2406.01956","kind":"arxiv","version":3}},"canonical_sha256":"9b6d144f5083bec300fa241ae60914801670ecd9f83b829c4669b19bfeeb7254","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b6d144f5083bec300fa241ae60914801670ecd9f83b829c4669b19bfeeb7254","first_computed_at":"2026-07-05T09:34:14.505617Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:34:14.505617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"co9MmoWs1IH3MI9ZdHI4KS4DLW7V3gBV82L3Lkv7HBeWruiMxExRQWeQpFDO0T8yTmTcQ865cayUP68G+VQ+BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:34:14.506169Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.01956","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e89d1aee22848db901cb2a421fe117b8f5fb291329654b6e82d9fe184cad6edc","sha256:686c9207e207f3e1a7b68e53af9eab92fb50c089a39ea953b2b70b231e0816c7"],"state_sha256":"218adc36e1aabfbb70cdc0f7e45d86a999938701343c38caf07cdc67b0f21d9a"}