{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OLA3QOAEJKLNSDVEVVGHDUF7DC","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":"168a7e5710734ed3087745bc62a9dcb553eb62d86d8db2592fee7eedd1e13330","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-24T17:47:21Z","title_canon_sha256":"c05f5373b7a8e8e5be6aa7b713cced67cb4e99509718991845156f0a76b511fc"},"schema_version":"1.0","source":{"id":"2605.25191","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.25191","created_at":"2026-05-26T02:04:22Z"},{"alias_kind":"arxiv_version","alias_value":"2605.25191v1","created_at":"2026-05-26T02:04:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25191","created_at":"2026-05-26T02:04:22Z"},{"alias_kind":"pith_short_12","alias_value":"OLA3QOAEJKLN","created_at":"2026-05-26T02:04:22Z"},{"alias_kind":"pith_short_16","alias_value":"OLA3QOAEJKLNSDVE","created_at":"2026-05-26T02:04:22Z"},{"alias_kind":"pith_short_8","alias_value":"OLA3QOAE","created_at":"2026-05-26T02:04:22Z"}],"graph_snapshots":[{"event_id":"sha256:3c03405d00bf53f9288e0ebd3a3a45f4ef461a6ebf3dddb9cf64474151e0f877","target":"graph","created_at":"2026-05-26T02:04:22Z","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/2605.25191/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-image diffusion models like Stable Diffusion generate high-quality images from text, but lack a way to inject visual guidance (e.g. sketches, styles) at inference without retraining. Existing methods either require computationally expensive fine-tuning or rely on style transfer techniques that risk semantic misalignment with textual prompts. We introduce Visual Concept Fusion (VCF), the first method offering dual conditioning on both an image and text prompt at inference time without any concept-specific training. VCF enables visual concept injection into Stable Diffusion by aligning C","authors_text":"Agata \\.Zywot, Aritra Bhowmik, Derck Prinzhorn, Iason Skylitsis, Konrad Szewczyk, Thijmen Nijdam, Zoe Tzifa-Kratira","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-24T17:47:21Z","title":"Injecting Image Guidance into Text-Conditioned Diffusion Models at Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25191","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:cfa72a56f491f8f75cba7ea03eaea98898aa053c7f0e588c08b65aa4e63f0340","target":"record","created_at":"2026-05-26T02:04:22Z","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":"168a7e5710734ed3087745bc62a9dcb553eb62d86d8db2592fee7eedd1e13330","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-24T17:47:21Z","title_canon_sha256":"c05f5373b7a8e8e5be6aa7b713cced67cb4e99509718991845156f0a76b511fc"},"schema_version":"1.0","source":{"id":"2605.25191","kind":"arxiv","version":1}},"canonical_sha256":"72c1b838044a96d90ea4ad4c71d0bf188efa5e2df498f8d71b4f7a6d56c68eb6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"72c1b838044a96d90ea4ad4c71d0bf188efa5e2df498f8d71b4f7a6d56c68eb6","first_computed_at":"2026-05-26T02:04:22.332010Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:04:22.332010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SgtBPbh8ADJyiyuEgwPAonIqkVr/WdFhBnvD5QQX3vXd+3JnaJRFGgaLAB1zJdd9l0lePLwA0btgSvpLKacdAw==","signature_status":"signed_v1","signed_at":"2026-05-26T02:04:22.332784Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.25191","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cfa72a56f491f8f75cba7ea03eaea98898aa053c7f0e588c08b65aa4e63f0340","sha256:3c03405d00bf53f9288e0ebd3a3a45f4ef461a6ebf3dddb9cf64474151e0f877"],"state_sha256":"2c187072d3f2af9e6af76d038fb43f73c65edc1ecb185e726aab00caf472ff6d"}