{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SO5DGOG4FZHZVELR2HDCYMVAE2","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":"c0e33f53768481e2eedf292a036100c81e7148492ac9c18095e105d126df48e6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-12T15:35:34Z","title_canon_sha256":"39c3e977f8fa68dc787afc434839e9eba9fd09d849d59fa67a1a2ebd616fd377"},"schema_version":"1.0","source":{"id":"2605.12271","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12271","created_at":"2026-05-27T01:05:57Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12271v2","created_at":"2026-05-27T01:05:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12271","created_at":"2026-05-27T01:05:57Z"},{"alias_kind":"pith_short_12","alias_value":"SO5DGOG4FZHZ","created_at":"2026-05-27T01:05:57Z"},{"alias_kind":"pith_short_16","alias_value":"SO5DGOG4FZHZVELR","created_at":"2026-05-27T01:05:57Z"},{"alias_kind":"pith_short_8","alias_value":"SO5DGOG4","created_at":"2026-05-27T01:05:57Z"}],"graph_snapshots":[{"event_id":"sha256:639828951e4d918138bb0bfc1ed054d659e132c68c85ade3353877dd8767f69f","target":"graph","created_at":"2026-05-27T01:05:57Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"V2V-Zero reaches 0.85 on GenEval with a frozen Qwen-Image backbone, closely matching its optimized text-to-image performance without fine-tuning, and scores 32.7/100 on Simple-V2V Bench while a video extension scores 20.2/100."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The frozen VLM already maps both text and images into the generator's conditioning space so that final-layer hidden states from visual pages can replace text conditioning without any fine-tuning or architectural changes."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"V2V-Zero adapts frozen VLMs for visual conditioning via hidden states from specification pages, scoring 0.85 on GenEval and 32.7 on a new seven-task benchmark while revealing capability hierarchies in attribute binding and structural control."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Visual specification pages replace text prompts in frozen generators without any retraining."}],"snapshot_sha256":"8274e763bce1d3161b4a9cacccf7d804a20e8f7e95d6e45c2976c625ad3f3f6e"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-26T14:45:24.437485Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-20T14:01:25.467010Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-20T10:17:13.945599Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T22:41:58.321139Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.12271/integrity.json","findings":[],"snapshot_sha256":"06ac31b9b5c5d3c1c8e7e01e86603ebd62e45f52bf211ba126be209800a564cf","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans often specify and create through visual artifacts: typography sheets, sketches, reference images, and annotated scenes. Yet modern visual generators still ask users to serialize this intent into text, a bottleneck that compresses signals like spatial structure, exact appearance, and glyph shape. We propose \\textbf{\\emph{visual-to-visual} (V2V)} generation, in which the user conditions a generative model with a visual specification page rather than a text prompt. The page is not an edit target, but a visual document that specifies the desired output. We introduce \\textbf{V2V-Zero}, a tra","authors_text":"Haoxuan Che, Jean-Michel Morel, Kangning Cui, Meng Chu, Raymond H. Chan, Rui Liu, Suiyun Zhang, Xiaodong Cun, Yaofang Liu, Zhaoqing Li","cross_cats":[],"headline":"Visual specification pages replace text prompts in frozen generators without any retraining.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-12T15:35:34Z","title":"Beyond Text Prompts: Visual-to-Visual Generation as A Unified Paradigm"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.12271","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-13T05:56:50.607649Z","id":"a5ab15ab-d024-4dc1-944f-22d1a68cae8e","model_set":{"reader":"grok-4.3"},"one_line_summary":"V2V-Zero adapts frozen VLMs for visual conditioning via hidden states from specification pages, scoring 0.85 on GenEval and 32.7 on a new seven-task benchmark while revealing capability hierarchies in attribute binding and structural control.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Visual specification pages replace text prompts in frozen generators without any retraining.","strongest_claim":"V2V-Zero reaches 0.85 on GenEval with a frozen Qwen-Image backbone, closely matching its optimized text-to-image performance without fine-tuning, and scores 32.7/100 on Simple-V2V Bench while a video extension scores 20.2/100.","weakest_assumption":"The frozen VLM already maps both text and images into the generator's conditioning space so that final-layer hidden states from visual pages can replace text conditioning without any fine-tuning or architectural changes."}},"verdict_id":"a5ab15ab-d024-4dc1-944f-22d1a68cae8e"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8e214e38f5a27d562601416996ba39b10fa3acd99a7f0b3b3940212cbf4b1b35","target":"record","created_at":"2026-05-27T01:05:57Z","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":"c0e33f53768481e2eedf292a036100c81e7148492ac9c18095e105d126df48e6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-12T15:35:34Z","title_canon_sha256":"39c3e977f8fa68dc787afc434839e9eba9fd09d849d59fa67a1a2ebd616fd377"},"schema_version":"1.0","source":{"id":"2605.12271","kind":"arxiv","version":2}},"canonical_sha256":"93ba3338dc2e4f9a9171d1c62c32a026ab7bbbe62a5b8d8539784346a9f5748c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"93ba3338dc2e4f9a9171d1c62c32a026ab7bbbe62a5b8d8539784346a9f5748c","first_computed_at":"2026-05-27T01:05:57.095844Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:05:57.095844Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lMy0oasEtdNc5UVTjQGNd3HPOPRtg4qTL30TTrZwn5TQSX3o2+DvsKai36M0HMczKqg6PCEPLnFdb3mLF32ECw==","signature_status":"signed_v1","signed_at":"2026-05-27T01:05:57.096600Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12271","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e214e38f5a27d562601416996ba39b10fa3acd99a7f0b3b3940212cbf4b1b35","sha256:639828951e4d918138bb0bfc1ed054d659e132c68c85ade3353877dd8767f69f"],"state_sha256":"558eadc6aae00f815c3e63b1a857df3eb17666de22ed56af9d68805e92e1fbf3"}