{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZHXZUHZLSAO4F3PNMAZMUS3JLD","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":"5c1e696a415d22e0d4db6e03b6cce776c8dd8025f8e7f9584c11dafb9397095d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-09T04:01:21Z","title_canon_sha256":"2f4981b4d731886bef277d85b6c048c814b471f60bc4809194b6aee1a2b5304c"},"schema_version":"1.0","source":{"id":"2608.08460","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.08460","created_at":"2026-08-11T01:22:41Z"},{"alias_kind":"arxiv_version","alias_value":"2608.08460v1","created_at":"2026-08-11T01:22:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08460","created_at":"2026-08-11T01:22:41Z"},{"alias_kind":"pith_short_12","alias_value":"ZHXZUHZLSAO4","created_at":"2026-08-11T01:22:41Z"},{"alias_kind":"pith_short_16","alias_value":"ZHXZUHZLSAO4F3PN","created_at":"2026-08-11T01:22:41Z"},{"alias_kind":"pith_short_8","alias_value":"ZHXZUHZL","created_at":"2026-08-11T01:22:41Z"}],"graph_snapshots":[{"event_id":"sha256:499a2c0772a81ddd4d3045675acedca34079d9efdd7ff40027ae14f963acce8a","target":"graph","created_at":"2026-08-11T01:22:41Z","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/2608.08460/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Given textual task instructions, generating step-by-step visual instructions as an image sequence requires the simultaneous satisfaction of multiple properties, specifically step faithfulness, cross-image consistency, and per-frame visual quality. Existing text-to-image generation approaches rarely meet all three properties, owing to independent sampling that breaks consistency, finetuning on low-quality video that degrades per-frame quality, and frozen backbones that lack multi-step understanding. In this work, we propose InstructionCrafter, a diffusion-based framework with the key idea of se","authors_text":"Kazuhiro Fukui, Satoshi Iizuka, Shun Okamoto","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-09T04:01:21Z","title":"InstructionCrafter: Generating Consistent and High-Fidelity Visual Instructions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08460","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:bd1b10b8d6e28fb1a953c33e38d11806593666b89db8b2e8e12c38bc6d90f021","target":"record","created_at":"2026-08-11T01:22:41Z","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":"5c1e696a415d22e0d4db6e03b6cce776c8dd8025f8e7f9584c11dafb9397095d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-09T04:01:21Z","title_canon_sha256":"2f4981b4d731886bef277d85b6c048c814b471f60bc4809194b6aee1a2b5304c"},"schema_version":"1.0","source":{"id":"2608.08460","kind":"arxiv","version":1}},"canonical_sha256":"c9ef9a1f2b901dc2eded6032ca4b6958c51e6f938a80b136b24e3b0a3df8c091","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9ef9a1f2b901dc2eded6032ca4b6958c51e6f938a80b136b24e3b0a3df8c091","first_computed_at":"2026-08-11T01:22:41.319482Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T01:22:41.319482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eyeDZZ1wJJQE2/Ah9T91hYZOq8FL1HkhYh1Sop7O/5YdFpMIEQYa1SyKJu988W4TU0yDJpeXA0lBV86VN752Dw==","signature_status":"signed_v1","signed_at":"2026-08-11T01:22:41.321896Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.08460","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd1b10b8d6e28fb1a953c33e38d11806593666b89db8b2e8e12c38bc6d90f021","sha256:499a2c0772a81ddd4d3045675acedca34079d9efdd7ff40027ae14f963acce8a"],"state_sha256":"2db6b827071c4c81750d35b724d9a372e1e762a826329cfcc4b42a649804c28b"}