{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZHXZUHZLSAO4F3PNMAZMUS3JLD","short_pith_number":"pith:ZHXZUHZL","schema_version":"1.0","canonical_sha256":"c9ef9a1f2b901dc2eded6032ca4b6958c51e6f938a80b136b24e3b0a3df8c091","source":{"kind":"arxiv","id":"2608.08460","version":1},"attestation_state":"computed","paper":{"title":"InstructionCrafter: Generating Consistent and High-Fidelity Visual Instructions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kazuhiro Fukui, Satoshi Iizuka, Shun Okamoto","submitted_at":"2026-08-09T04:01:21Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.08460","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-09T04:01:21Z","cross_cats_sorted":[],"title_canon_sha256":"2f4981b4d731886bef277d85b6c048c814b471f60bc4809194b6aee1a2b5304c","abstract_canon_sha256":"5c1e696a415d22e0d4db6e03b6cce776c8dd8025f8e7f9584c11dafb9397095d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T01:22:41.321896Z","signature_b64":"eyeDZZ1wJJQE2/Ah9T91hYZOq8FL1HkhYh1Sop7O/5YdFpMIEQYa1SyKJu988W4TU0yDJpeXA0lBV86VN752Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9ef9a1f2b901dc2eded6032ca4b6958c51e6f938a80b136b24e3b0a3df8c091","last_reissued_at":"2026-08-11T01:22:41.319482Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T01:22:41.319482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InstructionCrafter: Generating Consistent and High-Fidelity Visual Instructions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kazuhiro Fukui, Satoshi Iizuka, Shun Okamoto","submitted_at":"2026-08-09T04:01:21Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08460","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2608.08460/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.08460","created_at":"2026-08-11T01:22:41.320238+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.08460v1","created_at":"2026-08-11T01:22:41.320238+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08460","created_at":"2026-08-11T01:22:41.320238+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZHXZUHZLSAO4","created_at":"2026-08-11T01:22:41.320238+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZHXZUHZLSAO4F3PN","created_at":"2026-08-11T01:22:41.320238+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZHXZUHZL","created_at":"2026-08-11T01:22:41.320238+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZHXZUHZLSAO4F3PNMAZMUS3JLD","json":"https://pith.science/pith/ZHXZUHZLSAO4F3PNMAZMUS3JLD.json","graph_json":"https://pith.science/api/pith-number/ZHXZUHZLSAO4F3PNMAZMUS3JLD/graph.json","events_json":"https://pith.science/api/pith-number/ZHXZUHZLSAO4F3PNMAZMUS3JLD/events.json","paper":"https://pith.science/paper/ZHXZUHZL"},"agent_actions":{"view_html":"https://pith.science/pith/ZHXZUHZLSAO4F3PNMAZMUS3JLD","download_json":"https://pith.science/pith/ZHXZUHZLSAO4F3PNMAZMUS3JLD.json","view_paper":"https://pith.science/paper/ZHXZUHZL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.08460&json=true","fetch_graph":"https://pith.science/api/pith-number/ZHXZUHZLSAO4F3PNMAZMUS3JLD/graph.json","fetch_events":"https://pith.science/api/pith-number/ZHXZUHZLSAO4F3PNMAZMUS3JLD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZHXZUHZLSAO4F3PNMAZMUS3JLD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZHXZUHZLSAO4F3PNMAZMUS3JLD/action/storage_attestation","attest_author":"https://pith.science/pith/ZHXZUHZLSAO4F3PNMAZMUS3JLD/action/author_attestation","sign_citation":"https://pith.science/pith/ZHXZUHZLSAO4F3PNMAZMUS3JLD/action/citation_signature","submit_replication":"https://pith.science/pith/ZHXZUHZLSAO4F3PNMAZMUS3JLD/action/replication_record"}},"created_at":"2026-08-11T01:22:41.320238+00:00","updated_at":"2026-08-11T01:22:41.320238+00:00"}