{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:C4OVUXBTN3XBJOJ4AI4YJYYLRH","short_pith_number":"pith:C4OVUXBT","schema_version":"1.0","canonical_sha256":"171d5a5c336eee14b93c023984e30b89d3084ea39d61ff2c81c09e15565e19e3","source":{"kind":"arxiv","id":"2506.06733","version":3},"attestation_state":"computed","paper":{"title":"RecipeGen: A Step-Aligned Multimodal Benchmark for Real-World Recipe Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Wen, Chenming Zhang, Hong-Han Shuai, Hongxia Xie, Jidong Gao, Ruoxuan Zhang, Wen-Huang Cheng","submitted_at":"2025-06-07T09:35:35Z","abstract_excerpt":"Creating recipe images is a key challenge in food computing, with applications in culinary education and multimodal recipe assistants. However, existing datasets lack fine-grained alignment between recipe goals, step-wise instructions, and visual content. We present RecipeGen, the first large-scale, real-world benchmark for recipe-based Text-to-Image (T2I), Image-to-Video (I2V), and Text-to-Video (T2V) generation. RecipeGen contains 26,453 recipes, 196,724 images, and 4,491 videos, covering diverse ingredients, cooking procedures, styles, and dish types. We further propose domain-specific eval"},"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":"2506.06733","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-07T09:35:35Z","cross_cats_sorted":[],"title_canon_sha256":"ad2d4cca042b53c3675dcd537408575597ce5da0dfa20cd60c682d04b92df2a8","abstract_canon_sha256":"ebf9a5f955b7503a4f3347c0a396c04986857f221580f076fa33269dc863bfa8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:28.557646Z","signature_b64":"a7qN3Av6fuUG7PmVvPOqIiYfWfof6RqtyD+N/J8DKW+T/4Ljdf3Ek48rU4PIIxfWYEe7FsepQNUxeGHkdsOhCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"171d5a5c336eee14b93c023984e30b89d3084ea39d61ff2c81c09e15565e19e3","last_reissued_at":"2026-07-05T11:19:28.557058Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:28.557058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RecipeGen: A Step-Aligned Multimodal Benchmark for Real-World Recipe Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Wen, Chenming Zhang, Hong-Han Shuai, Hongxia Xie, Jidong Gao, Ruoxuan Zhang, Wen-Huang Cheng","submitted_at":"2025-06-07T09:35:35Z","abstract_excerpt":"Creating recipe images is a key challenge in food computing, with applications in culinary education and multimodal recipe assistants. However, existing datasets lack fine-grained alignment between recipe goals, step-wise instructions, and visual content. We present RecipeGen, the first large-scale, real-world benchmark for recipe-based Text-to-Image (T2I), Image-to-Video (I2V), and Text-to-Video (T2V) generation. RecipeGen contains 26,453 recipes, 196,724 images, and 4,491 videos, covering diverse ingredients, cooking procedures, styles, and dish types. We further propose domain-specific eval"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06733","kind":"arxiv","version":3},"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/2506.06733/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":"2506.06733","created_at":"2026-07-05T11:19:28.557133+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.06733v3","created_at":"2026-07-05T11:19:28.557133+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06733","created_at":"2026-07-05T11:19:28.557133+00:00"},{"alias_kind":"pith_short_12","alias_value":"C4OVUXBTN3XB","created_at":"2026-07-05T11:19:28.557133+00:00"},{"alias_kind":"pith_short_16","alias_value":"C4OVUXBTN3XBJOJ4","created_at":"2026-07-05T11:19:28.557133+00:00"},{"alias_kind":"pith_short_8","alias_value":"C4OVUXBT","created_at":"2026-07-05T11:19:28.557133+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/C4OVUXBTN3XBJOJ4AI4YJYYLRH","json":"https://pith.science/pith/C4OVUXBTN3XBJOJ4AI4YJYYLRH.json","graph_json":"https://pith.science/api/pith-number/C4OVUXBTN3XBJOJ4AI4YJYYLRH/graph.json","events_json":"https://pith.science/api/pith-number/C4OVUXBTN3XBJOJ4AI4YJYYLRH/events.json","paper":"https://pith.science/paper/C4OVUXBT"},"agent_actions":{"view_html":"https://pith.science/pith/C4OVUXBTN3XBJOJ4AI4YJYYLRH","download_json":"https://pith.science/pith/C4OVUXBTN3XBJOJ4AI4YJYYLRH.json","view_paper":"https://pith.science/paper/C4OVUXBT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.06733&json=true","fetch_graph":"https://pith.science/api/pith-number/C4OVUXBTN3XBJOJ4AI4YJYYLRH/graph.json","fetch_events":"https://pith.science/api/pith-number/C4OVUXBTN3XBJOJ4AI4YJYYLRH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C4OVUXBTN3XBJOJ4AI4YJYYLRH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C4OVUXBTN3XBJOJ4AI4YJYYLRH/action/storage_attestation","attest_author":"https://pith.science/pith/C4OVUXBTN3XBJOJ4AI4YJYYLRH/action/author_attestation","sign_citation":"https://pith.science/pith/C4OVUXBTN3XBJOJ4AI4YJYYLRH/action/citation_signature","submit_replication":"https://pith.science/pith/C4OVUXBTN3XBJOJ4AI4YJYYLRH/action/replication_record"}},"created_at":"2026-07-05T11:19:28.557133+00:00","updated_at":"2026-07-05T11:19:28.557133+00:00"}