{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6ATDHDUXWMNZRSFAL2KIKKGR3T","short_pith_number":"pith:6ATDHDUX","schema_version":"1.0","canonical_sha256":"f026338e97b31b98c8a05e948528d1dce02ee5eccf2d0c006e8d134737cf0a75","source":{"kind":"arxiv","id":"2605.20807","version":1},"attestation_state":"computed","paper":{"title":"Decomposing Subject-Driven Image Generation via Intermediate Structural Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanzhong Guo, Yizhou Yu","submitted_at":"2026-05-20T06:58:52Z","abstract_excerpt":"Subject-driven text-to-image generation still struggles to preserve high-frequency identity details such as logos, patterns, and text. Existing methods typically operate directly in RGB space, which often leads to detail degradation under substantial edits. We propose a two-stage framework that decouples structure from appearance by first predicting a Canny map and then rendering the final image conditioned on both the source appearance and the predicted structure. To improve text handling, we further introduce a fully automatic pipeline that constructs a 100k-pair text-aware dataset with cros"},"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":"2605.20807","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T06:58:52Z","cross_cats_sorted":[],"title_canon_sha256":"0ae6115cc3c6985fa13635dae56c74ca153cb3eb4c52372bda7746ca1485b48f","abstract_canon_sha256":"0df59ad12fab6feb2e5733b0b83a84e218893c8192304d0e394fff542f63367b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:55.541584Z","signature_b64":"EQnDNzl7BQeRICc0Oo4m37zerUW855FTeMo/XUyJojsznj9F5n8S8Xggmhh4lkFL1ZlqgJBIP95dvrWGz0KSDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f026338e97b31b98c8a05e948528d1dce02ee5eccf2d0c006e8d134737cf0a75","last_reissued_at":"2026-05-21T01:04:55.540873Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:55.540873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decomposing Subject-Driven Image Generation via Intermediate Structural Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanzhong Guo, Yizhou Yu","submitted_at":"2026-05-20T06:58:52Z","abstract_excerpt":"Subject-driven text-to-image generation still struggles to preserve high-frequency identity details such as logos, patterns, and text. Existing methods typically operate directly in RGB space, which often leads to detail degradation under substantial edits. We propose a two-stage framework that decouples structure from appearance by first predicting a Canny map and then rendering the final image conditioned on both the source appearance and the predicted structure. To improve text handling, we further introduce a fully automatic pipeline that constructs a 100k-pair text-aware dataset with cros"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20807","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/2605.20807/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":"2605.20807","created_at":"2026-05-21T01:04:55.540986+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.20807v1","created_at":"2026-05-21T01:04:55.540986+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20807","created_at":"2026-05-21T01:04:55.540986+00:00"},{"alias_kind":"pith_short_12","alias_value":"6ATDHDUXWMNZ","created_at":"2026-05-21T01:04:55.540986+00:00"},{"alias_kind":"pith_short_16","alias_value":"6ATDHDUXWMNZRSFA","created_at":"2026-05-21T01:04:55.540986+00:00"},{"alias_kind":"pith_short_8","alias_value":"6ATDHDUX","created_at":"2026-05-21T01:04:55.540986+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/6ATDHDUXWMNZRSFAL2KIKKGR3T","json":"https://pith.science/pith/6ATDHDUXWMNZRSFAL2KIKKGR3T.json","graph_json":"https://pith.science/api/pith-number/6ATDHDUXWMNZRSFAL2KIKKGR3T/graph.json","events_json":"https://pith.science/api/pith-number/6ATDHDUXWMNZRSFAL2KIKKGR3T/events.json","paper":"https://pith.science/paper/6ATDHDUX"},"agent_actions":{"view_html":"https://pith.science/pith/6ATDHDUXWMNZRSFAL2KIKKGR3T","download_json":"https://pith.science/pith/6ATDHDUXWMNZRSFAL2KIKKGR3T.json","view_paper":"https://pith.science/paper/6ATDHDUX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.20807&json=true","fetch_graph":"https://pith.science/api/pith-number/6ATDHDUXWMNZRSFAL2KIKKGR3T/graph.json","fetch_events":"https://pith.science/api/pith-number/6ATDHDUXWMNZRSFAL2KIKKGR3T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6ATDHDUXWMNZRSFAL2KIKKGR3T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6ATDHDUXWMNZRSFAL2KIKKGR3T/action/storage_attestation","attest_author":"https://pith.science/pith/6ATDHDUXWMNZRSFAL2KIKKGR3T/action/author_attestation","sign_citation":"https://pith.science/pith/6ATDHDUXWMNZRSFAL2KIKKGR3T/action/citation_signature","submit_replication":"https://pith.science/pith/6ATDHDUXWMNZRSFAL2KIKKGR3T/action/replication_record"}},"created_at":"2026-05-21T01:04:55.540986+00:00","updated_at":"2026-05-21T01:04:55.540986+00:00"}