{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OKO3HMQ6F75SZJ5IJFNRYC7HXV","short_pith_number":"pith:OKO3HMQ6","schema_version":"1.0","canonical_sha256":"729db3b21e2ffb2ca7a8495b1c0be7bd57c175400114ba809f65cce6ef6ea67c","source":{"kind":"arxiv","id":"2502.07556","version":1},"attestation_state":"computed","paper":{"title":"SketchFlex: Facilitating Spatial-Semantic Coherence in Text-to-Image Generation with Region-Based Sketches","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.HC","authors_text":"Haichuan Lin, Jiazhi Xia, Wei Zeng, Yilin Ye","submitted_at":"2025-02-11T13:48:11Z","abstract_excerpt":"Text-to-image models can generate visually appealing images from text descriptions. Efforts have been devoted to improving model controls with prompt tuning and spatial conditioning. However, our formative study highlights the challenges for non-expert users in crafting appropriate prompts and specifying fine-grained spatial conditions (e.g., depth or canny references) to generate semantically cohesive images, especially when multiple objects are involved. In response, we introduce SketchFlex, an interactive system designed to improve the flexibility of spatially conditioned image generation u"},"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":"2502.07556","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2025-02-11T13:48:11Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"f33e14b41bd07353af598e32ea68d4c958d86b48c40adc94a1eb9bf720eaa7bd","abstract_canon_sha256":"807fa3ff20b6d155f6de412166a00bda493948792df7d4f42792bfa3cbd7ae70"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:39.159509Z","signature_b64":"GXzqUIFanrRxwfXblO3DRcyQcW4wmE7479p6TQyO7mYJaDlU806i4ApsTr9Jm0VfvBAkOzjZhJfMLzgN/AyYAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"729db3b21e2ffb2ca7a8495b1c0be7bd57c175400114ba809f65cce6ef6ea67c","last_reissued_at":"2026-07-05T10:12:39.159093Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:39.159093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SketchFlex: Facilitating Spatial-Semantic Coherence in Text-to-Image Generation with Region-Based Sketches","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.HC","authors_text":"Haichuan Lin, Jiazhi Xia, Wei Zeng, Yilin Ye","submitted_at":"2025-02-11T13:48:11Z","abstract_excerpt":"Text-to-image models can generate visually appealing images from text descriptions. Efforts have been devoted to improving model controls with prompt tuning and spatial conditioning. However, our formative study highlights the challenges for non-expert users in crafting appropriate prompts and specifying fine-grained spatial conditions (e.g., depth or canny references) to generate semantically cohesive images, especially when multiple objects are involved. In response, we introduce SketchFlex, an interactive system designed to improve the flexibility of spatially conditioned image generation u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07556","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/2502.07556/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":"2502.07556","created_at":"2026-07-05T10:12:39.159150+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.07556v1","created_at":"2026-07-05T10:12:39.159150+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07556","created_at":"2026-07-05T10:12:39.159150+00:00"},{"alias_kind":"pith_short_12","alias_value":"OKO3HMQ6F75S","created_at":"2026-07-05T10:12:39.159150+00:00"},{"alias_kind":"pith_short_16","alias_value":"OKO3HMQ6F75SZJ5I","created_at":"2026-07-05T10:12:39.159150+00:00"},{"alias_kind":"pith_short_8","alias_value":"OKO3HMQ6","created_at":"2026-07-05T10:12:39.159150+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.15227","citing_title":"GenTune: Toward Traceable Prompts to Improve Controllability of Image Refinement in Environment Design","ref_index":72,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OKO3HMQ6F75SZJ5IJFNRYC7HXV","json":"https://pith.science/pith/OKO3HMQ6F75SZJ5IJFNRYC7HXV.json","graph_json":"https://pith.science/api/pith-number/OKO3HMQ6F75SZJ5IJFNRYC7HXV/graph.json","events_json":"https://pith.science/api/pith-number/OKO3HMQ6F75SZJ5IJFNRYC7HXV/events.json","paper":"https://pith.science/paper/OKO3HMQ6"},"agent_actions":{"view_html":"https://pith.science/pith/OKO3HMQ6F75SZJ5IJFNRYC7HXV","download_json":"https://pith.science/pith/OKO3HMQ6F75SZJ5IJFNRYC7HXV.json","view_paper":"https://pith.science/paper/OKO3HMQ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.07556&json=true","fetch_graph":"https://pith.science/api/pith-number/OKO3HMQ6F75SZJ5IJFNRYC7HXV/graph.json","fetch_events":"https://pith.science/api/pith-number/OKO3HMQ6F75SZJ5IJFNRYC7HXV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OKO3HMQ6F75SZJ5IJFNRYC7HXV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OKO3HMQ6F75SZJ5IJFNRYC7HXV/action/storage_attestation","attest_author":"https://pith.science/pith/OKO3HMQ6F75SZJ5IJFNRYC7HXV/action/author_attestation","sign_citation":"https://pith.science/pith/OKO3HMQ6F75SZJ5IJFNRYC7HXV/action/citation_signature","submit_replication":"https://pith.science/pith/OKO3HMQ6F75SZJ5IJFNRYC7HXV/action/replication_record"}},"created_at":"2026-07-05T10:12:39.159150+00:00","updated_at":"2026-07-05T10:12:39.159150+00:00"}