{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GWTJ2MGI6UQ22HWIJAM2RF6UEG","short_pith_number":"pith:GWTJ2MGI","schema_version":"1.0","canonical_sha256":"35a69d30c8f521ad1ec84819a897d421aa99f203d20cfed91147db173a85c140","source":{"kind":"arxiv","id":"2409.15278","version":4},"attestation_state":"computed","paper":{"title":"PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language Instructions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongsheng Li, Huan Teng, Junlin Xie, Le Zhuo, Peng Gao, Renrui Zhang, Shitian Zhao, Siyuan Huang, Weifeng Lin, Xinyu Wei, Yu Qiao","submitted_at":"2024-09-23T17:59:46Z","abstract_excerpt":"This paper presents a versatile image-to-image visual assistant, PixWizard, designed for image generation, manipulation, and translation based on free-from language instructions. To this end, we tackle a variety of vision tasks into a unified image-text-to-image generation framework and curate an Omni Pixel-to-Pixel Instruction-Tuning Dataset. By constructing detailed instruction templates in natural language, we comprehensively include a large set of diverse vision tasks such as text-to-image generation, image restoration, image grounding, dense image prediction, image editing, controllable g"},"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":"2409.15278","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-23T17:59:46Z","cross_cats_sorted":[],"title_canon_sha256":"6c319661bb2c58477596ea35806d0def462add489cb7515863bc32bce8f02fb2","abstract_canon_sha256":"04c96501d76e21144fadad994707cafafa8fe9bd3c4208ba88a477aebe9aaeea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:20:39.901739Z","signature_b64":"M5aKacVZNdMKawTxwS8M3WDjMQ0a1pPZe3Nf7PZ4IyA45LkfccCfsrWSxh3csla9ZPazFy3Xlagr9uysfynACg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35a69d30c8f521ad1ec84819a897d421aa99f203d20cfed91147db173a85c140","last_reissued_at":"2026-07-05T10:20:39.901166Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:20:39.901166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language Instructions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongsheng Li, Huan Teng, Junlin Xie, Le Zhuo, Peng Gao, Renrui Zhang, Shitian Zhao, Siyuan Huang, Weifeng Lin, Xinyu Wei, Yu Qiao","submitted_at":"2024-09-23T17:59:46Z","abstract_excerpt":"This paper presents a versatile image-to-image visual assistant, PixWizard, designed for image generation, manipulation, and translation based on free-from language instructions. To this end, we tackle a variety of vision tasks into a unified image-text-to-image generation framework and curate an Omni Pixel-to-Pixel Instruction-Tuning Dataset. By constructing detailed instruction templates in natural language, we comprehensively include a large set of diverse vision tasks such as text-to-image generation, image restoration, image grounding, dense image prediction, image editing, controllable g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15278","kind":"arxiv","version":4},"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/2409.15278/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":"2409.15278","created_at":"2026-07-05T10:20:39.901232+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.15278v4","created_at":"2026-07-05T10:20:39.901232+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15278","created_at":"2026-07-05T10:20:39.901232+00:00"},{"alias_kind":"pith_short_12","alias_value":"GWTJ2MGI6UQ2","created_at":"2026-07-05T10:20:39.901232+00:00"},{"alias_kind":"pith_short_16","alias_value":"GWTJ2MGI6UQ22HWI","created_at":"2026-07-05T10:20:39.901232+00:00"},{"alias_kind":"pith_short_8","alias_value":"GWTJ2MGI","created_at":"2026-07-05T10:20:39.901232+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20090","citing_title":"MetaEarth-MM: Unified Multimodal Remote Sensing Image Generation with Scene-centered Joint Modeling","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2507.01908","citing_title":"Reasoning to Edit: Hypothetical Instruction-Based Image Editing with Visual Reasoning","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2512.07348","citing_title":"MICo-150K: A Comprehensive Dataset Advancing Multi-Image Composition","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2509.20328","citing_title":"Video models are zero-shot learners and reasoners","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10859","citing_title":"Masked Generative Transformer Is What You Need for Image Editing","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09622","citing_title":"Any2Any 3D Diffusion Models with Knowledge Transfer: A Radiotherapy Planning Study","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23763","citing_title":"Edit Where You Mean: Region-Aware Adapter Injection for Mask-Free Local Image Editing","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04924","citing_title":"Your Pre-trained Diffusion Model Secretly Knows Restoration","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GWTJ2MGI6UQ22HWIJAM2RF6UEG","json":"https://pith.science/pith/GWTJ2MGI6UQ22HWIJAM2RF6UEG.json","graph_json":"https://pith.science/api/pith-number/GWTJ2MGI6UQ22HWIJAM2RF6UEG/graph.json","events_json":"https://pith.science/api/pith-number/GWTJ2MGI6UQ22HWIJAM2RF6UEG/events.json","paper":"https://pith.science/paper/GWTJ2MGI"},"agent_actions":{"view_html":"https://pith.science/pith/GWTJ2MGI6UQ22HWIJAM2RF6UEG","download_json":"https://pith.science/pith/GWTJ2MGI6UQ22HWIJAM2RF6UEG.json","view_paper":"https://pith.science/paper/GWTJ2MGI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.15278&json=true","fetch_graph":"https://pith.science/api/pith-number/GWTJ2MGI6UQ22HWIJAM2RF6UEG/graph.json","fetch_events":"https://pith.science/api/pith-number/GWTJ2MGI6UQ22HWIJAM2RF6UEG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GWTJ2MGI6UQ22HWIJAM2RF6UEG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GWTJ2MGI6UQ22HWIJAM2RF6UEG/action/storage_attestation","attest_author":"https://pith.science/pith/GWTJ2MGI6UQ22HWIJAM2RF6UEG/action/author_attestation","sign_citation":"https://pith.science/pith/GWTJ2MGI6UQ22HWIJAM2RF6UEG/action/citation_signature","submit_replication":"https://pith.science/pith/GWTJ2MGI6UQ22HWIJAM2RF6UEG/action/replication_record"}},"created_at":"2026-07-05T10:20:39.901232+00:00","updated_at":"2026-07-05T10:20:39.901232+00:00"}