{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CT5RIHBG5VSZVXOLD2XXXROXSW","short_pith_number":"pith:CT5RIHBG","schema_version":"1.0","canonical_sha256":"14fb141c26ed659addcb1eaf7bc5d7958e1d707d5b310bba91ef21b8ed504a6e","source":{"kind":"arxiv","id":"2312.06738","version":4},"attestation_state":"computed","paper":{"title":"InstructAny2Pix: Flexible Visual Editing via Multimodal Instruction Following","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aditya Grover, Harkanwar Singh, Shufan Li","submitted_at":"2023-12-11T17:53:45Z","abstract_excerpt":"The ability to provide fine-grained control for generating and editing visual imagery has profound implications for computer vision and its applications. Previous works have explored extending controllability in two directions: instruction tuning with text-based prompts and multi-modal conditioning. However, these works make one or more unnatural assumptions on the number and/or type of modality inputs used to express controllability. We propose InstructAny2Pix, a flexible multi-modal instruction-following system that enables users to edit an input image using instructions involving audio, ima"},"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":"2312.06738","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T17:53:45Z","cross_cats_sorted":[],"title_canon_sha256":"f6343b558e25980e17d2f509795ec3cd9bcb589a34417175ec9eb2cac9c3f1c3","abstract_canon_sha256":"8e5988ffcf58f69dea204490dcbe1d9a3be738e5bdc65e021c1e8e082ed13fe7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:39.115711Z","signature_b64":"O4Wi7+hIfipeGJ0MbmLaIv9XBATYvKR4WBJCsEhC0FxSM6chKIG9U+M2T0bdi3VBuMZafDzD2DKcM1SZnMniBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14fb141c26ed659addcb1eaf7bc5d7958e1d707d5b310bba91ef21b8ed504a6e","last_reissued_at":"2026-07-05T09:21:39.115136Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:39.115136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InstructAny2Pix: Flexible Visual Editing via Multimodal Instruction Following","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aditya Grover, Harkanwar Singh, Shufan Li","submitted_at":"2023-12-11T17:53:45Z","abstract_excerpt":"The ability to provide fine-grained control for generating and editing visual imagery has profound implications for computer vision and its applications. Previous works have explored extending controllability in two directions: instruction tuning with text-based prompts and multi-modal conditioning. However, these works make one or more unnatural assumptions on the number and/or type of modality inputs used to express controllability. We propose InstructAny2Pix, a flexible multi-modal instruction-following system that enables users to edit an input image using instructions involving audio, ima"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06738","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/2312.06738/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":"2312.06738","created_at":"2026-07-05T09:21:39.115193+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.06738v4","created_at":"2026-07-05T09:21:39.115193+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06738","created_at":"2026-07-05T09:21:39.115193+00:00"},{"alias_kind":"pith_short_12","alias_value":"CT5RIHBG5VSZ","created_at":"2026-07-05T09:21:39.115193+00:00"},{"alias_kind":"pith_short_16","alias_value":"CT5RIHBG5VSZVXOL","created_at":"2026-07-05T09:21:39.115193+00:00"},{"alias_kind":"pith_short_8","alias_value":"CT5RIHBG","created_at":"2026-07-05T09:21:39.115193+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05071","citing_title":"InstantRetouch: Efficient and High-Fidelity Instruction-Guided Image Retouching with Bilateral Space","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29308","citing_title":"MirrorPPR: Exemplar-Based Portrait Photo Retouching","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2505.20275","citing_title":"ImgEdit: A Unified Image Editing Dataset and Benchmark","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CT5RIHBG5VSZVXOLD2XXXROXSW","json":"https://pith.science/pith/CT5RIHBG5VSZVXOLD2XXXROXSW.json","graph_json":"https://pith.science/api/pith-number/CT5RIHBG5VSZVXOLD2XXXROXSW/graph.json","events_json":"https://pith.science/api/pith-number/CT5RIHBG5VSZVXOLD2XXXROXSW/events.json","paper":"https://pith.science/paper/CT5RIHBG"},"agent_actions":{"view_html":"https://pith.science/pith/CT5RIHBG5VSZVXOLD2XXXROXSW","download_json":"https://pith.science/pith/CT5RIHBG5VSZVXOLD2XXXROXSW.json","view_paper":"https://pith.science/paper/CT5RIHBG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.06738&json=true","fetch_graph":"https://pith.science/api/pith-number/CT5RIHBG5VSZVXOLD2XXXROXSW/graph.json","fetch_events":"https://pith.science/api/pith-number/CT5RIHBG5VSZVXOLD2XXXROXSW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CT5RIHBG5VSZVXOLD2XXXROXSW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CT5RIHBG5VSZVXOLD2XXXROXSW/action/storage_attestation","attest_author":"https://pith.science/pith/CT5RIHBG5VSZVXOLD2XXXROXSW/action/author_attestation","sign_citation":"https://pith.science/pith/CT5RIHBG5VSZVXOLD2XXXROXSW/action/citation_signature","submit_replication":"https://pith.science/pith/CT5RIHBG5VSZVXOLD2XXXROXSW/action/replication_record"}},"created_at":"2026-07-05T09:21:39.115193+00:00","updated_at":"2026-07-05T09:21:39.115193+00:00"}