{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CT5RIHBG5VSZVXOLD2XXXROXSW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8e5988ffcf58f69dea204490dcbe1d9a3be738e5bdc65e021c1e8e082ed13fe7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T17:53:45Z","title_canon_sha256":"f6343b558e25980e17d2f509795ec3cd9bcb589a34417175ec9eb2cac9c3f1c3"},"schema_version":"1.0","source":{"id":"2312.06738","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.06738","created_at":"2026-07-05T09:21:39Z"},{"alias_kind":"arxiv_version","alias_value":"2312.06738v4","created_at":"2026-07-05T09:21:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06738","created_at":"2026-07-05T09:21:39Z"},{"alias_kind":"pith_short_12","alias_value":"CT5RIHBG5VSZ","created_at":"2026-07-05T09:21:39Z"},{"alias_kind":"pith_short_16","alias_value":"CT5RIHBG5VSZVXOL","created_at":"2026-07-05T09:21:39Z"},{"alias_kind":"pith_short_8","alias_value":"CT5RIHBG","created_at":"2026-07-05T09:21:39Z"}],"graph_snapshots":[{"event_id":"sha256:b43674128b57e2323ef8c945841cba6bbfd6126b98982a2f27c4f186ce1d01f1","target":"graph","created_at":"2026-07-05T09:21:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2312.06738/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aditya Grover, Harkanwar Singh, Shufan Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T17:53:45Z","title":"InstructAny2Pix: Flexible Visual Editing via Multimodal Instruction Following"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06738","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7e6f42648f633051385b80cc731b8c230b9616bbe85f3c3008b5afb18fc12de7","target":"record","created_at":"2026-07-05T09:21:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8e5988ffcf58f69dea204490dcbe1d9a3be738e5bdc65e021c1e8e082ed13fe7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T17:53:45Z","title_canon_sha256":"f6343b558e25980e17d2f509795ec3cd9bcb589a34417175ec9eb2cac9c3f1c3"},"schema_version":"1.0","source":{"id":"2312.06738","kind":"arxiv","version":4}},"canonical_sha256":"14fb141c26ed659addcb1eaf7bc5d7958e1d707d5b310bba91ef21b8ed504a6e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"14fb141c26ed659addcb1eaf7bc5d7958e1d707d5b310bba91ef21b8ed504a6e","first_computed_at":"2026-07-05T09:21:39.115136Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:21:39.115136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O4Wi7+hIfipeGJ0MbmLaIv9XBATYvKR4WBJCsEhC0FxSM6chKIG9U+M2T0bdi3VBuMZafDzD2DKcM1SZnMniBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:21:39.115711Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.06738","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e6f42648f633051385b80cc731b8c230b9616bbe85f3c3008b5afb18fc12de7","sha256:b43674128b57e2323ef8c945841cba6bbfd6126b98982a2f27c4f186ce1d01f1"],"state_sha256":"6c1033cef4e3fdf560bee426a544bf6b8cc87b5618b8c9797b5338a4016354ab"}