{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QZZZN44SQZGDR4F7ZB5IVHPUOR","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":"739a27aed224136ec542ea1a2a4307442275e1a89ad0fbbecd1426f18320624f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-28T18:21:08Z","title_canon_sha256":"0347f15d39a4c26d01b08c939c4f7ee621e6c635ca7a47cbf453f487951bf15e"},"schema_version":"1.0","source":{"id":"2502.21291","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.21291","created_at":"2026-07-05T11:44:01Z"},{"alias_kind":"arxiv_version","alias_value":"2502.21291v4","created_at":"2026-07-05T11:44:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.21291","created_at":"2026-07-05T11:44:01Z"},{"alias_kind":"pith_short_12","alias_value":"QZZZN44SQZGD","created_at":"2026-07-05T11:44:01Z"},{"alias_kind":"pith_short_16","alias_value":"QZZZN44SQZGDR4F7","created_at":"2026-07-05T11:44:01Z"},{"alias_kind":"pith_short_8","alias_value":"QZZZN44S","created_at":"2026-07-05T11:44:01Z"}],"graph_snapshots":[{"event_id":"sha256:1352cd87b617809557323ef500ff1c9b9b351738edeb0ec46e15c9eb4b0cd299","target":"graph","created_at":"2026-07-05T11:44:01Z","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/2502.21291/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite significant progress in diffusion-based image generation, subject-driven generation and instruction-based editing remain challenging. Existing methods typically treat them separately, struggling with limited high-quality data and poor generalization. However, both tasks require capturing complex visual variations while maintaining consistency between inputs and outputs. Inspired by this, we propose MIGE, a unified framework that standardizes task representations using multimodal instructions. It first treats subject-driven generation as creation on a blank canvas and instruction-based ","authors_text":"Bingbing Xu, Huawei Shen, Wei Li, Xueyun Tian, Yige Yuan, Yuanzhuo Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-28T18:21:08Z","title":"MIGE: Mutually Enhanced Multimodal Instruction-Based Image Generation and Editing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.21291","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":"sha256:3d7d9e313075d859b0af6674ebd492e97fe1b33a17e8eb60816200bc651cb011","target":"record","created_at":"2026-07-05T11:44:01Z","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":"739a27aed224136ec542ea1a2a4307442275e1a89ad0fbbecd1426f18320624f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-28T18:21:08Z","title_canon_sha256":"0347f15d39a4c26d01b08c939c4f7ee621e6c635ca7a47cbf453f487951bf15e"},"schema_version":"1.0","source":{"id":"2502.21291","kind":"arxiv","version":4}},"canonical_sha256":"867396f392864c38f0bfc87a8a9df4745c4a8c34c1102b5bbee95af46a2163d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"867396f392864c38f0bfc87a8a9df4745c4a8c34c1102b5bbee95af46a2163d7","first_computed_at":"2026-07-05T11:44:01.741975Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:44:01.741975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lNUb2RjTQUX8gE8iGfW1TP3sBqNaqO0+2QU+SM00aELq/nI8I5FQd0zlxbVXjkZ1b/OsF+2jH2R5nEWIFkykCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:44:01.742441Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.21291","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d7d9e313075d859b0af6674ebd492e97fe1b33a17e8eb60816200bc651cb011","sha256:1352cd87b617809557323ef500ff1c9b9b351738edeb0ec46e15c9eb4b0cd299"],"state_sha256":"30edddf639c5f56f94442dc63a566c8e7148e35bdfcacf75067723e8c3323303"}