{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:D5X3AOS7RQF3FJK2AMRXAWWYER","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":"01b620df83f35e0b4361d1df5b58499345a4797c4d85606b71a0cede775b9459","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-16T20:56:57Z","title_canon_sha256":"eecc5f174bebbcb4012eecd88441bfd268fdc2ac91b8920c6218b7f152070056"},"schema_version":"1.0","source":{"id":"2507.13401","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.13401","created_at":"2026-07-05T11:39:16Z"},{"alias_kind":"arxiv_version","alias_value":"2507.13401v1","created_at":"2026-07-05T11:39:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13401","created_at":"2026-07-05T11:39:16Z"},{"alias_kind":"pith_short_12","alias_value":"D5X3AOS7RQF3","created_at":"2026-07-05T11:39:16Z"},{"alias_kind":"pith_short_16","alias_value":"D5X3AOS7RQF3FJK2","created_at":"2026-07-05T11:39:16Z"},{"alias_kind":"pith_short_8","alias_value":"D5X3AOS7","created_at":"2026-07-05T11:39:16Z"}],"graph_snapshots":[{"event_id":"sha256:244f1e1cc3afc93e471181a862bcc1b7c1e4a61a46b160681433415b05719e24","target":"graph","created_at":"2026-07-05T11:39:16Z","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/2507.13401/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the remarkable success of diffusion models in text-to-image generation, their effectiveness in grounded visual editing and compositional control remains challenging. Motivated by advances in self-supervised learning and in-context generative modeling, we propose a series of simple yet powerful design choices that significantly enhance diffusion model capacity for structured, controllable generation and editing. We introduce Masking-Augmented Diffusion with Inference-Time Scaling (MADI), a framework that improves the editability, compositionality and controllability of diffusion models ","authors_text":"Fatih Porikli, Munawar Hyatt, Risheek Garrepalli, Shreya Kadambi, Shubhankar Borse","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-16T20:56:57Z","title":"MADI: Masking-Augmented Diffusion with Inference-Time Scaling for Visual Editing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13401","kind":"arxiv","version":1},"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":"sha256:31bea83014bf01d9c1eaa64128f3f1ea566b1b00c6883b087e8597b7d144d0ec","target":"record","created_at":"2026-07-05T11:39:16Z","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":"01b620df83f35e0b4361d1df5b58499345a4797c4d85606b71a0cede775b9459","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-16T20:56:57Z","title_canon_sha256":"eecc5f174bebbcb4012eecd88441bfd268fdc2ac91b8920c6218b7f152070056"},"schema_version":"1.0","source":{"id":"2507.13401","kind":"arxiv","version":1}},"canonical_sha256":"1f6fb03a5f8c0bb2a55a0323705ad8247578a8beebc9e9ec495fd6c8f025dab0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f6fb03a5f8c0bb2a55a0323705ad8247578a8beebc9e9ec495fd6c8f025dab0","first_computed_at":"2026-07-05T11:39:16.874419Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:39:16.874419Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cWq4kx2jgc6l8cniMl0Y0q9quTiQ37LJ5Pdf1VYRIHxOe+tWiMP2P+q2yyjUHihWikVmExNZzY5CbSRDfzPiBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:39:16.874888Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.13401","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:31bea83014bf01d9c1eaa64128f3f1ea566b1b00c6883b087e8597b7d144d0ec","sha256:244f1e1cc3afc93e471181a862bcc1b7c1e4a61a46b160681433415b05719e24"],"state_sha256":"1419e9a4c628f10c2e9441f964bfe28f82c930d0a4c18ebba0dbb3162b2ff2e6"}