{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:M7Z3SWKZ7NBTQTWG5QWWDLNE7R","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":"42716ad52140d13a6210a3d9da61f99f0f560a30f6bb996828e50ad027caa0a7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T00:10:27Z","title_canon_sha256":"65c5c70ef1f6e92ee9ec1f82d33d5d7a7738ab50135f329bb615ea306d7e65c4"},"schema_version":"1.0","source":{"id":"2411.17949","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.17949","created_at":"2026-07-05T09:41:09Z"},{"alias_kind":"arxiv_version","alias_value":"2411.17949v1","created_at":"2026-07-05T09:41:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17949","created_at":"2026-07-05T09:41:09Z"},{"alias_kind":"pith_short_12","alias_value":"M7Z3SWKZ7NBT","created_at":"2026-07-05T09:41:09Z"},{"alias_kind":"pith_short_16","alias_value":"M7Z3SWKZ7NBTQTWG","created_at":"2026-07-05T09:41:09Z"},{"alias_kind":"pith_short_8","alias_value":"M7Z3SWKZ","created_at":"2026-07-05T09:41:09Z"}],"graph_snapshots":[{"event_id":"sha256:d4dbc3c4fc54ffd728bcdca66ca15d4ab03d2c497323e101bf114357b8199399","target":"graph","created_at":"2026-07-05T09:41:09Z","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/2411.17949/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Natural language often struggles to accurately associate positional and attribute information with multiple instances, which limits current text-based visual generation models to simpler compositions featuring only a few dominant instances. To address this limitation, this work enhances diffusion models by introducing regional instance control, where each instance is governed by a bounding box paired with a free-form caption. Previous methods in this area typically rely on implicit position encoding or explicit attention masks to separate regions of interest (ROIs), resulting in either inaccur","authors_text":"Kevin Qinghong Lin, Licheng Yu, Mike Zheng Shou, Pingchuan Ma, Yipin Zhou, Yixin Nie, Yuchao Gu, Yunfan Ye","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T00:10:27Z","title":"ROICtrl: Boosting Instance Control for Visual Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17949","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":"sha256:8038865df5b52f3de6cdd12eede2aefd191319405e77f5519d763ab861e7b4c4","target":"record","created_at":"2026-07-05T09:41:09Z","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":"42716ad52140d13a6210a3d9da61f99f0f560a30f6bb996828e50ad027caa0a7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T00:10:27Z","title_canon_sha256":"65c5c70ef1f6e92ee9ec1f82d33d5d7a7738ab50135f329bb615ea306d7e65c4"},"schema_version":"1.0","source":{"id":"2411.17949","kind":"arxiv","version":1}},"canonical_sha256":"67f3b95959fb43384ec6ec2d61ada4fc70538d206cbd5d786b2baab8950f1b53","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67f3b95959fb43384ec6ec2d61ada4fc70538d206cbd5d786b2baab8950f1b53","first_computed_at":"2026-07-05T09:41:09.338526Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:41:09.338526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"flWheEJkjFFGWQcV4T3J9nrJBArekObAY+sjYWGEcLgx7rtI4TvCXK8VwwgbGSTubMVtUwhNhE7eaCpMq1kaDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:41:09.338932Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.17949","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8038865df5b52f3de6cdd12eede2aefd191319405e77f5519d763ab861e7b4c4","sha256:d4dbc3c4fc54ffd728bcdca66ca15d4ab03d2c497323e101bf114357b8199399"],"state_sha256":"0bb9cb81ac3e72ea913c483c0ae95f0728f88aa3d4f2c11ea840000e4293f716"}