{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M7Z3SWKZ7NBTQTWG5QWWDLNE7R","short_pith_number":"pith:M7Z3SWKZ","schema_version":"1.0","canonical_sha256":"67f3b95959fb43384ec6ec2d61ada4fc70538d206cbd5d786b2baab8950f1b53","source":{"kind":"arxiv","id":"2411.17949","version":1},"attestation_state":"computed","paper":{"title":"ROICtrl: Boosting Instance Control for Visual Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kevin Qinghong Lin, Licheng Yu, Mike Zheng Shou, Pingchuan Ma, Yipin Zhou, Yixin Nie, Yuchao Gu, Yunfan Ye","submitted_at":"2024-11-27T00:10:27Z","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"},"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":"2411.17949","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T00:10:27Z","cross_cats_sorted":[],"title_canon_sha256":"65c5c70ef1f6e92ee9ec1f82d33d5d7a7738ab50135f329bb615ea306d7e65c4","abstract_canon_sha256":"42716ad52140d13a6210a3d9da61f99f0f560a30f6bb996828e50ad027caa0a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:09.338932Z","signature_b64":"flWheEJkjFFGWQcV4T3J9nrJBArekObAY+sjYWGEcLgx7rtI4TvCXK8VwwgbGSTubMVtUwhNhE7eaCpMq1kaDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67f3b95959fb43384ec6ec2d61ada4fc70538d206cbd5d786b2baab8950f1b53","last_reissued_at":"2026-07-05T09:41:09.338526Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:09.338526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ROICtrl: Boosting Instance Control for Visual Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kevin Qinghong Lin, Licheng Yu, Mike Zheng Shou, Pingchuan Ma, Yipin Zhou, Yixin Nie, Yuchao Gu, Yunfan Ye","submitted_at":"2024-11-27T00:10:27Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17949","kind":"arxiv","version":1},"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/2411.17949/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":"2411.17949","created_at":"2026-07-05T09:41:09.338589+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.17949v1","created_at":"2026-07-05T09:41:09.338589+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17949","created_at":"2026-07-05T09:41:09.338589+00:00"},{"alias_kind":"pith_short_12","alias_value":"M7Z3SWKZ7NBT","created_at":"2026-07-05T09:41:09.338589+00:00"},{"alias_kind":"pith_short_16","alias_value":"M7Z3SWKZ7NBTQTWG","created_at":"2026-07-05T09:41:09.338589+00:00"},{"alias_kind":"pith_short_8","alias_value":"M7Z3SWKZ","created_at":"2026-07-05T09:41:09.338589+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.01107","citing_title":"FICGen: Frequency-Inspired Contextual Disentanglement for Layout-driven Degraded Image Generation","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M7Z3SWKZ7NBTQTWG5QWWDLNE7R","json":"https://pith.science/pith/M7Z3SWKZ7NBTQTWG5QWWDLNE7R.json","graph_json":"https://pith.science/api/pith-number/M7Z3SWKZ7NBTQTWG5QWWDLNE7R/graph.json","events_json":"https://pith.science/api/pith-number/M7Z3SWKZ7NBTQTWG5QWWDLNE7R/events.json","paper":"https://pith.science/paper/M7Z3SWKZ"},"agent_actions":{"view_html":"https://pith.science/pith/M7Z3SWKZ7NBTQTWG5QWWDLNE7R","download_json":"https://pith.science/pith/M7Z3SWKZ7NBTQTWG5QWWDLNE7R.json","view_paper":"https://pith.science/paper/M7Z3SWKZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.17949&json=true","fetch_graph":"https://pith.science/api/pith-number/M7Z3SWKZ7NBTQTWG5QWWDLNE7R/graph.json","fetch_events":"https://pith.science/api/pith-number/M7Z3SWKZ7NBTQTWG5QWWDLNE7R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M7Z3SWKZ7NBTQTWG5QWWDLNE7R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M7Z3SWKZ7NBTQTWG5QWWDLNE7R/action/storage_attestation","attest_author":"https://pith.science/pith/M7Z3SWKZ7NBTQTWG5QWWDLNE7R/action/author_attestation","sign_citation":"https://pith.science/pith/M7Z3SWKZ7NBTQTWG5QWWDLNE7R/action/citation_signature","submit_replication":"https://pith.science/pith/M7Z3SWKZ7NBTQTWG5QWWDLNE7R/action/replication_record"}},"created_at":"2026-07-05T09:41:09.338589+00:00","updated_at":"2026-07-05T09:41:09.338589+00:00"}