{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WT4QMFDBMJPCQBYCJ6PHZYVYSB","short_pith_number":"pith:WT4QMFDB","schema_version":"1.0","canonical_sha256":"b4f9061461625e2807024f9e7ce2b890446968736acfd4e947deebbcac1105fa","source":{"kind":"arxiv","id":"2501.09194","version":2},"attestation_state":"computed","paper":{"title":"Grounding Text-to-Image Diffusion Models for Controlled High-Quality Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ahmad S\\\"uleyman, G\\\"oksel Biricik","submitted_at":"2025-01-15T22:55:26Z","abstract_excerpt":"Text-to-image (T2I) generative diffusion models have demonstrated outstanding performance in synthesizing diverse, high-quality visuals from text captions. Several layout-to-image models have been developed to control the generation process by utilizing a wide range of layouts, such as segmentation maps, edges, and human keypoints. In this work, we propose ObjectDiffusion, a model that conditions T2I diffusion models on semantic and spatial grounding information, enabling the precise rendering and placement of desired objects in specific locations defined by bounding boxes. To achieve this, we"},"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":"2501.09194","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-15T22:55:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a9bae42891364e130f4627d783d36182ebfa9ce9557af9b93a7553156be84d52","abstract_canon_sha256":"b728a136a0ed6e04f0c85aa874e08c85f9f65853445486c1417d44e4a69cee1a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:03.269324Z","signature_b64":"4vB2wXoQB8G0Z9Z9BzQ1kthqLtGUS2nTZJEDxBAl46xCb/SsbinMx86JOvjNjrGSK9yU7Oneuk31x+mLC6EODg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4f9061461625e2807024f9e7ce2b890446968736acfd4e947deebbcac1105fa","last_reissued_at":"2026-07-05T10:12:03.268820Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:03.268820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Grounding Text-to-Image Diffusion Models for Controlled High-Quality Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ahmad S\\\"uleyman, G\\\"oksel Biricik","submitted_at":"2025-01-15T22:55:26Z","abstract_excerpt":"Text-to-image (T2I) generative diffusion models have demonstrated outstanding performance in synthesizing diverse, high-quality visuals from text captions. Several layout-to-image models have been developed to control the generation process by utilizing a wide range of layouts, such as segmentation maps, edges, and human keypoints. In this work, we propose ObjectDiffusion, a model that conditions T2I diffusion models on semantic and spatial grounding information, enabling the precise rendering and placement of desired objects in specific locations defined by bounding boxes. To achieve this, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09194","kind":"arxiv","version":2},"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/2501.09194/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":"2501.09194","created_at":"2026-07-05T10:12:03.268880+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.09194v2","created_at":"2026-07-05T10:12:03.268880+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09194","created_at":"2026-07-05T10:12:03.268880+00:00"},{"alias_kind":"pith_short_12","alias_value":"WT4QMFDBMJPC","created_at":"2026-07-05T10:12:03.268880+00:00"},{"alias_kind":"pith_short_16","alias_value":"WT4QMFDBMJPCQBYC","created_at":"2026-07-05T10:12:03.268880+00:00"},{"alias_kind":"pith_short_8","alias_value":"WT4QMFDB","created_at":"2026-07-05T10:12:03.268880+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WT4QMFDBMJPCQBYCJ6PHZYVYSB","json":"https://pith.science/pith/WT4QMFDBMJPCQBYCJ6PHZYVYSB.json","graph_json":"https://pith.science/api/pith-number/WT4QMFDBMJPCQBYCJ6PHZYVYSB/graph.json","events_json":"https://pith.science/api/pith-number/WT4QMFDBMJPCQBYCJ6PHZYVYSB/events.json","paper":"https://pith.science/paper/WT4QMFDB"},"agent_actions":{"view_html":"https://pith.science/pith/WT4QMFDBMJPCQBYCJ6PHZYVYSB","download_json":"https://pith.science/pith/WT4QMFDBMJPCQBYCJ6PHZYVYSB.json","view_paper":"https://pith.science/paper/WT4QMFDB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.09194&json=true","fetch_graph":"https://pith.science/api/pith-number/WT4QMFDBMJPCQBYCJ6PHZYVYSB/graph.json","fetch_events":"https://pith.science/api/pith-number/WT4QMFDBMJPCQBYCJ6PHZYVYSB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WT4QMFDBMJPCQBYCJ6PHZYVYSB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WT4QMFDBMJPCQBYCJ6PHZYVYSB/action/storage_attestation","attest_author":"https://pith.science/pith/WT4QMFDBMJPCQBYCJ6PHZYVYSB/action/author_attestation","sign_citation":"https://pith.science/pith/WT4QMFDBMJPCQBYCJ6PHZYVYSB/action/citation_signature","submit_replication":"https://pith.science/pith/WT4QMFDBMJPCQBYCJ6PHZYVYSB/action/replication_record"}},"created_at":"2026-07-05T10:12:03.268880+00:00","updated_at":"2026-07-05T10:12:03.268880+00:00"}