{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:26TQHXQNWL654CET3MSBQVI5IH","short_pith_number":"pith:26TQHXQN","canonical_record":{"source":{"id":"2404.05331","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-08T09:18:32Z","cross_cats_sorted":[],"title_canon_sha256":"55de1651f57850c2bd737a06e989807ae5357a9f89243d6a7306a6645bc8651a","abstract_canon_sha256":"929f9e178af5a2e2ae3ffd355d10ecd4d70cb318387f40774449de7b7ff1815a"},"schema_version":"1.0"},"canonical_sha256":"d7a703de0db2fdde0893db2418551d41ea7111deffe09732227a55bdbc4a457a","source":{"kind":"arxiv","id":"2404.05331","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.05331","created_at":"2026-07-05T08:05:29Z"},{"alias_kind":"arxiv_version","alias_value":"2404.05331v1","created_at":"2026-07-05T08:05:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05331","created_at":"2026-07-05T08:05:29Z"},{"alias_kind":"pith_short_12","alias_value":"26TQHXQNWL65","created_at":"2026-07-05T08:05:29Z"},{"alias_kind":"pith_short_16","alias_value":"26TQHXQNWL654CET","created_at":"2026-07-05T08:05:29Z"},{"alias_kind":"pith_short_8","alias_value":"26TQHXQN","created_at":"2026-07-05T08:05:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:26TQHXQNWL654CET3MSBQVI5IH","target":"record","payload":{"canonical_record":{"source":{"id":"2404.05331","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-08T09:18:32Z","cross_cats_sorted":[],"title_canon_sha256":"55de1651f57850c2bd737a06e989807ae5357a9f89243d6a7306a6645bc8651a","abstract_canon_sha256":"929f9e178af5a2e2ae3ffd355d10ecd4d70cb318387f40774449de7b7ff1815a"},"schema_version":"1.0"},"canonical_sha256":"d7a703de0db2fdde0893db2418551d41ea7111deffe09732227a55bdbc4a457a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:29.157552Z","signature_b64":"hdyLayiZfN90Oez62OXyTP25mfZApAOGwo+uY+n01/0M6EZUD/8ODrof8MxwrKXmh7PfhjTOZwdHdMPSVIbkBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7a703de0db2fdde0893db2418551d41ea7111deffe09732227a55bdbc4a457a","last_reissued_at":"2026-07-05T08:05:29.157135Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:29.157135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.05331","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:05:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GQrJNrOVfPfuP4EJU6P7uV0R1CcHx9sdOpfqOkYsjvuJyKnCrTmHed8aGLkWJohiWrPK5RlaGV5/88wl0nFQBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:15:06.939279Z"},"content_sha256":"1276a4076dbedd5f92170b1452ae9b30287b30925bd83cb2b19a3fd0f665d790","schema_version":"1.0","event_id":"sha256:1276a4076dbedd5f92170b1452ae9b30287b30925bd83cb2b19a3fd0f665d790"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:26TQHXQNWL654CET3MSBQVI5IH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mask-ControlNet: Higher-Quality Image Generation with An Additional Mask Prompt","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoyu Wang, Huixin Xiong, Longguang Wang, Zhiheng Li, Zhiqi Huang","submitted_at":"2024-04-08T09:18:32Z","abstract_excerpt":"Text-to-image generation has witnessed great progress, especially with the recent advancements in diffusion models. Since texts cannot provide detailed conditions like object appearance, reference images are usually leveraged for the control of objects in the generated images. However, existing methods still suffer limited accuracy when the relationship between the foreground and background is complicated. To address this issue, we develop a framework termed Mask-ControlNet by introducing an additional mask prompt. Specifically, we first employ large vision models to obtain masks to segment th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05331","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/2404.05331/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:05:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mtY8UGXZYFtUzwCm0GdGSdXmKvdRAXSmBLACM8DGWcLvI8ExhHcLXXwIy30nxdudXRGSTvxjMnwBBLy+OQAhAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:15:06.939812Z"},"content_sha256":"edc5345ff71010571f7c0df4c031c23ce3b4eadda70d52c405fa7254804264cb","schema_version":"1.0","event_id":"sha256:edc5345ff71010571f7c0df4c031c23ce3b4eadda70d52c405fa7254804264cb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/26TQHXQNWL654CET3MSBQVI5IH/bundle.json","state_url":"https://pith.science/pith/26TQHXQNWL654CET3MSBQVI5IH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/26TQHXQNWL654CET3MSBQVI5IH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T12:15:06Z","links":{"resolver":"https://pith.science/pith/26TQHXQNWL654CET3MSBQVI5IH","bundle":"https://pith.science/pith/26TQHXQNWL654CET3MSBQVI5IH/bundle.json","state":"https://pith.science/pith/26TQHXQNWL654CET3MSBQVI5IH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/26TQHXQNWL654CET3MSBQVI5IH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:26TQHXQNWL654CET3MSBQVI5IH","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":"929f9e178af5a2e2ae3ffd355d10ecd4d70cb318387f40774449de7b7ff1815a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-08T09:18:32Z","title_canon_sha256":"55de1651f57850c2bd737a06e989807ae5357a9f89243d6a7306a6645bc8651a"},"schema_version":"1.0","source":{"id":"2404.05331","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.05331","created_at":"2026-07-05T08:05:29Z"},{"alias_kind":"arxiv_version","alias_value":"2404.05331v1","created_at":"2026-07-05T08:05:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05331","created_at":"2026-07-05T08:05:29Z"},{"alias_kind":"pith_short_12","alias_value":"26TQHXQNWL65","created_at":"2026-07-05T08:05:29Z"},{"alias_kind":"pith_short_16","alias_value":"26TQHXQNWL654CET","created_at":"2026-07-05T08:05:29Z"},{"alias_kind":"pith_short_8","alias_value":"26TQHXQN","created_at":"2026-07-05T08:05:29Z"}],"graph_snapshots":[{"event_id":"sha256:edc5345ff71010571f7c0df4c031c23ce3b4eadda70d52c405fa7254804264cb","target":"graph","created_at":"2026-07-05T08:05:29Z","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/2404.05331/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-image generation has witnessed great progress, especially with the recent advancements in diffusion models. Since texts cannot provide detailed conditions like object appearance, reference images are usually leveraged for the control of objects in the generated images. However, existing methods still suffer limited accuracy when the relationship between the foreground and background is complicated. To address this issue, we develop a framework termed Mask-ControlNet by introducing an additional mask prompt. Specifically, we first employ large vision models to obtain masks to segment th","authors_text":"Haoyu Wang, Huixin Xiong, Longguang Wang, Zhiheng Li, Zhiqi Huang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-08T09:18:32Z","title":"Mask-ControlNet: Higher-Quality Image Generation with An Additional Mask Prompt"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05331","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":"sha256:1276a4076dbedd5f92170b1452ae9b30287b30925bd83cb2b19a3fd0f665d790","target":"record","created_at":"2026-07-05T08:05:29Z","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":"929f9e178af5a2e2ae3ffd355d10ecd4d70cb318387f40774449de7b7ff1815a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-08T09:18:32Z","title_canon_sha256":"55de1651f57850c2bd737a06e989807ae5357a9f89243d6a7306a6645bc8651a"},"schema_version":"1.0","source":{"id":"2404.05331","kind":"arxiv","version":1}},"canonical_sha256":"d7a703de0db2fdde0893db2418551d41ea7111deffe09732227a55bdbc4a457a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d7a703de0db2fdde0893db2418551d41ea7111deffe09732227a55bdbc4a457a","first_computed_at":"2026-07-05T08:05:29.157135Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:05:29.157135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hdyLayiZfN90Oez62OXyTP25mfZApAOGwo+uY+n01/0M6EZUD/8ODrof8MxwrKXmh7PfhjTOZwdHdMPSVIbkBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:05:29.157552Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.05331","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1276a4076dbedd5f92170b1452ae9b30287b30925bd83cb2b19a3fd0f665d790","sha256:edc5345ff71010571f7c0df4c031c23ce3b4eadda70d52c405fa7254804264cb"],"state_sha256":"8b032ec3b9abadea646e8f7177676b3190836c330e798e522392a8faac04f1b1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QQyfpAeGSDpXqPho6SWNw+xTW7P76FCIHiYdjN8oKHIfP/cgoRL8kWhBaJw9uMZl4e5vj2eZs4MWflsezAMuAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T12:15:06.945967Z","bundle_sha256":"3b397d2fd83f5945c0323f7a835db5f879145e79f89cba8123e0ea9236ffc895"}}