{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GKUP5IKMUDKJI7PESMRJALE3GR","short_pith_number":"pith:GKUP5IKM","canonical_record":{"source":{"id":"2311.17002","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T17:57:44Z","cross_cats_sorted":[],"title_canon_sha256":"2feee21cc6129b269713960cbaaa5f3d5d87355e7948461a28ccea0126e6f829","abstract_canon_sha256":"5fb19192285d9cec36c2de0325de58a36fb4b4ff463f432e313e459ced588009"},"schema_version":"1.0"},"canonical_sha256":"32a8fea14ca0d4947de49322902c9b3458be4d2578e6c9a54bf8b6ebfff758ed","source":{"kind":"arxiv","id":"2311.17002","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.17002","created_at":"2026-07-05T08:05:53Z"},{"alias_kind":"arxiv_version","alias_value":"2311.17002v3","created_at":"2026-07-05T08:05:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17002","created_at":"2026-07-05T08:05:53Z"},{"alias_kind":"pith_short_12","alias_value":"GKUP5IKMUDKJ","created_at":"2026-07-05T08:05:53Z"},{"alias_kind":"pith_short_16","alias_value":"GKUP5IKMUDKJI7PE","created_at":"2026-07-05T08:05:53Z"},{"alias_kind":"pith_short_8","alias_value":"GKUP5IKM","created_at":"2026-07-05T08:05:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GKUP5IKMUDKJI7PESMRJALE3GR","target":"record","payload":{"canonical_record":{"source":{"id":"2311.17002","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T17:57:44Z","cross_cats_sorted":[],"title_canon_sha256":"2feee21cc6129b269713960cbaaa5f3d5d87355e7948461a28ccea0126e6f829","abstract_canon_sha256":"5fb19192285d9cec36c2de0325de58a36fb4b4ff463f432e313e459ced588009"},"schema_version":"1.0"},"canonical_sha256":"32a8fea14ca0d4947de49322902c9b3458be4d2578e6c9a54bf8b6ebfff758ed","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:53.997146Z","signature_b64":"zIzILGDEOMK6z8MC2d97iw61jfzrsFDMX3ack0TpZ7zD/ks6UMgTcrS7mEbyiMAnlMoV+U9LLkIIOHMKMYIvDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32a8fea14ca0d4947de49322902c9b3458be4d2578e6c9a54bf8b6ebfff758ed","last_reissued_at":"2026-07-05T08:05:53.996674Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:53.996674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.17002","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:05:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sLoZU4hmqO4A5JAHdzYCE8Drsag5J+VaaS7ARhzWvRY8NVvpRecTcgyNMwhYLW1DYMlSl8lfNjQLCnRxZck8Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T07:57:27.666938Z"},"content_sha256":"b9603d7bb7e4cd69f5eb13f74385ec50c1c2580c7e54a013c658e699c677be46","schema_version":"1.0","event_id":"sha256:b9603d7bb7e4cd69f5eb13f74385ec50c1c2580c7e54a013c658e699c677be46"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GKUP5IKMUDKJI7PESMRJALE3GR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ranni: Taming Text-to-Image Diffusion for Accurate Instruction Following","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Biao Gong, Di Chen, Jingren Zhou, Yujun Shen, Yu Liu, Yutong Feng","submitted_at":"2023-11-28T17:57:44Z","abstract_excerpt":"Existing text-to-image (T2I) diffusion models usually struggle in interpreting complex prompts, especially those with quantity, object-attribute binding, and multi-subject descriptions. In this work, we introduce a semantic panel as the middleware in decoding texts to images, supporting the generator to better follow instructions. The panel is obtained through arranging the visual concepts parsed from the input text by the aid of large language models, and then injected into the denoising network as a detailed control signal to complement the text condition. To facilitate text-to-panel learnin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17002","kind":"arxiv","version":3},"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/2311.17002/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":"2026-07-05T08:05:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gCnDGV/z4o0OoZpmlS8bdgdUv4Z8XbnU56KnEMkjJaCE40b1muiipzMFMwza1IKN97xvPaIADUx3Aeq43/XmAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T07:57:27.667457Z"},"content_sha256":"91e380a5a64c185b87a122fe7a2cb66a2bf953baf9f5260a44065f2d9ee25a0d","schema_version":"1.0","event_id":"sha256:91e380a5a64c185b87a122fe7a2cb66a2bf953baf9f5260a44065f2d9ee25a0d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GKUP5IKMUDKJI7PESMRJALE3GR/bundle.json","state_url":"https://pith.science/pith/GKUP5IKMUDKJI7PESMRJALE3GR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GKUP5IKMUDKJI7PESMRJALE3GR/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":"2026-08-19T07:57:27Z","links":{"resolver":"https://pith.science/pith/GKUP5IKMUDKJI7PESMRJALE3GR","bundle":"https://pith.science/pith/GKUP5IKMUDKJI7PESMRJALE3GR/bundle.json","state":"https://pith.science/pith/GKUP5IKMUDKJI7PESMRJALE3GR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GKUP5IKMUDKJI7PESMRJALE3GR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GKUP5IKMUDKJI7PESMRJALE3GR","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":"5fb19192285d9cec36c2de0325de58a36fb4b4ff463f432e313e459ced588009","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T17:57:44Z","title_canon_sha256":"2feee21cc6129b269713960cbaaa5f3d5d87355e7948461a28ccea0126e6f829"},"schema_version":"1.0","source":{"id":"2311.17002","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.17002","created_at":"2026-07-05T08:05:53Z"},{"alias_kind":"arxiv_version","alias_value":"2311.17002v3","created_at":"2026-07-05T08:05:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17002","created_at":"2026-07-05T08:05:53Z"},{"alias_kind":"pith_short_12","alias_value":"GKUP5IKMUDKJ","created_at":"2026-07-05T08:05:53Z"},{"alias_kind":"pith_short_16","alias_value":"GKUP5IKMUDKJI7PE","created_at":"2026-07-05T08:05:53Z"},{"alias_kind":"pith_short_8","alias_value":"GKUP5IKM","created_at":"2026-07-05T08:05:53Z"}],"graph_snapshots":[{"event_id":"sha256:91e380a5a64c185b87a122fe7a2cb66a2bf953baf9f5260a44065f2d9ee25a0d","target":"graph","created_at":"2026-07-05T08:05:53Z","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/2311.17002/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing text-to-image (T2I) diffusion models usually struggle in interpreting complex prompts, especially those with quantity, object-attribute binding, and multi-subject descriptions. In this work, we introduce a semantic panel as the middleware in decoding texts to images, supporting the generator to better follow instructions. The panel is obtained through arranging the visual concepts parsed from the input text by the aid of large language models, and then injected into the denoising network as a detailed control signal to complement the text condition. To facilitate text-to-panel learnin","authors_text":"Biao Gong, Di Chen, Jingren Zhou, Yujun Shen, Yu Liu, Yutong Feng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T17:57:44Z","title":"Ranni: Taming Text-to-Image Diffusion for Accurate Instruction Following"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17002","kind":"arxiv","version":3},"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:b9603d7bb7e4cd69f5eb13f74385ec50c1c2580c7e54a013c658e699c677be46","target":"record","created_at":"2026-07-05T08:05:53Z","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":"5fb19192285d9cec36c2de0325de58a36fb4b4ff463f432e313e459ced588009","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T17:57:44Z","title_canon_sha256":"2feee21cc6129b269713960cbaaa5f3d5d87355e7948461a28ccea0126e6f829"},"schema_version":"1.0","source":{"id":"2311.17002","kind":"arxiv","version":3}},"canonical_sha256":"32a8fea14ca0d4947de49322902c9b3458be4d2578e6c9a54bf8b6ebfff758ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"32a8fea14ca0d4947de49322902c9b3458be4d2578e6c9a54bf8b6ebfff758ed","first_computed_at":"2026-07-05T08:05:53.996674Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:05:53.996674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zIzILGDEOMK6z8MC2d97iw61jfzrsFDMX3ack0TpZ7zD/ks6UMgTcrS7mEbyiMAnlMoV+U9LLkIIOHMKMYIvDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:05:53.997146Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.17002","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b9603d7bb7e4cd69f5eb13f74385ec50c1c2580c7e54a013c658e699c677be46","sha256:91e380a5a64c185b87a122fe7a2cb66a2bf953baf9f5260a44065f2d9ee25a0d"],"state_sha256":"a0f0e9cc0f9ec6286a26eb92a74f405a9710042c380d9b0555c503bd32e15f2c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S73x83T8pXbKtyKdoLTd5ARN6xZ+iKrjhF1qmChLgbXx326iYnSeqKOlSqKEZwkTxYwUOHpUiBLZg0GUWVN3Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T07:57:27.672854Z","bundle_sha256":"0b257ca3859ff916e33786d689e3e6cf499ad7de748d62297a0a8cc00fff1e00"}}