{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YCN57ZGTXUDMV3AXUU2K3FI6DO","short_pith_number":"pith:YCN57ZGT","canonical_record":{"source":{"id":"2507.19939","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-26T12:57:02Z","cross_cats_sorted":[],"title_canon_sha256":"196bfc9cefb85bbc1342bdb5b8247f54549c6827323c398a58bd95eb42831d6d","abstract_canon_sha256":"7e0e60d4b6cbfbb499b0f11f40f046780c1a1be3706a43924fa11fd7873bef4b"},"schema_version":"1.0"},"canonical_sha256":"c09bdfe4d3bd06caec17a534ad951e1bbf68d18e2d9d315ab4a3f1b4a353d444","source":{"kind":"arxiv","id":"2507.19939","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.19939","created_at":"2026-07-05T11:43:45Z"},{"alias_kind":"arxiv_version","alias_value":"2507.19939v1","created_at":"2026-07-05T11:43:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19939","created_at":"2026-07-05T11:43:45Z"},{"alias_kind":"pith_short_12","alias_value":"YCN57ZGTXUDM","created_at":"2026-07-05T11:43:45Z"},{"alias_kind":"pith_short_16","alias_value":"YCN57ZGTXUDMV3AX","created_at":"2026-07-05T11:43:45Z"},{"alias_kind":"pith_short_8","alias_value":"YCN57ZGT","created_at":"2026-07-05T11:43:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YCN57ZGTXUDMV3AXUU2K3FI6DO","target":"record","payload":{"canonical_record":{"source":{"id":"2507.19939","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-26T12:57:02Z","cross_cats_sorted":[],"title_canon_sha256":"196bfc9cefb85bbc1342bdb5b8247f54549c6827323c398a58bd95eb42831d6d","abstract_canon_sha256":"7e0e60d4b6cbfbb499b0f11f40f046780c1a1be3706a43924fa11fd7873bef4b"},"schema_version":"1.0"},"canonical_sha256":"c09bdfe4d3bd06caec17a534ad951e1bbf68d18e2d9d315ab4a3f1b4a353d444","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:45.237144Z","signature_b64":"8/mYMNFndb07pNLG0nHOtuvtwKgKyxfirXPMHrXNbk70BVChwnQeul8uBwK4mZ8er8oipzMUM2kopRteUibEBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c09bdfe4d3bd06caec17a534ad951e1bbf68d18e2d9d315ab4a3f1b4a353d444","last_reissued_at":"2026-07-05T11:43:45.236717Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:45.236717Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.19939","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":"2026-07-05T11:43:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kjdut31f9bLvzFh9fPOuN9O9YeIhQ2+q4sEfK+8uJOyG8J8rnrVfmMtlZ4vEqFoL0qJXHBmHXzVJM3CXaNy0Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:34:53.446470Z"},"content_sha256":"4e92664ca464d388ca4910365c32f462eee2e11739b1a23bf3e5fb5f2e970689","schema_version":"1.0","event_id":"sha256:4e92664ca464d388ca4910365c32f462eee2e11739b1a23bf3e5fb5f2e970689"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YCN57ZGTXUDMV3AXUU2K3FI6DO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLMControl: Grounded Control of Text-to-Image Diffusion-based Synthesis with Multimodal LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haowang Cui, Jiaze Wang, Rui Chen","submitted_at":"2025-07-26T12:57:02Z","abstract_excerpt":"Recent spatial control methods for text-to-image (T2I) diffusion models have shown compelling results. However, these methods still fail to precisely follow the control conditions and generate the corresponding images, especially when encountering the textual prompts that contain multiple objects or have complex spatial compositions. In this work, we present a LLM-guided framework called LLM\\_Control to address the challenges of the controllable T2I generation task. By improving grounding capabilities, LLM\\_Control is introduced to accurately modulate the pre-trained diffusion models, where vi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19939","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/2507.19939/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":"2026-07-05T11:43:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ote5QR96PaOvljjHVF3pdSpSzjx5XnEtFUkyD8P+lV4GGIwMBblUVq69hlfhAG+/mkOheJzgZrKQYChE5VvyDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:34:53.446958Z"},"content_sha256":"1cda408d79bca92335c7eed2b7cb352680cc790f7687f5b4ee6bc17a511129dd","schema_version":"1.0","event_id":"sha256:1cda408d79bca92335c7eed2b7cb352680cc790f7687f5b4ee6bc17a511129dd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YCN57ZGTXUDMV3AXUU2K3FI6DO/bundle.json","state_url":"https://pith.science/pith/YCN57ZGTXUDMV3AXUU2K3FI6DO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YCN57ZGTXUDMV3AXUU2K3FI6DO/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":"2026-08-04T23:34:53Z","links":{"resolver":"https://pith.science/pith/YCN57ZGTXUDMV3AXUU2K3FI6DO","bundle":"https://pith.science/pith/YCN57ZGTXUDMV3AXUU2K3FI6DO/bundle.json","state":"https://pith.science/pith/YCN57ZGTXUDMV3AXUU2K3FI6DO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YCN57ZGTXUDMV3AXUU2K3FI6DO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YCN57ZGTXUDMV3AXUU2K3FI6DO","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":"7e0e60d4b6cbfbb499b0f11f40f046780c1a1be3706a43924fa11fd7873bef4b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-26T12:57:02Z","title_canon_sha256":"196bfc9cefb85bbc1342bdb5b8247f54549c6827323c398a58bd95eb42831d6d"},"schema_version":"1.0","source":{"id":"2507.19939","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.19939","created_at":"2026-07-05T11:43:45Z"},{"alias_kind":"arxiv_version","alias_value":"2507.19939v1","created_at":"2026-07-05T11:43:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19939","created_at":"2026-07-05T11:43:45Z"},{"alias_kind":"pith_short_12","alias_value":"YCN57ZGTXUDM","created_at":"2026-07-05T11:43:45Z"},{"alias_kind":"pith_short_16","alias_value":"YCN57ZGTXUDMV3AX","created_at":"2026-07-05T11:43:45Z"},{"alias_kind":"pith_short_8","alias_value":"YCN57ZGT","created_at":"2026-07-05T11:43:45Z"}],"graph_snapshots":[{"event_id":"sha256:1cda408d79bca92335c7eed2b7cb352680cc790f7687f5b4ee6bc17a511129dd","target":"graph","created_at":"2026-07-05T11:43:45Z","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/2507.19939/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent spatial control methods for text-to-image (T2I) diffusion models have shown compelling results. However, these methods still fail to precisely follow the control conditions and generate the corresponding images, especially when encountering the textual prompts that contain multiple objects or have complex spatial compositions. In this work, we present a LLM-guided framework called LLM\\_Control to address the challenges of the controllable T2I generation task. By improving grounding capabilities, LLM\\_Control is introduced to accurately modulate the pre-trained diffusion models, where vi","authors_text":"Haowang Cui, Jiaze Wang, Rui Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-26T12:57:02Z","title":"LLMControl: Grounded Control of Text-to-Image Diffusion-based Synthesis with Multimodal LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19939","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":"sha256:4e92664ca464d388ca4910365c32f462eee2e11739b1a23bf3e5fb5f2e970689","target":"record","created_at":"2026-07-05T11:43:45Z","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":"7e0e60d4b6cbfbb499b0f11f40f046780c1a1be3706a43924fa11fd7873bef4b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-26T12:57:02Z","title_canon_sha256":"196bfc9cefb85bbc1342bdb5b8247f54549c6827323c398a58bd95eb42831d6d"},"schema_version":"1.0","source":{"id":"2507.19939","kind":"arxiv","version":1}},"canonical_sha256":"c09bdfe4d3bd06caec17a534ad951e1bbf68d18e2d9d315ab4a3f1b4a353d444","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c09bdfe4d3bd06caec17a534ad951e1bbf68d18e2d9d315ab4a3f1b4a353d444","first_computed_at":"2026-07-05T11:43:45.236717Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:45.236717Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8/mYMNFndb07pNLG0nHOtuvtwKgKyxfirXPMHrXNbk70BVChwnQeul8uBwK4mZ8er8oipzMUM2kopRteUibEBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:45.237144Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.19939","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e92664ca464d388ca4910365c32f462eee2e11739b1a23bf3e5fb5f2e970689","sha256:1cda408d79bca92335c7eed2b7cb352680cc790f7687f5b4ee6bc17a511129dd"],"state_sha256":"2171d36b82519ec773bf5d3a37696fc6c310c83d6cfdd6549153709df29c4873"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b6yN9guoxh0ZxyDUlxFe+5x4T3LLmZCb00gpgcPLQnFUFjX3OIT3JjCPrTzWSfLJUCD2JN0oJnWeX+yXAfmoBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T23:34:53.450183Z","bundle_sha256":"e7d79e8e61094a830facad14861c245c898719e26df849e35f07198a8445f609"}}