{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZVJPM6SZQ5E2BG6WOF6VHQUNCO","short_pith_number":"pith:ZVJPM6SZ","canonical_record":{"source":{"id":"2407.00737","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-30T15:50:32Z","cross_cats_sorted":[],"title_canon_sha256":"e970b2886f33e920072d606a67da0da1a5db599b41250568e8284ab3c59c7fc2","abstract_canon_sha256":"76a72d413ee60ae2a327213cba64979ecc43d989f9eb636cd212a01ccb323c4d"},"schema_version":"1.0"},"canonical_sha256":"cd52f67a598749a09bd6717d53c28d1395dfbe8433ef9ef55d37b5ee8c68a4cf","source":{"kind":"arxiv","id":"2407.00737","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.00737","created_at":"2026-07-05T08:59:31Z"},{"alias_kind":"arxiv_version","alias_value":"2407.00737v2","created_at":"2026-07-05T08:59:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00737","created_at":"2026-07-05T08:59:31Z"},{"alias_kind":"pith_short_12","alias_value":"ZVJPM6SZQ5E2","created_at":"2026-07-05T08:59:31Z"},{"alias_kind":"pith_short_16","alias_value":"ZVJPM6SZQ5E2BG6W","created_at":"2026-07-05T08:59:31Z"},{"alias_kind":"pith_short_8","alias_value":"ZVJPM6SZ","created_at":"2026-07-05T08:59:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZVJPM6SZQ5E2BG6WOF6VHQUNCO","target":"record","payload":{"canonical_record":{"source":{"id":"2407.00737","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-30T15:50:32Z","cross_cats_sorted":[],"title_canon_sha256":"e970b2886f33e920072d606a67da0da1a5db599b41250568e8284ab3c59c7fc2","abstract_canon_sha256":"76a72d413ee60ae2a327213cba64979ecc43d989f9eb636cd212a01ccb323c4d"},"schema_version":"1.0"},"canonical_sha256":"cd52f67a598749a09bd6717d53c28d1395dfbe8433ef9ef55d37b5ee8c68a4cf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:59:31.327273Z","signature_b64":"rcn4rvZ7qGPNnhF+74+6a+IbDFusE+qoRCbzGahpfCN4BgWw/J3S4ZTWDn7S9qf9S6Fr28COuwX5i+DaucDRDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd52f67a598749a09bd6717d53c28d1395dfbe8433ef9ef55d37b5ee8c68a4cf","last_reissued_at":"2026-07-05T08:59:31.326773Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:59:31.326773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.00737","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:59:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y2cVe4L/+iLJT2lIjJjIMJz5ChFpBX2p0VB8/AM3G5ogKo106tOm/X39kFJKXz6IdobQzdhD8tFJWux2XXh2BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T01:48:15.123848Z"},"content_sha256":"1bcab2dee20e41baf06bc476b7c040e4d958401e04d23b3d232c4080afdb7a63","schema_version":"1.0","event_id":"sha256:1bcab2dee20e41baf06bc476b7c040e4d958401e04d23b3d232c4080afdb7a63"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZVJPM6SZQ5E2BG6WOF6VHQUNCO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM4GEN: Leveraging Semantic Representation of LLMs for Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bai Liu, Changjie Fan, Jun Dan, Mushui Liu, Yang Zhen, Yuhang Ma, Yunlong Yu, Zeng Zhao, Zhipeng Hu","submitted_at":"2024-06-30T15:50:32Z","abstract_excerpt":"Diffusion models have exhibited substantial success in text-to-image generation. However, they often encounter challenges when dealing with complex and dense prompts involving multiple objects, attribute binding, and long descriptions. In this paper, we propose a novel framework called \\textbf{LLM4GEN}, which enhances the semantic understanding of text-to-image diffusion models by leveraging the representation of Large Language Models (LLMs). It can be seamlessly incorporated into various diffusion models as a plug-and-play component. A specially designed Cross-Adapter Module (CAM) integrates "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00737","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/2407.00737/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":"2026-07-05T08:59:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ajiGYtNDuxZC0naCZ6/kFc+rrB2ei6i+n374Lo9KvuwioV9IRTMRAhgTh+dvrhKk6OaFB75hqX9b4/MKYgfyCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T01:48:15.124802Z"},"content_sha256":"f72d9636d391b5d0da93b7a8fbe2674eb46c1e2105d39b56c64cc54dbad9da16","schema_version":"1.0","event_id":"sha256:f72d9636d391b5d0da93b7a8fbe2674eb46c1e2105d39b56c64cc54dbad9da16"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZVJPM6SZQ5E2BG6WOF6VHQUNCO/bundle.json","state_url":"https://pith.science/pith/ZVJPM6SZQ5E2BG6WOF6VHQUNCO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZVJPM6SZQ5E2BG6WOF6VHQUNCO/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":"2026-08-20T01:48:15Z","links":{"resolver":"https://pith.science/pith/ZVJPM6SZQ5E2BG6WOF6VHQUNCO","bundle":"https://pith.science/pith/ZVJPM6SZQ5E2BG6WOF6VHQUNCO/bundle.json","state":"https://pith.science/pith/ZVJPM6SZQ5E2BG6WOF6VHQUNCO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZVJPM6SZQ5E2BG6WOF6VHQUNCO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZVJPM6SZQ5E2BG6WOF6VHQUNCO","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":"76a72d413ee60ae2a327213cba64979ecc43d989f9eb636cd212a01ccb323c4d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-30T15:50:32Z","title_canon_sha256":"e970b2886f33e920072d606a67da0da1a5db599b41250568e8284ab3c59c7fc2"},"schema_version":"1.0","source":{"id":"2407.00737","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.00737","created_at":"2026-07-05T08:59:31Z"},{"alias_kind":"arxiv_version","alias_value":"2407.00737v2","created_at":"2026-07-05T08:59:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00737","created_at":"2026-07-05T08:59:31Z"},{"alias_kind":"pith_short_12","alias_value":"ZVJPM6SZQ5E2","created_at":"2026-07-05T08:59:31Z"},{"alias_kind":"pith_short_16","alias_value":"ZVJPM6SZQ5E2BG6W","created_at":"2026-07-05T08:59:31Z"},{"alias_kind":"pith_short_8","alias_value":"ZVJPM6SZ","created_at":"2026-07-05T08:59:31Z"}],"graph_snapshots":[{"event_id":"sha256:f72d9636d391b5d0da93b7a8fbe2674eb46c1e2105d39b56c64cc54dbad9da16","target":"graph","created_at":"2026-07-05T08:59:31Z","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/2407.00737/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion models have exhibited substantial success in text-to-image generation. However, they often encounter challenges when dealing with complex and dense prompts involving multiple objects, attribute binding, and long descriptions. In this paper, we propose a novel framework called \\textbf{LLM4GEN}, which enhances the semantic understanding of text-to-image diffusion models by leveraging the representation of Large Language Models (LLMs). It can be seamlessly incorporated into various diffusion models as a plug-and-play component. A specially designed Cross-Adapter Module (CAM) integrates ","authors_text":"Bai Liu, Changjie Fan, Jun Dan, Mushui Liu, Yang Zhen, Yuhang Ma, Yunlong Yu, Zeng Zhao, Zhipeng Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-30T15:50:32Z","title":"LLM4GEN: Leveraging Semantic Representation of LLMs for Text-to-Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00737","kind":"arxiv","version":2},"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":"sha256:1bcab2dee20e41baf06bc476b7c040e4d958401e04d23b3d232c4080afdb7a63","target":"record","created_at":"2026-07-05T08:59:31Z","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":"76a72d413ee60ae2a327213cba64979ecc43d989f9eb636cd212a01ccb323c4d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-30T15:50:32Z","title_canon_sha256":"e970b2886f33e920072d606a67da0da1a5db599b41250568e8284ab3c59c7fc2"},"schema_version":"1.0","source":{"id":"2407.00737","kind":"arxiv","version":2}},"canonical_sha256":"cd52f67a598749a09bd6717d53c28d1395dfbe8433ef9ef55d37b5ee8c68a4cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd52f67a598749a09bd6717d53c28d1395dfbe8433ef9ef55d37b5ee8c68a4cf","first_computed_at":"2026-07-05T08:59:31.326773Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:59:31.326773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rcn4rvZ7qGPNnhF+74+6a+IbDFusE+qoRCbzGahpfCN4BgWw/J3S4ZTWDn7S9qf9S6Fr28COuwX5i+DaucDRDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:59:31.327273Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.00737","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1bcab2dee20e41baf06bc476b7c040e4d958401e04d23b3d232c4080afdb7a63","sha256:f72d9636d391b5d0da93b7a8fbe2674eb46c1e2105d39b56c64cc54dbad9da16"],"state_sha256":"db8e008e4e0db4a22e7846a23533fb8beccea55d526bc3083120007bda75a5bf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BaUHzglRzvTCLgqF3baGQ4EbaDXxqc/GY1lwvDiLZXAVBpfTe2O9bbkPUmC5MHiINc6W7twuoqf9rnvgOWRuCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T01:48:15.128448Z","bundle_sha256":"fe53fd27930e6c6b65a9ab9f88e3ca23ce5df35ba2bc82f156d6ca6a0276ab01"}}