{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MZZTVC5L246IMA7ZR6Q5VDJHM5","short_pith_number":"pith:MZZTVC5L","canonical_record":{"source":{"id":"2508.04732","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-05T20:53:43Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"cdda82d2a5eb2e40599a5c419a9774fab3c41f17bb1dc7add2d64c3a6069600e","abstract_canon_sha256":"3cf375b32a9c98c5e0d23f828750b6094f7b5d96c0108b2f4a8667d7be14fc6b"},"schema_version":"1.0"},"canonical_sha256":"66733a8babd73c8603f98fa1da8d276753100386cddb0f7409d78c9f992ba68e","source":{"kind":"arxiv","id":"2508.04732","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.04732","created_at":"2026-07-05T11:50:00Z"},{"alias_kind":"arxiv_version","alias_value":"2508.04732v1","created_at":"2026-07-05T11:50:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.04732","created_at":"2026-07-05T11:50:00Z"},{"alias_kind":"pith_short_12","alias_value":"MZZTVC5L246I","created_at":"2026-07-05T11:50:00Z"},{"alias_kind":"pith_short_16","alias_value":"MZZTVC5L246IMA7Z","created_at":"2026-07-05T11:50:00Z"},{"alias_kind":"pith_short_8","alias_value":"MZZTVC5L","created_at":"2026-07-05T11:50:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MZZTVC5L246IMA7ZR6Q5VDJHM5","target":"record","payload":{"canonical_record":{"source":{"id":"2508.04732","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-05T20:53:43Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"cdda82d2a5eb2e40599a5c419a9774fab3c41f17bb1dc7add2d64c3a6069600e","abstract_canon_sha256":"3cf375b32a9c98c5e0d23f828750b6094f7b5d96c0108b2f4a8667d7be14fc6b"},"schema_version":"1.0"},"canonical_sha256":"66733a8babd73c8603f98fa1da8d276753100386cddb0f7409d78c9f992ba68e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:00.807950Z","signature_b64":"IyTUF7VEYbeLQZNo/dar8UeRIpelKtmtXYqtML1N7c4OECT076WaJIvaTiaWz1RQCsHzI8J4YgyDBujTbtBeCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66733a8babd73c8603f98fa1da8d276753100386cddb0f7409d78c9f992ba68e","last_reissued_at":"2026-07-05T11:50:00.807472Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:00.807472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.04732","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":"2026-07-05T11:50:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7dU8K6aWsH7Gkd3btBOUbB8Lwl2L4sVASmwxtYZ7p1PgTdzTMdZrJngf4F9J2FtNZCj8pYdBIWqu0GTXrcmxAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:53:55.829996Z"},"content_sha256":"1226ee02bb14b1e09e287578b35aae3bfc2c6838fd2f8038a2802887a2a6e9c1","schema_version":"1.0","event_id":"sha256:1226ee02bb14b1e09e287578b35aae3bfc2c6838fd2f8038a2802887a2a6e9c1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MZZTVC5L246IMA7ZR6Q5VDJHM5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LumiGen: An LVLM-Enhanced Iterative Framework for Fine-Grained Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.LG","authors_text":"Nicholas Evans, Xiangyu Zhou, Xiaoqi Dong, Yujia Lin","submitted_at":"2025-08-05T20:53:43Z","abstract_excerpt":"Text-to-Image (T2I) generation has made significant advancements with diffusion models, yet challenges persist in handling complex instructions, ensuring fine-grained content control, and maintaining deep semantic consistency. Existing T2I models often struggle with tasks like accurate text rendering, precise pose generation, or intricate compositional coherence. Concurrently, Vision-Language Models (LVLMs) have demonstrated powerful capabilities in cross-modal understanding and instruction following. We propose LumiGen, a novel LVLM-enhanced iterative framework designed to elevate T2I model p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.04732","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/2508.04732/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":"2026-07-05T11:50:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fpdh/kVyY/4YdqjE/NcRuvNfi7JHij6W/ZpZByeEeFQaibYJf6XRtIGbXqOFe9usIBJaEht2BDW+34CiGYdWDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:53:55.830557Z"},"content_sha256":"c57aa59e69f84e4921d5c620fcde241e1b7ad8909117c3de3c090e913751ddc4","schema_version":"1.0","event_id":"sha256:c57aa59e69f84e4921d5c620fcde241e1b7ad8909117c3de3c090e913751ddc4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MZZTVC5L246IMA7ZR6Q5VDJHM5/bundle.json","state_url":"https://pith.science/pith/MZZTVC5L246IMA7ZR6Q5VDJHM5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MZZTVC5L246IMA7ZR6Q5VDJHM5/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":"2026-08-07T15:53:55Z","links":{"resolver":"https://pith.science/pith/MZZTVC5L246IMA7ZR6Q5VDJHM5","bundle":"https://pith.science/pith/MZZTVC5L246IMA7ZR6Q5VDJHM5/bundle.json","state":"https://pith.science/pith/MZZTVC5L246IMA7ZR6Q5VDJHM5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MZZTVC5L246IMA7ZR6Q5VDJHM5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MZZTVC5L246IMA7ZR6Q5VDJHM5","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":"3cf375b32a9c98c5e0d23f828750b6094f7b5d96c0108b2f4a8667d7be14fc6b","cross_cats_sorted":["cs.GR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-05T20:53:43Z","title_canon_sha256":"cdda82d2a5eb2e40599a5c419a9774fab3c41f17bb1dc7add2d64c3a6069600e"},"schema_version":"1.0","source":{"id":"2508.04732","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.04732","created_at":"2026-07-05T11:50:00Z"},{"alias_kind":"arxiv_version","alias_value":"2508.04732v1","created_at":"2026-07-05T11:50:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.04732","created_at":"2026-07-05T11:50:00Z"},{"alias_kind":"pith_short_12","alias_value":"MZZTVC5L246I","created_at":"2026-07-05T11:50:00Z"},{"alias_kind":"pith_short_16","alias_value":"MZZTVC5L246IMA7Z","created_at":"2026-07-05T11:50:00Z"},{"alias_kind":"pith_short_8","alias_value":"MZZTVC5L","created_at":"2026-07-05T11:50:00Z"}],"graph_snapshots":[{"event_id":"sha256:c57aa59e69f84e4921d5c620fcde241e1b7ad8909117c3de3c090e913751ddc4","target":"graph","created_at":"2026-07-05T11:50:00Z","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/2508.04732/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-Image (T2I) generation has made significant advancements with diffusion models, yet challenges persist in handling complex instructions, ensuring fine-grained content control, and maintaining deep semantic consistency. Existing T2I models often struggle with tasks like accurate text rendering, precise pose generation, or intricate compositional coherence. Concurrently, Vision-Language Models (LVLMs) have demonstrated powerful capabilities in cross-modal understanding and instruction following. We propose LumiGen, a novel LVLM-enhanced iterative framework designed to elevate T2I model p","authors_text":"Nicholas Evans, Xiangyu Zhou, Xiaoqi Dong, Yujia Lin","cross_cats":["cs.GR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-05T20:53:43Z","title":"LumiGen: An LVLM-Enhanced Iterative Framework for Fine-Grained Text-to-Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.04732","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":"sha256:1226ee02bb14b1e09e287578b35aae3bfc2c6838fd2f8038a2802887a2a6e9c1","target":"record","created_at":"2026-07-05T11:50:00Z","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":"3cf375b32a9c98c5e0d23f828750b6094f7b5d96c0108b2f4a8667d7be14fc6b","cross_cats_sorted":["cs.GR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-05T20:53:43Z","title_canon_sha256":"cdda82d2a5eb2e40599a5c419a9774fab3c41f17bb1dc7add2d64c3a6069600e"},"schema_version":"1.0","source":{"id":"2508.04732","kind":"arxiv","version":1}},"canonical_sha256":"66733a8babd73c8603f98fa1da8d276753100386cddb0f7409d78c9f992ba68e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66733a8babd73c8603f98fa1da8d276753100386cddb0f7409d78c9f992ba68e","first_computed_at":"2026-07-05T11:50:00.807472Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:50:00.807472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IyTUF7VEYbeLQZNo/dar8UeRIpelKtmtXYqtML1N7c4OECT076WaJIvaTiaWz1RQCsHzI8J4YgyDBujTbtBeCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:50:00.807950Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.04732","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1226ee02bb14b1e09e287578b35aae3bfc2c6838fd2f8038a2802887a2a6e9c1","sha256:c57aa59e69f84e4921d5c620fcde241e1b7ad8909117c3de3c090e913751ddc4"],"state_sha256":"ac7c36fd999e7dd02305a315ffa2f7cc4825d873f0f3d18a5ee66e2bed44a350"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jl3h6a4CfdRIgqr30HUbgzs0wPQ1/q+mPXIA/ky/RamGK+hxYhAcCVZoGGSxArZ5W2WT6/n2TGmEHbmq4+PhCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T15:53:55.834649Z","bundle_sha256":"385bd1b65b8b1bf9a8090b8fc2facff65cbf4dc1b762e7e925d1ab5274e006df"}}