{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4JTHLNIIFDSOLG2A255KBLOJD4","short_pith_number":"pith:4JTHLNII","canonical_record":{"source":{"id":"2505.10046","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-15T07:43:23Z","cross_cats_sorted":[],"title_canon_sha256":"a4aae470e2c825130ecef18b99f9d78de521afdc3b7c902c25939a2863172851","abstract_canon_sha256":"c45bae4eb391e82181c2e58650e9a0eb95adcca5632a25a53e1b1d1f7ef025cb"},"schema_version":"1.0"},"canonical_sha256":"e26675b50828e4e59b40d77aa0adc91f14423f39bdb032cd2a0f1c8cc6a49089","source":{"kind":"arxiv","id":"2505.10046","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.10046","created_at":"2026-07-05T11:03:32Z"},{"alias_kind":"arxiv_version","alias_value":"2505.10046v1","created_at":"2026-07-05T11:03:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10046","created_at":"2026-07-05T11:03:32Z"},{"alias_kind":"pith_short_12","alias_value":"4JTHLNIIFDSO","created_at":"2026-07-05T11:03:32Z"},{"alias_kind":"pith_short_16","alias_value":"4JTHLNIIFDSOLG2A","created_at":"2026-07-05T11:03:32Z"},{"alias_kind":"pith_short_8","alias_value":"4JTHLNII","created_at":"2026-07-05T11:03:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4JTHLNIIFDSOLG2A255KBLOJD4","target":"record","payload":{"canonical_record":{"source":{"id":"2505.10046","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-15T07:43:23Z","cross_cats_sorted":[],"title_canon_sha256":"a4aae470e2c825130ecef18b99f9d78de521afdc3b7c902c25939a2863172851","abstract_canon_sha256":"c45bae4eb391e82181c2e58650e9a0eb95adcca5632a25a53e1b1d1f7ef025cb"},"schema_version":"1.0"},"canonical_sha256":"e26675b50828e4e59b40d77aa0adc91f14423f39bdb032cd2a0f1c8cc6a49089","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:32.348082Z","signature_b64":"I02+tcsqc/NGZWqK7TsT5zmUMqiLbslQHDVsmy9AR5scrlMYCy2Oud4+4PCJwyqtMUO0NdAXJxSFReGSx0AaDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e26675b50828e4e59b40d77aa0adc91f14423f39bdb032cd2a0f1c8cc6a49089","last_reissued_at":"2026-07-05T11:03:32.347587Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:32.347587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.10046","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":"2026-07-05T11:03:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DzLf+XsPomrPngMI2Q7UxRLsYAEehTSaeSHOtWCusNYgWfCWm/6PrC8gNqq03jK3QfUtf0CBFjf7/Vo2OlECAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T20:31:50.038052Z"},"content_sha256":"c0f7d57ebeb0bce6cc7883a12a1c20870dff5fa8340ed0c035aba41daa063c2c","schema_version":"1.0","event_id":"sha256:c0f7d57ebeb0bce6cc7883a12a1c20870dff5fa8340ed0c035aba41daa063c2c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4JTHLNIIFDSOLG2A255KBLOJD4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingda Tang, Boyang Zheng, Saining Xie, Sayak Paul, Xichen Pan","submitted_at":"2025-05-15T07:43:23Z","abstract_excerpt":"This paper does not describe a new method; instead, it provides a thorough exploration of an important yet understudied design space related to recent advances in text-to-image synthesis -- specifically, the deep fusion of large language models (LLMs) and diffusion transformers (DiTs) for multi-modal generation. Previous studies mainly focused on overall system performance rather than detailed comparisons with alternative methods, and key design details and training recipes were often left undisclosed. These gaps create uncertainty about the real potential of this approach. To fill these gaps,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10046","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/2505.10046/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":"2026-07-05T11:03:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TXf4UF4f8iWxSjlyCMifI9i8YoaQR/mdS1ge9rYaJuO9/QLH9WWdvjiEXsj3JfwpFF4UhJJ9gMYQp/M3Lsm1Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T20:31:50.039131Z"},"content_sha256":"530538b84c118bae83765c1d04ad0f9466ab9c6d0eb918c5f4f87efdcfd63b14","schema_version":"1.0","event_id":"sha256:530538b84c118bae83765c1d04ad0f9466ab9c6d0eb918c5f4f87efdcfd63b14"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4JTHLNIIFDSOLG2A255KBLOJD4/bundle.json","state_url":"https://pith.science/pith/4JTHLNIIFDSOLG2A255KBLOJD4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4JTHLNIIFDSOLG2A255KBLOJD4/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":"2026-08-16T20:31:50Z","links":{"resolver":"https://pith.science/pith/4JTHLNIIFDSOLG2A255KBLOJD4","bundle":"https://pith.science/pith/4JTHLNIIFDSOLG2A255KBLOJD4/bundle.json","state":"https://pith.science/pith/4JTHLNIIFDSOLG2A255KBLOJD4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4JTHLNIIFDSOLG2A255KBLOJD4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4JTHLNIIFDSOLG2A255KBLOJD4","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":"c45bae4eb391e82181c2e58650e9a0eb95adcca5632a25a53e1b1d1f7ef025cb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-15T07:43:23Z","title_canon_sha256":"a4aae470e2c825130ecef18b99f9d78de521afdc3b7c902c25939a2863172851"},"schema_version":"1.0","source":{"id":"2505.10046","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.10046","created_at":"2026-07-05T11:03:32Z"},{"alias_kind":"arxiv_version","alias_value":"2505.10046v1","created_at":"2026-07-05T11:03:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10046","created_at":"2026-07-05T11:03:32Z"},{"alias_kind":"pith_short_12","alias_value":"4JTHLNIIFDSO","created_at":"2026-07-05T11:03:32Z"},{"alias_kind":"pith_short_16","alias_value":"4JTHLNIIFDSOLG2A","created_at":"2026-07-05T11:03:32Z"},{"alias_kind":"pith_short_8","alias_value":"4JTHLNII","created_at":"2026-07-05T11:03:32Z"}],"graph_snapshots":[{"event_id":"sha256:530538b84c118bae83765c1d04ad0f9466ab9c6d0eb918c5f4f87efdcfd63b14","target":"graph","created_at":"2026-07-05T11:03:32Z","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/2505.10046/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper does not describe a new method; instead, it provides a thorough exploration of an important yet understudied design space related to recent advances in text-to-image synthesis -- specifically, the deep fusion of large language models (LLMs) and diffusion transformers (DiTs) for multi-modal generation. Previous studies mainly focused on overall system performance rather than detailed comparisons with alternative methods, and key design details and training recipes were often left undisclosed. These gaps create uncertainty about the real potential of this approach. To fill these gaps,","authors_text":"Bingda Tang, Boyang Zheng, Saining Xie, Sayak Paul, Xichen Pan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-15T07:43:23Z","title":"Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10046","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:c0f7d57ebeb0bce6cc7883a12a1c20870dff5fa8340ed0c035aba41daa063c2c","target":"record","created_at":"2026-07-05T11:03:32Z","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":"c45bae4eb391e82181c2e58650e9a0eb95adcca5632a25a53e1b1d1f7ef025cb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-15T07:43:23Z","title_canon_sha256":"a4aae470e2c825130ecef18b99f9d78de521afdc3b7c902c25939a2863172851"},"schema_version":"1.0","source":{"id":"2505.10046","kind":"arxiv","version":1}},"canonical_sha256":"e26675b50828e4e59b40d77aa0adc91f14423f39bdb032cd2a0f1c8cc6a49089","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e26675b50828e4e59b40d77aa0adc91f14423f39bdb032cd2a0f1c8cc6a49089","first_computed_at":"2026-07-05T11:03:32.347587Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:03:32.347587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I02+tcsqc/NGZWqK7TsT5zmUMqiLbslQHDVsmy9AR5scrlMYCy2Oud4+4PCJwyqtMUO0NdAXJxSFReGSx0AaDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:03:32.348082Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.10046","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c0f7d57ebeb0bce6cc7883a12a1c20870dff5fa8340ed0c035aba41daa063c2c","sha256:530538b84c118bae83765c1d04ad0f9466ab9c6d0eb918c5f4f87efdcfd63b14"],"state_sha256":"f16767339d993ab4ee6583788898a04e609b29bec078265b8bb10fe1ac14e3d4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RBHsy8Tr57ygwWgHXi+w8DlaXIsp1nMbB/sGGecU+Ern5RN8uPE0FdHYVvRgaeMMXX3+8KUnOu8xlvB6yLvGDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T20:31:50.052045Z","bundle_sha256":"20e5279e4073befa6e3d59a4d5b2a59a69a3248470a206736ce67b159e9c78e3"}}