{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CQM5SNP2KR3H6XS3FD5ADNW2RP","short_pith_number":"pith:CQM5SNP2","canonical_record":{"source":{"id":"2405.05945","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-09T17:35:16Z","cross_cats_sorted":[],"title_canon_sha256":"0eaa036b314fc1911fb26a0adc3dc9a4169df9dc25158eb904b0fd583b0c10df","abstract_canon_sha256":"f44260d539c96cce76217889caa69970d65db154a4ca788f7e6708df8d70304b"},"schema_version":"1.0"},"canonical_sha256":"1419d935fa54767f5e5b28fa01b6da8bcbd14a66370e777679db4b6acb9a46ae","source":{"kind":"arxiv","id":"2405.05945","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.05945","created_at":"2026-07-05T08:31:15Z"},{"alias_kind":"arxiv_version","alias_value":"2405.05945v3","created_at":"2026-07-05T08:31:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.05945","created_at":"2026-07-05T08:31:15Z"},{"alias_kind":"pith_short_12","alias_value":"CQM5SNP2KR3H","created_at":"2026-07-05T08:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"CQM5SNP2KR3H6XS3","created_at":"2026-07-05T08:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"CQM5SNP2","created_at":"2026-07-05T08:31:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CQM5SNP2KR3H6XS3FD5ADNW2RP","target":"record","payload":{"canonical_record":{"source":{"id":"2405.05945","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-09T17:35:16Z","cross_cats_sorted":[],"title_canon_sha256":"0eaa036b314fc1911fb26a0adc3dc9a4169df9dc25158eb904b0fd583b0c10df","abstract_canon_sha256":"f44260d539c96cce76217889caa69970d65db154a4ca788f7e6708df8d70304b"},"schema_version":"1.0"},"canonical_sha256":"1419d935fa54767f5e5b28fa01b6da8bcbd14a66370e777679db4b6acb9a46ae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:15.234578Z","signature_b64":"j9d9Vm4acZvv6XrimOA7ZgDBz4NFYUlbYVw7rGewTndsOARV/QS/w+VZ9qZRPrgZjZMaipPv3UThwApVNTJiAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1419d935fa54767f5e5b28fa01b6da8bcbd14a66370e777679db4b6acb9a46ae","last_reissued_at":"2026-07-05T08:31:15.234066Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:15.234066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.05945","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":"2026-07-05T08:31:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gMIJSqpRFcWhaxLqbbUWDPa9FOZ9SsTabYnFOtAzxXhEwUqAN9P9f2q58lRBijwwGhYZL5TKKkTdjWaTwbDVDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:38:26.462881Z"},"content_sha256":"22313424693d0a57a554a0576c57934857cc7d500d728f603eab386f985a9c2c","schema_version":"1.0","event_id":"sha256:22313424693d0a57a554a0576c57934857cc7d500d728f603eab386f985a9c2c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CQM5SNP2KR3H6XS3FD5ADNW2RP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Lin, Dongyang Liu, He Tong, Hongsheng Li, Jingwen He, Junlin Xi, Le Zhuo, Longtian Qiu, Peng Gao, Renrui Zhang, Rongjie Huang, Ruoyi Du, Shijie Geng, Tianshuo Yang, Weicai Ye, Wenqi Shao, Xu Luo, Yuhang Zhang, Yu Qiao, Zhengkai Jiang","submitted_at":"2024-05-09T17:35:16Z","abstract_excerpt":"Sora unveils the potential of scaling Diffusion Transformer for generating photorealistic images and videos at arbitrary resolutions, aspect ratios, and durations, yet it still lacks sufficient implementation details. In this technical report, we introduce the Lumina-T2X family - a series of Flow-based Large Diffusion Transformers (Flag-DiT) equipped with zero-initialized attention, as a unified framework designed to transform noise into images, videos, multi-view 3D objects, and audio clips conditioned on text instructions. By tokenizing the latent spatial-temporal space and incorporating lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.05945","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/2405.05945/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":"2026-07-05T08:31:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EGWFLEA0+TVv5FLf7LZvX+pwf9UM6TcI57XN8C9Std/68cbVgpU3WraDcFCykl4ezNHvMdFrf4XvwUShLRNPBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:38:26.463254Z"},"content_sha256":"2d664bf508a40f24dda43327840b5e35752687addb86694f7e72c604e00220b6","schema_version":"1.0","event_id":"sha256:2d664bf508a40f24dda43327840b5e35752687addb86694f7e72c604e00220b6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CQM5SNP2KR3H6XS3FD5ADNW2RP/bundle.json","state_url":"https://pith.science/pith/CQM5SNP2KR3H6XS3FD5ADNW2RP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CQM5SNP2KR3H6XS3FD5ADNW2RP/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":"2026-07-06T18:38:26Z","links":{"resolver":"https://pith.science/pith/CQM5SNP2KR3H6XS3FD5ADNW2RP","bundle":"https://pith.science/pith/CQM5SNP2KR3H6XS3FD5ADNW2RP/bundle.json","state":"https://pith.science/pith/CQM5SNP2KR3H6XS3FD5ADNW2RP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CQM5SNP2KR3H6XS3FD5ADNW2RP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CQM5SNP2KR3H6XS3FD5ADNW2RP","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":"f44260d539c96cce76217889caa69970d65db154a4ca788f7e6708df8d70304b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-09T17:35:16Z","title_canon_sha256":"0eaa036b314fc1911fb26a0adc3dc9a4169df9dc25158eb904b0fd583b0c10df"},"schema_version":"1.0","source":{"id":"2405.05945","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.05945","created_at":"2026-07-05T08:31:15Z"},{"alias_kind":"arxiv_version","alias_value":"2405.05945v3","created_at":"2026-07-05T08:31:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.05945","created_at":"2026-07-05T08:31:15Z"},{"alias_kind":"pith_short_12","alias_value":"CQM5SNP2KR3H","created_at":"2026-07-05T08:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"CQM5SNP2KR3H6XS3","created_at":"2026-07-05T08:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"CQM5SNP2","created_at":"2026-07-05T08:31:15Z"}],"graph_snapshots":[{"event_id":"sha256:2d664bf508a40f24dda43327840b5e35752687addb86694f7e72c604e00220b6","target":"graph","created_at":"2026-07-05T08:31:15Z","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/2405.05945/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sora unveils the potential of scaling Diffusion Transformer for generating photorealistic images and videos at arbitrary resolutions, aspect ratios, and durations, yet it still lacks sufficient implementation details. In this technical report, we introduce the Lumina-T2X family - a series of Flow-based Large Diffusion Transformers (Flag-DiT) equipped with zero-initialized attention, as a unified framework designed to transform noise into images, videos, multi-view 3D objects, and audio clips conditioned on text instructions. By tokenizing the latent spatial-temporal space and incorporating lea","authors_text":"Chen Lin, Dongyang Liu, He Tong, Hongsheng Li, Jingwen He, Junlin Xi, Le Zhuo, Longtian Qiu, Peng Gao, Renrui Zhang, Rongjie Huang, Ruoyi Du, Shijie Geng, Tianshuo Yang, Weicai Ye, Wenqi Shao, Xu Luo, Yuhang Zhang, Yu Qiao, Zhengkai Jiang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-09T17:35:16Z","title":"Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.05945","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":"sha256:22313424693d0a57a554a0576c57934857cc7d500d728f603eab386f985a9c2c","target":"record","created_at":"2026-07-05T08:31:15Z","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":"f44260d539c96cce76217889caa69970d65db154a4ca788f7e6708df8d70304b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-09T17:35:16Z","title_canon_sha256":"0eaa036b314fc1911fb26a0adc3dc9a4169df9dc25158eb904b0fd583b0c10df"},"schema_version":"1.0","source":{"id":"2405.05945","kind":"arxiv","version":3}},"canonical_sha256":"1419d935fa54767f5e5b28fa01b6da8bcbd14a66370e777679db4b6acb9a46ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1419d935fa54767f5e5b28fa01b6da8bcbd14a66370e777679db4b6acb9a46ae","first_computed_at":"2026-07-05T08:31:15.234066Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:31:15.234066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j9d9Vm4acZvv6XrimOA7ZgDBz4NFYUlbYVw7rGewTndsOARV/QS/w+VZ9qZRPrgZjZMaipPv3UThwApVNTJiAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:31:15.234578Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.05945","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:22313424693d0a57a554a0576c57934857cc7d500d728f603eab386f985a9c2c","sha256:2d664bf508a40f24dda43327840b5e35752687addb86694f7e72c604e00220b6"],"state_sha256":"867a3b18370337be8adab083799e8a4d042b1083b6fb29abac0f776258e695d6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XnVghgHLDdthIysASXWllVgPtmeA7gK29UW2aemWrD6/mtiR8P8Ve+yzPk9psKwCSgts3cimKo/nLxj/nzgWDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:38:26.465267Z","bundle_sha256":"bd4b8ca2c8ed9416ff6a4876c363082084f7433bbed7cce2a071256d0a97e7c6"}}