{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LWNFJYGGY7CTUR2MKD6OCOGPH5","short_pith_number":"pith:LWNFJYGG","canonical_record":{"source":{"id":"2511.22699","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-27T18:52:07Z","cross_cats_sorted":[],"title_canon_sha256":"7931a46ee722028694343234e0238fae075761d2346e14a627a72a44763d3125","abstract_canon_sha256":"9578fb621740b6bca9b287fc21991fcd64edd1bc183c38b5b16e7a3bb0e623e1"},"schema_version":"1.0"},"canonical_sha256":"5d9a54e0c6c7c53a474c50fce138cf3f5f1f1f2447b250f211ee8ec5105a655b","source":{"kind":"arxiv","id":"2511.22699","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.22699","created_at":"2026-06-23T03:13:51Z"},{"alias_kind":"arxiv_version","alias_value":"2511.22699v4","created_at":"2026-06-23T03:13:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.22699","created_at":"2026-06-23T03:13:51Z"},{"alias_kind":"pith_short_12","alias_value":"LWNFJYGGY7CT","created_at":"2026-06-23T03:13:51Z"},{"alias_kind":"pith_short_16","alias_value":"LWNFJYGGY7CTUR2M","created_at":"2026-06-23T03:13:51Z"},{"alias_kind":"pith_short_8","alias_value":"LWNFJYGG","created_at":"2026-06-23T03:13:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LWNFJYGGY7CTUR2MKD6OCOGPH5","target":"record","payload":{"canonical_record":{"source":{"id":"2511.22699","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-27T18:52:07Z","cross_cats_sorted":[],"title_canon_sha256":"7931a46ee722028694343234e0238fae075761d2346e14a627a72a44763d3125","abstract_canon_sha256":"9578fb621740b6bca9b287fc21991fcd64edd1bc183c38b5b16e7a3bb0e623e1"},"schema_version":"1.0"},"canonical_sha256":"5d9a54e0c6c7c53a474c50fce138cf3f5f1f1f2447b250f211ee8ec5105a655b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:13:51.898783Z","signature_b64":"sch7r7H7IWsqK2VS5svG8DDkbu5GnJ44Vj5mYO1jmTRlJLl2/nkxBuoPJ0XYScVjflC+KwT6DN6l0QGAbL5XAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d9a54e0c6c7c53a474c50fce138cf3f5f1f1f2447b250f211ee8ec5105a655b","last_reissued_at":"2026-06-23T03:13:51.898241Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:13:51.898241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2511.22699","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T03:13:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dnWLHMZJvoe157ZotPp73IH6IUHo1bJOhuPdg8uLVH0krId+aafZsy4bLPERrdQE1wyOdTb8zKmNdPrE4IwCCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:11:17.094912Z"},"content_sha256":"a5ab5aab3db065263a5a7e83c280aa38eee84d944b3b47c9a15acf9fe9f12e7c","schema_version":"1.0","event_id":"sha256:a5ab5aab3db065263a5a7e83c280aa38eee84d944b3b47c9a15acf9fe9f12e7c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LWNFJYGGY7CTUR2MKD6OCOGPH5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A 6-billion-parameter image model reaches commercial-level photorealism and text rendering with far less training compute than larger rivals.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aiming Hao, Chi Zhang, David Liu, Dengyang Jiang, Dongyang Liu, Feng Yu, Huanqia Cai, Liangchen Li, Peng Gao, Qilong Wu, Ruikai Zhou, Ruoyi Du, Shifeng Zhang, Shijie Huang, Shilin Zhou, Sihan Cao, Steven Hoi, Xin Jin, Yuming Jiang, Zechao Zhan, Zhaohui Hou, Zhen Li, Zhong-Yu Li, Z-Image Team","submitted_at":"2025-11-27T18:52:07Z","abstract_excerpt":"The landscape of high-performance image generation models is currently dominated by proprietary systems, such as Nano Banana Pro and Seedream 4.0. Leading open-source alternatives, including Qwen-Image, Hunyuan-Image-3.0 and FLUX.2, are characterized by massive parameter counts (20B to 80B), making them impractical for inference, and fine-tuning on consumer-grade hardware. To address this gap, we propose Z-Image, an efficient 6B-parameter foundation generative model built upon a Scalable Single-Stream Diffusion Transformer (S3-DiT) architecture that challenges the \"scale-at-all-costs\" paradigm"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Z-Image achieves performance comparable to or surpassing that of leading competitors across various dimensions. Most notably, Z-Image exhibits exceptional capabilities in photorealistic image generation and bilingual text rendering, delivering results that rival top-tier commercial models, thereby demonstrating that state-of-the-art results are achievable with significantly reduced computational overhead.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that the curated data infrastructure, streamlined training curriculum, S3-DiT architecture, and few-step distillation with reward post-training directly produce the claimed performance levels without undisclosed advantages in training data scale or evaluation methodology.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Z-Image is an efficient 6B-parameter foundation model for image generation that rivals larger commercial systems in photorealism and bilingual text rendering through a new single-stream diffusion transformer and streamlined training.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A 6-billion-parameter image model reaches commercial-level photorealism and text rendering with far less training compute than larger rivals.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"4d8df2d777d09a4012e36644cfa11712de1d248f02d73ef5697e2e891ffb41b1"},"source":{"id":"2511.22699","kind":"arxiv","version":4},"verdict":{"id":"0b562510-9624-47fc-bb30-bc162b42349b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-11T14:01:29.639989Z","strongest_claim":"Z-Image achieves performance comparable to or surpassing that of leading competitors across various dimensions. Most notably, Z-Image exhibits exceptional capabilities in photorealistic image generation and bilingual text rendering, delivering results that rival top-tier commercial models, thereby demonstrating that state-of-the-art results are achievable with significantly reduced computational overhead.","one_line_summary":"Z-Image is an efficient 6B-parameter foundation model for image generation that rivals larger commercial systems in photorealism and bilingual text rendering through a new single-stream diffusion transformer and streamlined training.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that the curated data infrastructure, streamlined training curriculum, S3-DiT architecture, and few-step distillation with reward post-training directly produce the claimed performance levels without undisclosed advantages in training data scale or evaluation methodology.","pith_extraction_headline":"A 6-billion-parameter image model reaches commercial-level photorealism and text rendering with far less training compute than larger rivals."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2511.22699/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":"0b562510-9624-47fc-bb30-bc162b42349b"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T03:13:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lfRh1Jm0rvGANXpFlGWv22sk0NH4yVW5PBO252pWI+VGuHe6+pf1lo+ON0WWjiwRgASsVQhxiZlVm+EW1froCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:11:17.095574Z"},"content_sha256":"68a17eb424ab26b6e56bb7936facb20261b28b2d99e9b9fd3be7b212f3ac3233","schema_version":"1.0","event_id":"sha256:68a17eb424ab26b6e56bb7936facb20261b28b2d99e9b9fd3be7b212f3ac3233"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LWNFJYGGY7CTUR2MKD6OCOGPH5/bundle.json","state_url":"https://pith.science/pith/LWNFJYGGY7CTUR2MKD6OCOGPH5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LWNFJYGGY7CTUR2MKD6OCOGPH5/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":"2026-08-05T07:11:17Z","links":{"resolver":"https://pith.science/pith/LWNFJYGGY7CTUR2MKD6OCOGPH5","bundle":"https://pith.science/pith/LWNFJYGGY7CTUR2MKD6OCOGPH5/bundle.json","state":"https://pith.science/pith/LWNFJYGGY7CTUR2MKD6OCOGPH5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LWNFJYGGY7CTUR2MKD6OCOGPH5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LWNFJYGGY7CTUR2MKD6OCOGPH5","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":"9578fb621740b6bca9b287fc21991fcd64edd1bc183c38b5b16e7a3bb0e623e1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-27T18:52:07Z","title_canon_sha256":"7931a46ee722028694343234e0238fae075761d2346e14a627a72a44763d3125"},"schema_version":"1.0","source":{"id":"2511.22699","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.22699","created_at":"2026-06-23T03:13:51Z"},{"alias_kind":"arxiv_version","alias_value":"2511.22699v4","created_at":"2026-06-23T03:13:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.22699","created_at":"2026-06-23T03:13:51Z"},{"alias_kind":"pith_short_12","alias_value":"LWNFJYGGY7CT","created_at":"2026-06-23T03:13:51Z"},{"alias_kind":"pith_short_16","alias_value":"LWNFJYGGY7CTUR2M","created_at":"2026-06-23T03:13:51Z"},{"alias_kind":"pith_short_8","alias_value":"LWNFJYGG","created_at":"2026-06-23T03:13:51Z"}],"graph_snapshots":[{"event_id":"sha256:68a17eb424ab26b6e56bb7936facb20261b28b2d99e9b9fd3be7b212f3ac3233","target":"graph","created_at":"2026-06-23T03:13:51Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Z-Image achieves performance comparable to or surpassing that of leading competitors across various dimensions. Most notably, Z-Image exhibits exceptional capabilities in photorealistic image generation and bilingual text rendering, delivering results that rival top-tier commercial models, thereby demonstrating that state-of-the-art results are achievable with significantly reduced computational overhead."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that the curated data infrastructure, streamlined training curriculum, S3-DiT architecture, and few-step distillation with reward post-training directly produce the claimed performance levels without undisclosed advantages in training data scale or evaluation methodology."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Z-Image is an efficient 6B-parameter foundation model for image generation that rivals larger commercial systems in photorealism and bilingual text rendering through a new single-stream diffusion transformer and streamlined training."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A 6-billion-parameter image model reaches commercial-level photorealism and text rendering with far less training compute than larger rivals."}],"snapshot_sha256":"4d8df2d777d09a4012e36644cfa11712de1d248f02d73ef5697e2e891ffb41b1"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2511.22699/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The landscape of high-performance image generation models is currently dominated by proprietary systems, such as Nano Banana Pro and Seedream 4.0. Leading open-source alternatives, including Qwen-Image, Hunyuan-Image-3.0 and FLUX.2, are characterized by massive parameter counts (20B to 80B), making them impractical for inference, and fine-tuning on consumer-grade hardware. To address this gap, we propose Z-Image, an efficient 6B-parameter foundation generative model built upon a Scalable Single-Stream Diffusion Transformer (S3-DiT) architecture that challenges the \"scale-at-all-costs\" paradigm","authors_text":"Aiming Hao, Chi Zhang, David Liu, Dengyang Jiang, Dongyang Liu, Feng Yu, Huanqia Cai, Liangchen Li, Peng Gao, Qilong Wu, Ruikai Zhou, Ruoyi Du, Shifeng Zhang, Shijie Huang, Shilin Zhou, Sihan Cao, Steven Hoi, Xin Jin, Yuming Jiang, Zechao Zhan, Zhaohui Hou, Zhen Li, Zhong-Yu Li, Z-Image Team","cross_cats":[],"headline":"A 6-billion-parameter image model reaches commercial-level photorealism and text rendering with far less training compute than larger rivals.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-27T18:52:07Z","title":"Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.22699","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-11T14:01:29.639989Z","id":"0b562510-9624-47fc-bb30-bc162b42349b","model_set":{"reader":"grok-4.3"},"one_line_summary":"Z-Image is an efficient 6B-parameter foundation model for image generation that rivals larger commercial systems in photorealism and bilingual text rendering through a new single-stream diffusion transformer and streamlined training.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A 6-billion-parameter image model reaches commercial-level photorealism and text rendering with far less training compute than larger rivals.","strongest_claim":"Z-Image achieves performance comparable to or surpassing that of leading competitors across various dimensions. Most notably, Z-Image exhibits exceptional capabilities in photorealistic image generation and bilingual text rendering, delivering results that rival top-tier commercial models, thereby demonstrating that state-of-the-art results are achievable with significantly reduced computational overhead.","weakest_assumption":"The assumption that the curated data infrastructure, streamlined training curriculum, S3-DiT architecture, and few-step distillation with reward post-training directly produce the claimed performance levels without undisclosed advantages in training data scale or evaluation methodology."}},"verdict_id":"0b562510-9624-47fc-bb30-bc162b42349b"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a5ab5aab3db065263a5a7e83c280aa38eee84d944b3b47c9a15acf9fe9f12e7c","target":"record","created_at":"2026-06-23T03:13:51Z","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":"9578fb621740b6bca9b287fc21991fcd64edd1bc183c38b5b16e7a3bb0e623e1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-27T18:52:07Z","title_canon_sha256":"7931a46ee722028694343234e0238fae075761d2346e14a627a72a44763d3125"},"schema_version":"1.0","source":{"id":"2511.22699","kind":"arxiv","version":4}},"canonical_sha256":"5d9a54e0c6c7c53a474c50fce138cf3f5f1f1f2447b250f211ee8ec5105a655b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5d9a54e0c6c7c53a474c50fce138cf3f5f1f1f2447b250f211ee8ec5105a655b","first_computed_at":"2026-06-23T03:13:51.898241Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T03:13:51.898241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sch7r7H7IWsqK2VS5svG8DDkbu5GnJ44Vj5mYO1jmTRlJLl2/nkxBuoPJ0XYScVjflC+KwT6DN6l0QGAbL5XAQ==","signature_status":"signed_v1","signed_at":"2026-06-23T03:13:51.898783Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.22699","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5ab5aab3db065263a5a7e83c280aa38eee84d944b3b47c9a15acf9fe9f12e7c","sha256:68a17eb424ab26b6e56bb7936facb20261b28b2d99e9b9fd3be7b212f3ac3233"],"state_sha256":"765635189a79d5667787b7099b3f6689d435011b5514c32735c917551d790112"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hJB3HofXKrffk1yPyennH/NMkokgiJWPDirIixdBVClO7iiLXTGVQMusZlPC+F2JCD/kmMNdNjQ/9JjZS6O0Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T07:11:17.100118Z","bundle_sha256":"e103f9a7a2dc25529d61de0cb763869c667d82f7311e525981b2a99fba043dfe"}}