{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PST5I4D4GWZ3WMI4DFF7Q2JBJL","short_pith_number":"pith:PST5I4D4","canonical_record":{"source":{"id":"2512.07584","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-08T14:26:40Z","cross_cats_sorted":[],"title_canon_sha256":"6850a6385b82853bb522cf7464bd9f5be137f809e1f5a12dccdbef1f499b1388","abstract_canon_sha256":"9f227b0bccbebc8744b99cf4eb999281b276d24bbd380e88435359ab9f120f37"},"schema_version":"1.0"},"canonical_sha256":"7ca7d4707c35b3bb311c194bf869214ac510d55e742a7aa7acc0b9a76bf5c05d","source":{"kind":"arxiv","id":"2512.07584","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.07584","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"arxiv_version","alias_value":"2512.07584v1","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.07584","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"pith_short_12","alias_value":"PST5I4D4GWZ3","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"PST5I4D4GWZ3WMI4","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"PST5I4D4","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PST5I4D4GWZ3WMI4DFF7Q2JBJL","target":"record","payload":{"canonical_record":{"source":{"id":"2512.07584","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-08T14:26:40Z","cross_cats_sorted":[],"title_canon_sha256":"6850a6385b82853bb522cf7464bd9f5be137f809e1f5a12dccdbef1f499b1388","abstract_canon_sha256":"9f227b0bccbebc8744b99cf4eb999281b276d24bbd380e88435359ab9f120f37"},"schema_version":"1.0"},"canonical_sha256":"7ca7d4707c35b3bb311c194bf869214ac510d55e742a7aa7acc0b9a76bf5c05d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:48.572051Z","signature_b64":"XnkW3yujR+TtnhjQeS0NDpHgGMTIF5g9armddPj6BmbDPWUZc3Lt7feWb7BUbliiHuviA3A7ti2BletZBUo+Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ca7d4707c35b3bb311c194bf869214ac510d55e742a7aa7acc0b9a76bf5c05d","last_reissued_at":"2026-05-17T23:38:48.571583Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:48.571583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2512.07584","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":"2026-05-17T23:38:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c+TIBOKb7jpVhMSTI3dq+40moDY0L8MPRGd+5YhO5RJOJbOE9ps3PxZIeXwrZ0cx4iU9Q2Ye0OxHxen84riACg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T16:34:55.336980Z"},"content_sha256":"192fd0e1d2d1d9fd41e21583bb3dd01267dc0f1abac4a18dcaec0301444d0a6c","schema_version":"1.0","event_id":"sha256:192fd0e1d2d1d9fd41e21583bb3dd01267dc0f1abac4a18dcaec0301444d0a6c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PST5I4D4GWZ3WMI4DFF7Q2JBJL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LongCat-Image Technical Report","license":"http://creativecommons.org/licenses/by/4.0/","headline":"LongCat-Image achieves state-of-the-art Chinese text rendering in images using a compact 6B-parameter diffusion model.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoxian Tan, Jiale Huang, Jie Hu, Junqiang Wu, Jun-Yan He, Lishuai Gao, Meituan LongCat Team: Hanghang Ma, Songlin Xiao, Xiaoming Wei, Xiaoqi Ma, Xunliang Cai, Yayong Guan","submitted_at":"2025-12-08T14:26:40Z","abstract_excerpt":"We introduce LongCat-Image, a pioneering open-source and bilingual (Chinese-English) foundation model for image generation, designed to address core challenges in multilingual text rendering, photorealism, deployment efficiency, and developer accessibility prevalent in current leading models. 1) We achieve this through rigorous data curation strategies across the pre-training, mid-training, and SFT stages, complemented by the coordinated use of curated reward models during the RL phase. This strategy establishes the model as a new state-of-the-art (SOTA), delivering superior text-rendering cap"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"With a core diffusion model of only 6B parameters, LongCat-Image sets a new industry standard for Chinese character rendering, outperforming both major open-source and commercial solutions in coverage and accuracy while delivering superior text-rendering capabilities and remarkable photorealism.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that the curated data and reward models used in RL produce generalizable gains rather than benchmark-specific improvements, with no external independent verification of the SOTA claims provided in the abstract.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LongCat-Image delivers a compact 6B-parameter bilingual image generation model that sets new standards for Chinese character rendering accuracy and photorealism while remaining efficient and fully open-source.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"LongCat-Image achieves state-of-the-art Chinese text rendering in images using a compact 6B-parameter diffusion model.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e07d4e6ed66bfbeefbef9f8f1a3ada462b3b69383e72baab46eb26da46066bfe"},"source":{"id":"2512.07584","kind":"arxiv","version":1},"verdict":{"id":"593a971c-0aaa-424d-8150-f92b28b95f85","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T08:00:43.637852Z","strongest_claim":"With a core diffusion model of only 6B parameters, LongCat-Image sets a new industry standard for Chinese character rendering, outperforming both major open-source and commercial solutions in coverage and accuracy while delivering superior text-rendering capabilities and remarkable photorealism.","one_line_summary":"LongCat-Image delivers a compact 6B-parameter bilingual image generation model that sets new standards for Chinese character rendering accuracy and photorealism while remaining efficient and fully open-source.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that the curated data and reward models used in RL produce generalizable gains rather than benchmark-specific improvements, with no external independent verification of the SOTA claims provided in the abstract.","pith_extraction_headline":"LongCat-Image achieves state-of-the-art Chinese text rendering in images using a compact 6B-parameter diffusion model."},"references":{"count":32,"sample":[{"doi":"","year":null,"title":"Qwen-Image Technical Report","work_id":"d06d7ecc-7579-4f89-a60b-4278a0f3c562","ref_index":1,"cited_arxiv_id":"2508.02324","is_internal_anchor":true},{"doi":"","year":null,"title":"Seedream 2.0: A Native Chinese-English Bilingual Image Generation Foundation Model","work_id":"e285b9d3-0bf4-4f98-ba3a-e545425ab960","ref_index":2,"cited_arxiv_id":"2503.07703","is_internal_anchor":true},{"doi":"","year":null,"title":"Seedream 3.0 Technical Report","work_id":"013e56d0-7f47-4d0e-bbca-e9540fc0e0cc","ref_index":3,"cited_arxiv_id":"2504.11346","is_internal_anchor":true},{"doi":"","year":null,"title":"Seedream 4.0: Toward Next-generation Multimodal Image Generation","work_id":"15c839a0-48a3-4218-82b6-cac5b7f66e13","ref_index":4,"cited_arxiv_id":"2509.20427","is_internal_anchor":true},{"doi":"","year":null,"title":"Image editing with diffusion models: A survey.arXiv preprint arXiv:2504.13226, 2025a","work_id":"95cf95fb-4e54-4a77-8927-383d24d11972","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":32,"snapshot_sha256":"0a374f782ccdbb62f71140678d6bfb5bd836567d5d38290b959961ac33c15122","internal_anchors":28},"formal_canon":{"evidence_count":2,"snapshot_sha256":"74be8608be5a052ec66b6e86d6e8c6c721ad3d089d65cb2e13a22772031cfc5d"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"593a971c-0aaa-424d-8150-f92b28b95f85"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C2afGVA7cPw70bzL9Uthfxm0H7kP3EfyEgaN+Sqb9L3Za8nEKGiZyx6O2S0VjpB4EqPPx9rz31Oq340uJxuuBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T16:34:55.337837Z"},"content_sha256":"5d03a4f35e769140f188c89a0e102c98dadabd3c97a1621f8fe0311fa61d259b","schema_version":"1.0","event_id":"sha256:5d03a4f35e769140f188c89a0e102c98dadabd3c97a1621f8fe0311fa61d259b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PST5I4D4GWZ3WMI4DFF7Q2JBJL/bundle.json","state_url":"https://pith.science/pith/PST5I4D4GWZ3WMI4DFF7Q2JBJL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PST5I4D4GWZ3WMI4DFF7Q2JBJL/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":"2026-05-26T16:34:55Z","links":{"resolver":"https://pith.science/pith/PST5I4D4GWZ3WMI4DFF7Q2JBJL","bundle":"https://pith.science/pith/PST5I4D4GWZ3WMI4DFF7Q2JBJL/bundle.json","state":"https://pith.science/pith/PST5I4D4GWZ3WMI4DFF7Q2JBJL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PST5I4D4GWZ3WMI4DFF7Q2JBJL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PST5I4D4GWZ3WMI4DFF7Q2JBJL","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":"9f227b0bccbebc8744b99cf4eb999281b276d24bbd380e88435359ab9f120f37","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-08T14:26:40Z","title_canon_sha256":"6850a6385b82853bb522cf7464bd9f5be137f809e1f5a12dccdbef1f499b1388"},"schema_version":"1.0","source":{"id":"2512.07584","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.07584","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"arxiv_version","alias_value":"2512.07584v1","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.07584","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"pith_short_12","alias_value":"PST5I4D4GWZ3","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"PST5I4D4GWZ3WMI4","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"PST5I4D4","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:5d03a4f35e769140f188c89a0e102c98dadabd3c97a1621f8fe0311fa61d259b","target":"graph","created_at":"2026-05-17T23:38:48Z","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":"With a core diffusion model of only 6B parameters, LongCat-Image sets a new industry standard for Chinese character rendering, outperforming both major open-source and commercial solutions in coverage and accuracy while delivering superior text-rendering capabilities and remarkable photorealism."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that the curated data and reward models used in RL produce generalizable gains rather than benchmark-specific improvements, with no external independent verification of the SOTA claims provided in the abstract."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"LongCat-Image delivers a compact 6B-parameter bilingual image generation model that sets new standards for Chinese character rendering accuracy and photorealism while remaining efficient and fully open-source."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"LongCat-Image achieves state-of-the-art Chinese text rendering in images using a compact 6B-parameter diffusion model."}],"snapshot_sha256":"e07d4e6ed66bfbeefbef9f8f1a3ada462b3b69383e72baab46eb26da46066bfe"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"74be8608be5a052ec66b6e86d6e8c6c721ad3d089d65cb2e13a22772031cfc5d"},"paper":{"abstract_excerpt":"We introduce LongCat-Image, a pioneering open-source and bilingual (Chinese-English) foundation model for image generation, designed to address core challenges in multilingual text rendering, photorealism, deployment efficiency, and developer accessibility prevalent in current leading models. 1) We achieve this through rigorous data curation strategies across the pre-training, mid-training, and SFT stages, complemented by the coordinated use of curated reward models during the RL phase. This strategy establishes the model as a new state-of-the-art (SOTA), delivering superior text-rendering cap","authors_text":"Haoxian Tan, Jiale Huang, Jie Hu, Junqiang Wu, Jun-Yan He, Lishuai Gao, Meituan LongCat Team: Hanghang Ma, Songlin Xiao, Xiaoming Wei, Xiaoqi Ma, Xunliang Cai, Yayong Guan","cross_cats":[],"headline":"LongCat-Image achieves state-of-the-art Chinese text rendering in images using a compact 6B-parameter diffusion model.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-08T14:26:40Z","title":"LongCat-Image Technical Report"},"references":{"count":32,"internal_anchors":28,"resolved_work":32,"sample":[{"cited_arxiv_id":"2508.02324","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Qwen-Image Technical Report","work_id":"d06d7ecc-7579-4f89-a60b-4278a0f3c562","year":null},{"cited_arxiv_id":"2503.07703","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Seedream 2.0: A Native Chinese-English Bilingual Image Generation Foundation Model","work_id":"e285b9d3-0bf4-4f98-ba3a-e545425ab960","year":null},{"cited_arxiv_id":"2504.11346","doi":"","is_internal_anchor":true,"ref_index":3,"title":"Seedream 3.0 Technical Report","work_id":"013e56d0-7f47-4d0e-bbca-e9540fc0e0cc","year":null},{"cited_arxiv_id":"2509.20427","doi":"","is_internal_anchor":true,"ref_index":4,"title":"Seedream 4.0: Toward Next-generation Multimodal Image Generation","work_id":"15c839a0-48a3-4218-82b6-cac5b7f66e13","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Image editing with diffusion models: A survey.arXiv preprint arXiv:2504.13226, 2025a","work_id":"95cf95fb-4e54-4a77-8927-383d24d11972","year":null}],"snapshot_sha256":"0a374f782ccdbb62f71140678d6bfb5bd836567d5d38290b959961ac33c15122"},"source":{"id":"2512.07584","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-16T08:00:43.637852Z","id":"593a971c-0aaa-424d-8150-f92b28b95f85","model_set":{"reader":"grok-4.3"},"one_line_summary":"LongCat-Image delivers a compact 6B-parameter bilingual image generation model that sets new standards for Chinese character rendering accuracy and photorealism while remaining efficient and fully open-source.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"LongCat-Image achieves state-of-the-art Chinese text rendering in images using a compact 6B-parameter diffusion model.","strongest_claim":"With a core diffusion model of only 6B parameters, LongCat-Image sets a new industry standard for Chinese character rendering, outperforming both major open-source and commercial solutions in coverage and accuracy while delivering superior text-rendering capabilities and remarkable photorealism.","weakest_assumption":"The assumption that the curated data and reward models used in RL produce generalizable gains rather than benchmark-specific improvements, with no external independent verification of the SOTA claims provided in the abstract."}},"verdict_id":"593a971c-0aaa-424d-8150-f92b28b95f85"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:192fd0e1d2d1d9fd41e21583bb3dd01267dc0f1abac4a18dcaec0301444d0a6c","target":"record","created_at":"2026-05-17T23:38:48Z","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":"9f227b0bccbebc8744b99cf4eb999281b276d24bbd380e88435359ab9f120f37","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-08T14:26:40Z","title_canon_sha256":"6850a6385b82853bb522cf7464bd9f5be137f809e1f5a12dccdbef1f499b1388"},"schema_version":"1.0","source":{"id":"2512.07584","kind":"arxiv","version":1}},"canonical_sha256":"7ca7d4707c35b3bb311c194bf869214ac510d55e742a7aa7acc0b9a76bf5c05d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ca7d4707c35b3bb311c194bf869214ac510d55e742a7aa7acc0b9a76bf5c05d","first_computed_at":"2026-05-17T23:38:48.571583Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:48.571583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XnkW3yujR+TtnhjQeS0NDpHgGMTIF5g9armddPj6BmbDPWUZc3Lt7feWb7BUbliiHuviA3A7ti2BletZBUo+Aw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:48.572051Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.07584","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:192fd0e1d2d1d9fd41e21583bb3dd01267dc0f1abac4a18dcaec0301444d0a6c","sha256:5d03a4f35e769140f188c89a0e102c98dadabd3c97a1621f8fe0311fa61d259b"],"state_sha256":"b68aa655efb9da1daceda02f78e2b244f97f40d64574d21080440545c3e56b27"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"92jaGUtlHhrCKiZkjtvWBJXoRqlY/67jcZ2p+Ij36CYtun+4x/343FoVjJ+T2WInIl7MplrVgW1eZ/cecko/BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T16:34:55.341478Z","bundle_sha256":"39b3463e61ccd8192f71de754048a339cc6b328b46647f6d5513d78a0fc7bd75"}}