{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:XLMUT3UJRA4NW74L6ILZWM47Z2","short_pith_number":"pith:XLMUT3UJ","canonical_record":{"source":{"id":"2604.24763","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-27T17:59:56Z","cross_cats_sorted":[],"title_canon_sha256":"fcd3d766fa645fb882bbaf1a54ecfdd2df1a45fc353c92e79193608fca6e7dc7","abstract_canon_sha256":"6da0401ac5d63b909a123cde4a092dd4683b560b4692dc78f5060d4c533dfc94"},"schema_version":"1.0"},"canonical_sha256":"bad949ee898838db7f8bf2179b339fceb6b0809c8883ffb59838abe81b908e48","source":{"kind":"arxiv","id":"2604.24763","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.24763","created_at":"2026-05-20T00:04:32Z"},{"alias_kind":"arxiv_version","alias_value":"2604.24763v2","created_at":"2026-05-20T00:04:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.24763","created_at":"2026-05-20T00:04:32Z"},{"alias_kind":"pith_short_12","alias_value":"XLMUT3UJRA4N","created_at":"2026-05-20T00:04:32Z"},{"alias_kind":"pith_short_16","alias_value":"XLMUT3UJRA4NW74L","created_at":"2026-05-20T00:04:32Z"},{"alias_kind":"pith_short_8","alias_value":"XLMUT3UJ","created_at":"2026-05-20T00:04:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:XLMUT3UJRA4NW74L6ILZWM47Z2","target":"record","payload":{"canonical_record":{"source":{"id":"2604.24763","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-27T17:59:56Z","cross_cats_sorted":[],"title_canon_sha256":"fcd3d766fa645fb882bbaf1a54ecfdd2df1a45fc353c92e79193608fca6e7dc7","abstract_canon_sha256":"6da0401ac5d63b909a123cde4a092dd4683b560b4692dc78f5060d4c533dfc94"},"schema_version":"1.0"},"canonical_sha256":"bad949ee898838db7f8bf2179b339fceb6b0809c8883ffb59838abe81b908e48","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:32.948674Z","signature_b64":"JPMCX/LgRJuGEDhEOLS78VC/igbClh+2pLJuiHONPsWApuFQj2owpafYlCYPbMwpHzV8yQ5pDHiRVVF/o2qkBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bad949ee898838db7f8bf2179b339fceb6b0809c8883ffb59838abe81b908e48","last_reissued_at":"2026-05-20T00:04:32.947791Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:32.947791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.24763","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:04:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Is88d0AZV6LzPX7EBDwqW/GbDzXERQnVaNbuDv7hGWsmy8qunGowH2JL4kQ6IvAiyg36rLtQa0Pj0nZpo154Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T19:25:28.630286Z"},"content_sha256":"d040c2a2ed5aaba368fa6ed1847b1167dbf715a4c42ccae3c67af8ac9c7b2cc9","schema_version":"1.0","event_id":"sha256:d040c2a2ed5aaba368fa6ed1847b1167dbf715a4c42ccae3c67af8ac9c7b2cc9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:XLMUT3UJRA4NW74L6ILZWM47Z2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Tuna-2 shows that simple pixel patch embeddings can replace pretrained vision encoders for unified multimodal understanding and generation.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Belinda Zeng, Jonas Schult, Luke Zettlemoyer, Mengzhao Chen, Ping Luo, Sen He, Shoufa Chen, Tao Xiang, Tianhong Li, Weiming Ren, Wenhu Chen, Xiaoke Huang, Yatai Ji, Yuren Cong, Zhiheng Liu","submitted_at":"2026-04-27T17:59:56Z","abstract_excerpt":"Unified multimodal models typically rely on pretrained vision encoders and use separate visual representations for understanding and generation, creating misalignment between the two tasks and preventing fully end-to-end optimization from raw pixels. We introduce Tuna-2, a native unified multimodal model that performs visual understanding and generation directly based on pixel embeddings. Tuna-2 drastically simplifies the model architecture by employing simple patch embedding layers to encode visual input, completely discarding the modular vision encoder designs such as the VAE or the represen"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Tuna-2 achieves state-of-the-art performance in multimodal benchmarks, demonstrating that unified pixel-space modelling can fully compete with latent-space approaches for high-quality image generation. Moreover, while the encoder-based variant converges faster in early pretraining, Tuna-2's encoder-free design achieves stronger multimodal understanding at scale, particularly on tasks requiring fine-grained visual perception.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That simple patch embedding layers applied directly to pixels can extract sufficient visual features for both high-quality generation and fine-grained understanding without the inductive biases or pretraining provided by dedicated vision encoders.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Tuna-2 shows pixel embeddings can replace vision encoders in unified multimodal models, achieving competitive or superior results on understanding and generation benchmarks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Tuna-2 shows that simple pixel patch embeddings can replace pretrained vision encoders for unified multimodal understanding and generation.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"0d852a7d6154f4060b4655365e59ed1af7074e4b6ca131d8bfbdf770df1f3477"},"source":{"id":"2604.24763","kind":"arxiv","version":2},"verdict":{"id":"c5793468-ad57-400e-91e7-1d7890d12b31","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T04:27:47.732435Z","strongest_claim":"Tuna-2 achieves state-of-the-art performance in multimodal benchmarks, demonstrating that unified pixel-space modelling can fully compete with latent-space approaches for high-quality image generation. Moreover, while the encoder-based variant converges faster in early pretraining, Tuna-2's encoder-free design achieves stronger multimodal understanding at scale, particularly on tasks requiring fine-grained visual perception.","one_line_summary":"Tuna-2 shows pixel embeddings can replace vision encoders in unified multimodal models, achieving competitive or superior results on understanding and generation benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That simple patch embedding layers applied directly to pixels can extract sufficient visual features for both high-quality generation and fine-grained understanding without the inductive biases or pretraining provided by dedicated vision encoders.","pith_extraction_headline":"Tuna-2 shows that simple pixel patch embeddings can replace pretrained vision encoders for unified multimodal understanding and generation."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.24763/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_compliance","ran_at":"2026-05-19T21:44:27.612842Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"fd1d77f395f8cfc7b6286c0bd81ecda604b883af1c59a7bd11bba05c71223451"},"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":"c5793468-ad57-400e-91e7-1d7890d12b31"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:04:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l3B/TKW5xISDXpfS7tGWu/OeS5zFumXXo/8uChBjph/ZCdb2YTUcPmU1TyB3uq8Gs0oNac2aIL7Kof4HoQAFCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T19:25:28.630815Z"},"content_sha256":"0b5ea6a5fc0e6d83b937a7c33e707ede1a7e3a30398a97d4d5e2d849f64ef8fc","schema_version":"1.0","event_id":"sha256:0b5ea6a5fc0e6d83b937a7c33e707ede1a7e3a30398a97d4d5e2d849f64ef8fc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XLMUT3UJRA4NW74L6ILZWM47Z2/bundle.json","state_url":"https://pith.science/pith/XLMUT3UJRA4NW74L6ILZWM47Z2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XLMUT3UJRA4NW74L6ILZWM47Z2/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":"2026-06-02T19:25:28Z","links":{"resolver":"https://pith.science/pith/XLMUT3UJRA4NW74L6ILZWM47Z2","bundle":"https://pith.science/pith/XLMUT3UJRA4NW74L6ILZWM47Z2/bundle.json","state":"https://pith.science/pith/XLMUT3UJRA4NW74L6ILZWM47Z2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XLMUT3UJRA4NW74L6ILZWM47Z2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XLMUT3UJRA4NW74L6ILZWM47Z2","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":"6da0401ac5d63b909a123cde4a092dd4683b560b4692dc78f5060d4c533dfc94","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-27T17:59:56Z","title_canon_sha256":"fcd3d766fa645fb882bbaf1a54ecfdd2df1a45fc353c92e79193608fca6e7dc7"},"schema_version":"1.0","source":{"id":"2604.24763","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.24763","created_at":"2026-05-20T00:04:32Z"},{"alias_kind":"arxiv_version","alias_value":"2604.24763v2","created_at":"2026-05-20T00:04:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.24763","created_at":"2026-05-20T00:04:32Z"},{"alias_kind":"pith_short_12","alias_value":"XLMUT3UJRA4N","created_at":"2026-05-20T00:04:32Z"},{"alias_kind":"pith_short_16","alias_value":"XLMUT3UJRA4NW74L","created_at":"2026-05-20T00:04:32Z"},{"alias_kind":"pith_short_8","alias_value":"XLMUT3UJ","created_at":"2026-05-20T00:04:32Z"}],"graph_snapshots":[{"event_id":"sha256:0b5ea6a5fc0e6d83b937a7c33e707ede1a7e3a30398a97d4d5e2d849f64ef8fc","target":"graph","created_at":"2026-05-20T00:04:32Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Tuna-2 achieves state-of-the-art performance in multimodal benchmarks, demonstrating that unified pixel-space modelling can fully compete with latent-space approaches for high-quality image generation. Moreover, while the encoder-based variant converges faster in early pretraining, Tuna-2's encoder-free design achieves stronger multimodal understanding at scale, particularly on tasks requiring fine-grained visual perception."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That simple patch embedding layers applied directly to pixels can extract sufficient visual features for both high-quality generation and fine-grained understanding without the inductive biases or pretraining provided by dedicated vision encoders."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Tuna-2 shows pixel embeddings can replace vision encoders in unified multimodal models, achieving competitive or superior results on understanding and generation benchmarks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Tuna-2 shows that simple pixel patch embeddings can replace pretrained vision encoders for unified multimodal understanding and generation."}],"snapshot_sha256":"0d852a7d6154f4060b4655365e59ed1af7074e4b6ca131d8bfbdf770df1f3477"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T21:44:27.612842Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2604.24763/integrity.json","findings":[],"snapshot_sha256":"fd1d77f395f8cfc7b6286c0bd81ecda604b883af1c59a7bd11bba05c71223451","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unified multimodal models typically rely on pretrained vision encoders and use separate visual representations for understanding and generation, creating misalignment between the two tasks and preventing fully end-to-end optimization from raw pixels. We introduce Tuna-2, a native unified multimodal model that performs visual understanding and generation directly based on pixel embeddings. Tuna-2 drastically simplifies the model architecture by employing simple patch embedding layers to encode visual input, completely discarding the modular vision encoder designs such as the VAE or the represen","authors_text":"Belinda Zeng, Jonas Schult, Luke Zettlemoyer, Mengzhao Chen, Ping Luo, Sen He, Shoufa Chen, Tao Xiang, Tianhong Li, Weiming Ren, Wenhu Chen, Xiaoke Huang, Yatai Ji, Yuren Cong, Zhiheng Liu","cross_cats":[],"headline":"Tuna-2 shows that simple pixel patch embeddings can replace pretrained vision encoders for unified multimodal understanding and generation.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-27T17:59:56Z","title":"Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.24763","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-08T04:27:47.732435Z","id":"c5793468-ad57-400e-91e7-1d7890d12b31","model_set":{"reader":"grok-4.3"},"one_line_summary":"Tuna-2 shows pixel embeddings can replace vision encoders in unified multimodal models, achieving competitive or superior results on understanding and generation benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Tuna-2 shows that simple pixel patch embeddings can replace pretrained vision encoders for unified multimodal understanding and generation.","strongest_claim":"Tuna-2 achieves state-of-the-art performance in multimodal benchmarks, demonstrating that unified pixel-space modelling can fully compete with latent-space approaches for high-quality image generation. Moreover, while the encoder-based variant converges faster in early pretraining, Tuna-2's encoder-free design achieves stronger multimodal understanding at scale, particularly on tasks requiring fine-grained visual perception.","weakest_assumption":"That simple patch embedding layers applied directly to pixels can extract sufficient visual features for both high-quality generation and fine-grained understanding without the inductive biases or pretraining provided by dedicated vision encoders."}},"verdict_id":"c5793468-ad57-400e-91e7-1d7890d12b31"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d040c2a2ed5aaba368fa6ed1847b1167dbf715a4c42ccae3c67af8ac9c7b2cc9","target":"record","created_at":"2026-05-20T00:04:32Z","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":"6da0401ac5d63b909a123cde4a092dd4683b560b4692dc78f5060d4c533dfc94","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-27T17:59:56Z","title_canon_sha256":"fcd3d766fa645fb882bbaf1a54ecfdd2df1a45fc353c92e79193608fca6e7dc7"},"schema_version":"1.0","source":{"id":"2604.24763","kind":"arxiv","version":2}},"canonical_sha256":"bad949ee898838db7f8bf2179b339fceb6b0809c8883ffb59838abe81b908e48","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bad949ee898838db7f8bf2179b339fceb6b0809c8883ffb59838abe81b908e48","first_computed_at":"2026-05-20T00:04:32.947791Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:04:32.947791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JPMCX/LgRJuGEDhEOLS78VC/igbClh+2pLJuiHONPsWApuFQj2owpafYlCYPbMwpHzV8yQ5pDHiRVVF/o2qkBw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:04:32.948674Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.24763","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d040c2a2ed5aaba368fa6ed1847b1167dbf715a4c42ccae3c67af8ac9c7b2cc9","sha256:0b5ea6a5fc0e6d83b937a7c33e707ede1a7e3a30398a97d4d5e2d849f64ef8fc"],"state_sha256":"1d5fdcf6245aa6e9ff568f26633ed3432d22ea254676afd7f21184c09827f310"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hBh4v9lnQdhhoFLz0/wNzEW29PUIHgh/mWzFtKpnUo4CYvV3AaeWRtT5a70zWIgyfwjpu9tMfs+Ir3wHlPwwCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T19:25:28.633011Z","bundle_sha256":"12b3fabf5dcf924b3dd8d800e66f97f94f277b16297b5e05cc91601cfaeed15a"}}