{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:Z7J6R26O2WMKTIDAPIVAZTPWWO","short_pith_number":"pith:Z7J6R26O","canonical_record":{"source":{"id":"2605.00809","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-01T17:51:38Z","cross_cats_sorted":[],"title_canon_sha256":"928e2a93b338332a1a6ae9c2c6c6ad21678f39ee6c7230cefc2936ba17eeb327","abstract_canon_sha256":"fab2a47d18f8a0fe7e8c6b249310094018ee16cca82076d63b06ce86bd610cfd"},"schema_version":"1.0"},"canonical_sha256":"cfd3e8ebced598a9a0607a2a0ccdf6b3880c85160ddfe080754e7dfd7ec6e7ba","source":{"kind":"arxiv","id":"2605.00809","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.00809","created_at":"2026-06-10T01:10:02Z"},{"alias_kind":"arxiv_version","alias_value":"2605.00809v2","created_at":"2026-06-10T01:10:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.00809","created_at":"2026-06-10T01:10:02Z"},{"alias_kind":"pith_short_12","alias_value":"Z7J6R26O2WMK","created_at":"2026-06-10T01:10:02Z"},{"alias_kind":"pith_short_16","alias_value":"Z7J6R26O2WMKTIDA","created_at":"2026-06-10T01:10:02Z"},{"alias_kind":"pith_short_8","alias_value":"Z7J6R26O","created_at":"2026-06-10T01:10:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:Z7J6R26O2WMKTIDAPIVAZTPWWO","target":"record","payload":{"canonical_record":{"source":{"id":"2605.00809","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-01T17:51:38Z","cross_cats_sorted":[],"title_canon_sha256":"928e2a93b338332a1a6ae9c2c6c6ad21678f39ee6c7230cefc2936ba17eeb327","abstract_canon_sha256":"fab2a47d18f8a0fe7e8c6b249310094018ee16cca82076d63b06ce86bd610cfd"},"schema_version":"1.0"},"canonical_sha256":"cfd3e8ebced598a9a0607a2a0ccdf6b3880c85160ddfe080754e7dfd7ec6e7ba","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:02.636520Z","signature_b64":"EqUon7kM3cU7hofmnMZO6EnHWCwmEpCrG3E4migsgGhOfYYt9jmJJLo7yr7rkIt5zHYtxp8wNMBl/gkDfB9cDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfd3e8ebced598a9a0607a2a0ccdf6b3880c85160ddfe080754e7dfd7ec6e7ba","last_reissued_at":"2026-06-10T01:10:02.635414Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:02.635414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.00809","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":"2026-06-10T01:10:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Px1q3Qoy+M0IHqC9b0qyli5UY90ku9rx6ceCEo8EQgMu27g4r5oxLBs63vspdykMgyRApzPBgqGLYs+HpiSDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T03:50:15.081966Z"},"content_sha256":"2f6dba33760b04555499ba0df88a6843eb6c10a43df773ec8d8f76f9603c2c5c","schema_version":"1.0","event_id":"sha256:2f6dba33760b04555499ba0df88a6843eb6c10a43df773ec8d8f76f9603c2c5c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:Z7J6R26O2WMKTIDAPIVAZTPWWO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Let ViT Speak: Generative Language-Image Pre-training","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"A ViT can learn to generate language tokens from visual tokens using only a language modeling objective, aligning it with autoregressive LLMs without contrastive batches or a separate text decoder.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mengcheng Lan, Qi She, Weixian Lei, Yan Fang, Yao Zhao, Yingchen Yu, Yujie Zhong, Yunchao Wei, Yunqing Zhao, Zilong Huang","submitted_at":"2026-05-01T17:51:38Z","abstract_excerpt":"In this paper, we present \\textbf{Gen}erative \\textbf{L}anguage-\\textbf{I}mage \\textbf{P}re-training (GenLIP), a minimalist generative pretraining framework for Vision Transformers (ViTs) designed for multimodal large language models (MLLMs). To better align vision encoders with the autoregressive nature of LLMs, GenLIP trains a ViT to predict language tokens directly from visual tokens using a standard language modeling objective, without contrastive batch construction or an additional text decoder. This design offers three key advantages: (1) \\textbf{Simplicity}: a single transformer jointly"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Trained on 8B samples from Recap-DataComp-1B, GenLIP matches or surpasses strong baselines despite using substantially less pretraining data. After continued pretraining on multi-resolution images at native aspect ratios, GenLIP further improves on detail-sensitive tasks such as OCR and chart understanding.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That training a ViT to predict language tokens directly from visual tokens using only a language modeling objective will produce a vision encoder that aligns effectively with autoregressive LLMs without needing contrastive batch construction or an additional text decoder.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"GenLIP pretrains ViTs to generate language tokens from visual tokens via autoregressive language modeling, matching strong baselines on multimodal tasks with less data.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A ViT can learn to generate language tokens from visual tokens using only a language modeling objective, aligning it with autoregressive LLMs without contrastive batches or a separate text decoder.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"37db47e83e491e57c877e035697f97c7aaa32e8fa769b261b6652a58510634ce"},"source":{"id":"2605.00809","kind":"arxiv","version":2},"verdict":{"id":"7e04d2db-b33e-497a-a045-a60eb4c954ca","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-09T18:53:36.754036Z","strongest_claim":"Trained on 8B samples from Recap-DataComp-1B, GenLIP matches or surpasses strong baselines despite using substantially less pretraining data. After continued pretraining on multi-resolution images at native aspect ratios, GenLIP further improves on detail-sensitive tasks such as OCR and chart understanding.","one_line_summary":"GenLIP pretrains ViTs to generate language tokens from visual tokens via autoregressive language modeling, matching strong baselines on multimodal tasks with less data.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That training a ViT to predict language tokens directly from visual tokens using only a language modeling objective will produce a vision encoder that aligns effectively with autoregressive LLMs without needing contrastive batch construction or an additional text decoder.","pith_extraction_headline":"A ViT can learn to generate language tokens from visual tokens using only a language modeling objective, aligning it with autoregressive LLMs without contrastive batches or a separate text decoder."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.00809/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T19:33:29.536387Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T17:48:59.422737Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"87f41b401d52c132de956a21acbf104e1d30a05eeeaee098f27c8e0b6531bd5e"},"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":"7e04d2db-b33e-497a-a045-a60eb4c954ca"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-10T01:10:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M01c5BGrXcU7s4tnz/nMStd1LmNNTqGjBm8DbqZcebJg/wATsBpB8s8aYZQuc9JUPuSO+nX4KMHbCzcQuamqDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T03:50:15.082449Z"},"content_sha256":"a9d50e299ac5597d0b8a2da47aa12a051e41ef24b47f45d0a361e0cf553d2613","schema_version":"1.0","event_id":"sha256:a9d50e299ac5597d0b8a2da47aa12a051e41ef24b47f45d0a361e0cf553d2613"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z7J6R26O2WMKTIDAPIVAZTPWWO/bundle.json","state_url":"https://pith.science/pith/Z7J6R26O2WMKTIDAPIVAZTPWWO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z7J6R26O2WMKTIDAPIVAZTPWWO/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":"2026-07-09T03:50:15Z","links":{"resolver":"https://pith.science/pith/Z7J6R26O2WMKTIDAPIVAZTPWWO","bundle":"https://pith.science/pith/Z7J6R26O2WMKTIDAPIVAZTPWWO/bundle.json","state":"https://pith.science/pith/Z7J6R26O2WMKTIDAPIVAZTPWWO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z7J6R26O2WMKTIDAPIVAZTPWWO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Z7J6R26O2WMKTIDAPIVAZTPWWO","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":"fab2a47d18f8a0fe7e8c6b249310094018ee16cca82076d63b06ce86bd610cfd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-01T17:51:38Z","title_canon_sha256":"928e2a93b338332a1a6ae9c2c6c6ad21678f39ee6c7230cefc2936ba17eeb327"},"schema_version":"1.0","source":{"id":"2605.00809","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.00809","created_at":"2026-06-10T01:10:02Z"},{"alias_kind":"arxiv_version","alias_value":"2605.00809v2","created_at":"2026-06-10T01:10:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.00809","created_at":"2026-06-10T01:10:02Z"},{"alias_kind":"pith_short_12","alias_value":"Z7J6R26O2WMK","created_at":"2026-06-10T01:10:02Z"},{"alias_kind":"pith_short_16","alias_value":"Z7J6R26O2WMKTIDA","created_at":"2026-06-10T01:10:02Z"},{"alias_kind":"pith_short_8","alias_value":"Z7J6R26O","created_at":"2026-06-10T01:10:02Z"}],"graph_snapshots":[{"event_id":"sha256:a9d50e299ac5597d0b8a2da47aa12a051e41ef24b47f45d0a361e0cf553d2613","target":"graph","created_at":"2026-06-10T01:10:02Z","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":"Trained on 8B samples from Recap-DataComp-1B, GenLIP matches or surpasses strong baselines despite using substantially less pretraining data. After continued pretraining on multi-resolution images at native aspect ratios, GenLIP further improves on detail-sensitive tasks such as OCR and chart understanding."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That training a ViT to predict language tokens directly from visual tokens using only a language modeling objective will produce a vision encoder that aligns effectively with autoregressive LLMs without needing contrastive batch construction or an additional text decoder."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"GenLIP pretrains ViTs to generate language tokens from visual tokens via autoregressive language modeling, matching strong baselines on multimodal tasks with less data."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A ViT can learn to generate language tokens from visual tokens using only a language modeling objective, aligning it with autoregressive LLMs without contrastive batches or a separate text decoder."}],"snapshot_sha256":"37db47e83e491e57c877e035697f97c7aaa32e8fa769b261b6652a58510634ce"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T19:33:29.536387Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T17:48:59.422737Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.00809/integrity.json","findings":[],"snapshot_sha256":"87f41b401d52c132de956a21acbf104e1d30a05eeeaee098f27c8e0b6531bd5e","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present \\textbf{Gen}erative \\textbf{L}anguage-\\textbf{I}mage \\textbf{P}re-training (GenLIP), a minimalist generative pretraining framework for Vision Transformers (ViTs) designed for multimodal large language models (MLLMs). To better align vision encoders with the autoregressive nature of LLMs, GenLIP trains a ViT to predict language tokens directly from visual tokens using a standard language modeling objective, without contrastive batch construction or an additional text decoder. This design offers three key advantages: (1) \\textbf{Simplicity}: a single transformer jointly","authors_text":"Mengcheng Lan, Qi She, Weixian Lei, Yan Fang, Yao Zhao, Yingchen Yu, Yujie Zhong, Yunchao Wei, Yunqing Zhao, Zilong Huang","cross_cats":[],"headline":"A ViT can learn to generate language tokens from visual tokens using only a language modeling objective, aligning it with autoregressive LLMs without contrastive batches or a separate text decoder.","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-01T17:51:38Z","title":"Let ViT Speak: Generative Language-Image Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.00809","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-09T18:53:36.754036Z","id":"7e04d2db-b33e-497a-a045-a60eb4c954ca","model_set":{"reader":"grok-4.3"},"one_line_summary":"GenLIP pretrains ViTs to generate language tokens from visual tokens via autoregressive language modeling, matching strong baselines on multimodal tasks with less data.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A ViT can learn to generate language tokens from visual tokens using only a language modeling objective, aligning it with autoregressive LLMs without contrastive batches or a separate text decoder.","strongest_claim":"Trained on 8B samples from Recap-DataComp-1B, GenLIP matches or surpasses strong baselines despite using substantially less pretraining data. After continued pretraining on multi-resolution images at native aspect ratios, GenLIP further improves on detail-sensitive tasks such as OCR and chart understanding.","weakest_assumption":"That training a ViT to predict language tokens directly from visual tokens using only a language modeling objective will produce a vision encoder that aligns effectively with autoregressive LLMs without needing contrastive batch construction or an additional text decoder."}},"verdict_id":"7e04d2db-b33e-497a-a045-a60eb4c954ca"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2f6dba33760b04555499ba0df88a6843eb6c10a43df773ec8d8f76f9603c2c5c","target":"record","created_at":"2026-06-10T01:10:02Z","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":"fab2a47d18f8a0fe7e8c6b249310094018ee16cca82076d63b06ce86bd610cfd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-01T17:51:38Z","title_canon_sha256":"928e2a93b338332a1a6ae9c2c6c6ad21678f39ee6c7230cefc2936ba17eeb327"},"schema_version":"1.0","source":{"id":"2605.00809","kind":"arxiv","version":2}},"canonical_sha256":"cfd3e8ebced598a9a0607a2a0ccdf6b3880c85160ddfe080754e7dfd7ec6e7ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cfd3e8ebced598a9a0607a2a0ccdf6b3880c85160ddfe080754e7dfd7ec6e7ba","first_computed_at":"2026-06-10T01:10:02.635414Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:10:02.635414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EqUon7kM3cU7hofmnMZO6EnHWCwmEpCrG3E4migsgGhOfYYt9jmJJLo7yr7rkIt5zHYtxp8wNMBl/gkDfB9cDw==","signature_status":"signed_v1","signed_at":"2026-06-10T01:10:02.636520Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.00809","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2f6dba33760b04555499ba0df88a6843eb6c10a43df773ec8d8f76f9603c2c5c","sha256:a9d50e299ac5597d0b8a2da47aa12a051e41ef24b47f45d0a361e0cf553d2613"],"state_sha256":"7b2495280d9db648eb9e6ca0dc868cd9683cd9bc8fd6b86f87523e82740588a4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pV4ymA9eH/WyAbr/L+Khc7kthU/AuUTyQIY2boVK6kaoqfF/ODEKwm1WI0B81Hq7bJ8ud/brWaj6sIoESiEqBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T03:50:15.084556Z","bundle_sha256":"347e44fb395d1542d6e376ac5edd5fa2d77d28391c55b58cbdb192f6f4ec3ae1"}}