{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XOXV7X4LUOULXV7PNH2D5DGGUH","short_pith_number":"pith:XOXV7X4L","schema_version":"1.0","canonical_sha256":"bbaf5fdf8ba3a8bbd7ef69f43e8cc6a1d8b1a569666715363bc6caf5ffc2536c","source":{"kind":"arxiv","id":"2411.19722","version":2},"attestation_state":"computed","paper":{"title":"JetFormer: An Autoregressive Generative Model of Raw Images and Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Alexander Kolesnikov, Andr\\'e Susano Pinto, Michael Tschannen","submitted_at":"2024-11-29T14:14:59Z","abstract_excerpt":"Removing modeling constraints and unifying architectures across domains has been a key driver of the recent progress in training large multimodal models. However, most of these models still rely on many separately trained components such as modality-specific encoders and decoders. In this work, we further streamline joint generative modeling of images and text. We propose an autoregressive decoder-only transformer - JetFormer - which is trained to directly maximize the likelihood of raw data, without relying on any separately pretrained components, and can understand and generate both text and"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2411.19722","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-29T14:14:59Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"a2636ad6df8ec64da165921495f1431caa433355223879857aaa911e84c0c96c","abstract_canon_sha256":"8d0b00cf813d6ea5ada90b717a0319145d152aff9b42b5c93c90bd780d0d2f62"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:22.393824Z","signature_b64":"YPvgWw9AGKGrTjKUg9zflk3zf+HaW7s3qdzX4GnaWVofXyTR9TDx69cxKRSD9EjHIm+eu+VPEK2V/mb76YPtBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbaf5fdf8ba3a8bbd7ef69f43e8cc6a1d8b1a569666715363bc6caf5ffc2536c","last_reissued_at":"2026-07-05T11:05:22.393374Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:22.393374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"JetFormer: An Autoregressive Generative Model of Raw Images and Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Alexander Kolesnikov, Andr\\'e Susano Pinto, Michael Tschannen","submitted_at":"2024-11-29T14:14:59Z","abstract_excerpt":"Removing modeling constraints and unifying architectures across domains has been a key driver of the recent progress in training large multimodal models. However, most of these models still rely on many separately trained components such as modality-specific encoders and decoders. In this work, we further streamline joint generative modeling of images and text. We propose an autoregressive decoder-only transformer - JetFormer - which is trained to directly maximize the likelihood of raw data, without relying on any separately pretrained components, and can understand and generate both text and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19722","kind":"arxiv","version":2},"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/2411.19722/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2411.19722","created_at":"2026-07-05T11:05:22.393434+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.19722v2","created_at":"2026-07-05T11:05:22.393434+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19722","created_at":"2026-07-05T11:05:22.393434+00:00"},{"alias_kind":"pith_short_12","alias_value":"XOXV7X4LUOUL","created_at":"2026-07-05T11:05:22.393434+00:00"},{"alias_kind":"pith_short_16","alias_value":"XOXV7X4LUOULXV7P","created_at":"2026-07-05T11:05:22.393434+00:00"},{"alias_kind":"pith_short_8","alias_value":"XOXV7X4L","created_at":"2026-07-05T11:05:22.393434+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26016","citing_title":"MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26016","citing_title":"MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15741","citing_title":"HyperDiT: Hyper-Connected Transformers for High-Fidelity Pixel-Space Diffusion","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18267","citing_title":"SRC-Flow: Compact Semantic Representations Enable Normalizing Flows for Image Generation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27760","citing_title":"PixelU: A U-Shaped Transformer for Efficient End-to-End Pixel Diffusion","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27978","citing_title":"Parallel Rollout Approximation for Pixel-Space Autoregressive Image Generation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15741","citing_title":"HyperDiT: Hyper-Connected Transformers for High-Fidelity Pixel-Space Diffusion","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17759","citing_title":"FrequencyBooster: Full-Frequency Modeling for High-Fidelity Pixel Diffusion","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18267","citing_title":"SRC-Flow: Compact Semantic Representations Enable Normalizing Flows for Image Generation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2511.19365","citing_title":"DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2501.07542","citing_title":"Imagine while Reasoning in Space: Multimodal Visualization-of-Thought","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02355","citing_title":"From Broad Exploration to Stable Synthesis: Entropy-Guided Optimization for Autoregressive Image Generation","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20041","citing_title":"Normalizing Flows with Iterative Denoising","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XOXV7X4LUOULXV7PNH2D5DGGUH","json":"https://pith.science/pith/XOXV7X4LUOULXV7PNH2D5DGGUH.json","graph_json":"https://pith.science/api/pith-number/XOXV7X4LUOULXV7PNH2D5DGGUH/graph.json","events_json":"https://pith.science/api/pith-number/XOXV7X4LUOULXV7PNH2D5DGGUH/events.json","paper":"https://pith.science/paper/XOXV7X4L"},"agent_actions":{"view_html":"https://pith.science/pith/XOXV7X4LUOULXV7PNH2D5DGGUH","download_json":"https://pith.science/pith/XOXV7X4LUOULXV7PNH2D5DGGUH.json","view_paper":"https://pith.science/paper/XOXV7X4L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.19722&json=true","fetch_graph":"https://pith.science/api/pith-number/XOXV7X4LUOULXV7PNH2D5DGGUH/graph.json","fetch_events":"https://pith.science/api/pith-number/XOXV7X4LUOULXV7PNH2D5DGGUH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XOXV7X4LUOULXV7PNH2D5DGGUH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XOXV7X4LUOULXV7PNH2D5DGGUH/action/storage_attestation","attest_author":"https://pith.science/pith/XOXV7X4LUOULXV7PNH2D5DGGUH/action/author_attestation","sign_citation":"https://pith.science/pith/XOXV7X4LUOULXV7PNH2D5DGGUH/action/citation_signature","submit_replication":"https://pith.science/pith/XOXV7X4LUOULXV7PNH2D5DGGUH/action/replication_record"}},"created_at":"2026-07-05T11:05:22.393434+00:00","updated_at":"2026-07-05T11:05:22.393434+00:00"}