{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XOXV7X4LUOULXV7PNH2D5DGGUH","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":"8d0b00cf813d6ea5ada90b717a0319145d152aff9b42b5c93c90bd780d0d2f62","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-29T14:14:59Z","title_canon_sha256":"a2636ad6df8ec64da165921495f1431caa433355223879857aaa911e84c0c96c"},"schema_version":"1.0","source":{"id":"2411.19722","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.19722","created_at":"2026-07-05T11:05:22Z"},{"alias_kind":"arxiv_version","alias_value":"2411.19722v2","created_at":"2026-07-05T11:05:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19722","created_at":"2026-07-05T11:05:22Z"},{"alias_kind":"pith_short_12","alias_value":"XOXV7X4LUOUL","created_at":"2026-07-05T11:05:22Z"},{"alias_kind":"pith_short_16","alias_value":"XOXV7X4LUOULXV7P","created_at":"2026-07-05T11:05:22Z"},{"alias_kind":"pith_short_8","alias_value":"XOXV7X4L","created_at":"2026-07-05T11:05:22Z"}],"graph_snapshots":[{"event_id":"sha256:df72ecf5dc4ee70593251f47c40b0917602f04a25774d930c7ae51bf467bdefc","target":"graph","created_at":"2026-07-05T11:05:22Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2411.19722/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alexander Kolesnikov, Andr\\'e Susano Pinto, Michael Tschannen","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-29T14:14:59Z","title":"JetFormer: An Autoregressive Generative Model of Raw Images and Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19722","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3cb3ae6382a0d5f2f94d9b6bf002c39e6dcb26cef1d66964f9f9871926b37351","target":"record","created_at":"2026-07-05T11:05:22Z","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":"8d0b00cf813d6ea5ada90b717a0319145d152aff9b42b5c93c90bd780d0d2f62","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-29T14:14:59Z","title_canon_sha256":"a2636ad6df8ec64da165921495f1431caa433355223879857aaa911e84c0c96c"},"schema_version":"1.0","source":{"id":"2411.19722","kind":"arxiv","version":2}},"canonical_sha256":"bbaf5fdf8ba3a8bbd7ef69f43e8cc6a1d8b1a569666715363bc6caf5ffc2536c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bbaf5fdf8ba3a8bbd7ef69f43e8cc6a1d8b1a569666715363bc6caf5ffc2536c","first_computed_at":"2026-07-05T11:05:22.393374Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:22.393374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YPvgWw9AGKGrTjKUg9zflk3zf+HaW7s3qdzX4GnaWVofXyTR9TDx69cxKRSD9EjHIm+eu+VPEK2V/mb76YPtBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:22.393824Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.19722","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3cb3ae6382a0d5f2f94d9b6bf002c39e6dcb26cef1d66964f9f9871926b37351","sha256:df72ecf5dc4ee70593251f47c40b0917602f04a25774d930c7ae51bf467bdefc"],"state_sha256":"d2f01e1685cf73250aba8d3eaf9d5c244c1522f699b1dc41b6346fad8f3f7ba9"}