{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JCOZG6DABFQF54NFW4UZISITZP","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":"e9e8c725afa8e8782f9f6a9d851afc9bca57fbdb51b79757311aadaf9f4aebb7","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-27T10:40:23Z","title_canon_sha256":"7d70a6b226c44a700b00cc53cefd1a7cc4be2be8e705736d3e996c12cf48c5c6"},"schema_version":"1.0","source":{"id":"2309.15564","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.15564","created_at":"2026-07-05T06:55:07Z"},{"alias_kind":"arxiv_version","alias_value":"2309.15564v2","created_at":"2026-07-05T06:55:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15564","created_at":"2026-07-05T06:55:07Z"},{"alias_kind":"pith_short_12","alias_value":"JCOZG6DABFQF","created_at":"2026-07-05T06:55:07Z"},{"alias_kind":"pith_short_16","alias_value":"JCOZG6DABFQF54NF","created_at":"2026-07-05T06:55:07Z"},{"alias_kind":"pith_short_8","alias_value":"JCOZG6DA","created_at":"2026-07-05T06:55:07Z"}],"graph_snapshots":[{"event_id":"sha256:f0bc12e28f89ec4b98f3aeb8fc31dc5a145e5da44b62626dbb24624a874cc255","target":"graph","created_at":"2026-07-05T06:55:07Z","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/2309.15564/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, advances in the large-scale pretraining of language and text-to-image models have revolutionized the field of machine learning. Yet, integrating these two modalities into a single, robust model capable of generating seamless multimodal outputs remains a significant challenge. To address this gap, we present the Joint Autoregressive Mixture (JAM) framework, a modular approach that systematically fuses existing text and image generation models. We also introduce a specialized, data-efficient instruction-tuning strategy, tailored for mixed-modal generation tasks. Our final instru","authors_text":"Armen Aghajanyan, Barlas Oguz, Emanuele Aiello, Lili Yu, Yixin Nie","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-27T10:40:23Z","title":"Jointly Training Large Autoregressive Multimodal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.15564","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":"sha256:247a3810f652eb3c9ee2a3e937e4604198fd8fa28b30a662fba5d1a66dd43085","target":"record","created_at":"2026-07-05T06:55:07Z","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":"e9e8c725afa8e8782f9f6a9d851afc9bca57fbdb51b79757311aadaf9f4aebb7","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-27T10:40:23Z","title_canon_sha256":"7d70a6b226c44a700b00cc53cefd1a7cc4be2be8e705736d3e996c12cf48c5c6"},"schema_version":"1.0","source":{"id":"2309.15564","kind":"arxiv","version":2}},"canonical_sha256":"489d93786009605ef1a5b729944913cbf8fdb7a0ccee1918569cd3d73be282a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"489d93786009605ef1a5b729944913cbf8fdb7a0ccee1918569cd3d73be282a8","first_computed_at":"2026-07-05T06:55:07.237945Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:55:07.237945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0BoOoVN26dJy1Ylb+UpyptphFXEO59vKNReGT370WgElQqYMgeDPD/XLiAYUncWa4UdkMWsDEYcVmxvGtdccCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:55:07.238365Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.15564","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:247a3810f652eb3c9ee2a3e937e4604198fd8fa28b30a662fba5d1a66dd43085","sha256:f0bc12e28f89ec4b98f3aeb8fc31dc5a145e5da44b62626dbb24624a874cc255"],"state_sha256":"fb7c5932078868de6ab31cdac5c3289450c385b64c55c0423d3b4dbc6e3a0e0f"}