{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:57AIJRR2GVEDPOQ7E5Y337OYXL","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":"3b04bd2884ac84a78c70db8e2ad6cb11a8b428cc3488e34d8898f99e07188b56","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-05T21:27:27Z","title_canon_sha256":"be95cb923a4ce82fedd155b33d82b49df313fb9ef6b8c9f5f3e20f5b9721ed8e"},"schema_version":"1.0","source":{"id":"2309.02591","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.02591","created_at":"2026-07-05T06:48:14Z"},{"alias_kind":"arxiv_version","alias_value":"2309.02591v1","created_at":"2026-07-05T06:48:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.02591","created_at":"2026-07-05T06:48:14Z"},{"alias_kind":"pith_short_12","alias_value":"57AIJRR2GVED","created_at":"2026-07-05T06:48:14Z"},{"alias_kind":"pith_short_16","alias_value":"57AIJRR2GVEDPOQ7","created_at":"2026-07-05T06:48:14Z"},{"alias_kind":"pith_short_8","alias_value":"57AIJRR2","created_at":"2026-07-05T06:48:14Z"}],"graph_snapshots":[{"event_id":"sha256:51e3688a3e6cbee9f522e4b5b5544faf414dc2c21be4841e1246bd4eea70ca54","target":"graph","created_at":"2026-07-05T06:48:14Z","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/2309.02591/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present CM3Leon (pronounced \"Chameleon\"), a retrieval-augmented, token-based, decoder-only multi-modal language model capable of generating and infilling both text and images. CM3Leon uses the CM3 multi-modal architecture but additionally shows the extreme benefits of scaling up and tuning on more diverse instruction-style data. It is the first multi-modal model trained with a recipe adapted from text-only language models, including a large-scale retrieval-augmented pre-training stage and a second multi-task supervised fine-tuning (SFT) stage. It is also a general-purpose model that can do ","authors_text":"Adam Polyak, Armen Aghajanyan, Arun Babu, Asli Celikyilmaz, Benjamin Muller, Binh Tang, Bowen Shi, Brian Karrer, Candace Ross, Gargi Ghosh, Hovhannes Tamoyan, Lili Yu, Luke Zettlemoyer, Maryam Fazel-Zarandi, Olga Golovneva, Oron Ashual, Puxin Xu, Ramakanth Pasunuru, Richard James, Russell Howes, Shang-Wen Li, Shelly Sheynin, Susan Zhang, Tianlu Wang, Uriel Singer, Vasu Sharma, Yaniv Taigman","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-05T21:27:27Z","title":"Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.02591","kind":"arxiv","version":1},"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":"sha256:578e5067b6ed9298ba3067725f475021dd7ccb7158b906ce3fed6def97ce59ad","target":"record","created_at":"2026-07-05T06:48:14Z","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":"3b04bd2884ac84a78c70db8e2ad6cb11a8b428cc3488e34d8898f99e07188b56","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-05T21:27:27Z","title_canon_sha256":"be95cb923a4ce82fedd155b33d82b49df313fb9ef6b8c9f5f3e20f5b9721ed8e"},"schema_version":"1.0","source":{"id":"2309.02591","kind":"arxiv","version":1}},"canonical_sha256":"efc084c63a354837ba1f2771bdfdd8badbb1493d7350879bab573d2c74cd33d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"efc084c63a354837ba1f2771bdfdd8badbb1493d7350879bab573d2c74cd33d0","first_computed_at":"2026-07-05T06:48:14.702874Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:48:14.702874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YMrielb5Hc+WjQa9YcjbVMJV8I/xvanOrK7pf9RtQCBQb8MEhBm/TtKTPgzYe8LpzWc4sF2EAcGS1MydVF7DBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:48:14.703272Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.02591","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:578e5067b6ed9298ba3067725f475021dd7ccb7158b906ce3fed6def97ce59ad","sha256:51e3688a3e6cbee9f522e4b5b5544faf414dc2c21be4841e1246bd4eea70ca54"],"state_sha256":"b2d752035ae1b153db43651ab0b417e2335eaf3b7663365ca42f1cde4d3ccefd"}