{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:R3SLMFZPKZTVQ4TK6BQZEZBOFF","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":"be9a63eda8bcad0dcf2c2f72f96b57100090df26fbb59a301665b42e515e9633","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-28T17:57:06Z","title_canon_sha256":"8b2a2522c0f67d039e0debb2176a8a0c9600c7a117468c61eb092627845bee55"},"schema_version":"1.0","source":{"id":"2312.17172","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.17172","created_at":"2026-07-05T07:28:40Z"},{"alias_kind":"arxiv_version","alias_value":"2312.17172v1","created_at":"2026-07-05T07:28:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.17172","created_at":"2026-07-05T07:28:40Z"},{"alias_kind":"pith_short_12","alias_value":"R3SLMFZPKZTV","created_at":"2026-07-05T07:28:40Z"},{"alias_kind":"pith_short_16","alias_value":"R3SLMFZPKZTVQ4TK","created_at":"2026-07-05T07:28:40Z"},{"alias_kind":"pith_short_8","alias_value":"R3SLMFZP","created_at":"2026-07-05T07:28:40Z"}],"graph_snapshots":[{"event_id":"sha256:0ab4343cbdae3c1d52a9815c86ea5c35410fadb0d116f22fdc9dcfb4045eccda","target":"graph","created_at":"2026-07-05T07:28:40Z","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/2312.17172/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Unified-IO 2, the first autoregressive multimodal model that is capable of understanding and generating image, text, audio, and action. To unify different modalities, we tokenize inputs and outputs -- images, text, audio, action, bounding boxes, etc., into a shared semantic space and then process them with a single encoder-decoder transformer model. Since training with such diverse modalities is challenging, we propose various architectural improvements to stabilize model training. We train our model from scratch on a large multimodal pre-training corpus from diverse sources with a ","authors_text":"Aniruddha Kembhavi, Christopher Clark, Derek Hoiem, Jiasen Lu, Ryan Marten, Sangho Lee, Savya Khosla, Zichen Zhang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-28T17:57:06Z","title":"Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.17172","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:b788b585270c5d7f230daff0b87a82e2b8aa77a1db0c8961c0b2dd79f4b90a46","target":"record","created_at":"2026-07-05T07:28:40Z","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":"be9a63eda8bcad0dcf2c2f72f96b57100090df26fbb59a301665b42e515e9633","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-28T17:57:06Z","title_canon_sha256":"8b2a2522c0f67d039e0debb2176a8a0c9600c7a117468c61eb092627845bee55"},"schema_version":"1.0","source":{"id":"2312.17172","kind":"arxiv","version":1}},"canonical_sha256":"8ee4b6172f566758726af06192642e294709c64affc6b2e29a61a49f98d983c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ee4b6172f566758726af06192642e294709c64affc6b2e29a61a49f98d983c9","first_computed_at":"2026-07-05T07:28:40.405805Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:28:40.405805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g0T39IgxPHp3aAQobCxMkKKkLpme7yMPSop50x8wlUAw81hOD+FewGL4RjHiXycjEdKrTGkGodI9BLpseVdVAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:28:40.406260Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.17172","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b788b585270c5d7f230daff0b87a82e2b8aa77a1db0c8961c0b2dd79f4b90a46","sha256:0ab4343cbdae3c1d52a9815c86ea5c35410fadb0d116f22fdc9dcfb4045eccda"],"state_sha256":"c39357f514bf0876f593c0c0142c3c38f6fe0f2bcdd7fc4d7b8e85d33be66a05"}