{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:B6GFDHIM7PPV5HPGUNHWGHOC4E","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":"6bf55e1984bbc8a8fe9b9a3f2c7e1d6cebe2cca5a8d5e7c51d637b9929818cb3","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-20T18:46:31Z","title_canon_sha256":"c5880cbf8be4e472c1fcd123564e85fed769ea6e7398a55986755044618e1d5a"},"schema_version":"1.0","source":{"id":"2210.11522","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.11522","created_at":"2026-07-05T05:08:54Z"},{"alias_kind":"arxiv_version","alias_value":"2210.11522v1","created_at":"2026-07-05T05:08:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.11522","created_at":"2026-07-05T05:08:54Z"},{"alias_kind":"pith_short_12","alias_value":"B6GFDHIM7PPV","created_at":"2026-07-05T05:08:54Z"},{"alias_kind":"pith_short_16","alias_value":"B6GFDHIM7PPV5HPG","created_at":"2026-07-05T05:08:54Z"},{"alias_kind":"pith_short_8","alias_value":"B6GFDHIM","created_at":"2026-07-05T05:08:54Z"}],"graph_snapshots":[{"event_id":"sha256:0014bb8d5469966860ee0127958f714b76857ba784e37f9740640bb7a9d520d5","target":"graph","created_at":"2026-07-05T05:08:54Z","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/2210.11522/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large pre-trained models exhibit distinct and complementary capabilities dependent on the data they are trained on. Language models such as GPT-3 are capable of textual reasoning but cannot understand visual information, while vision models such as DALL-E can generate photorealistic photos but fail to understand complex language descriptions. In this work, we propose a unified framework for composing ensembles of different pre-trained models -- combining the strengths of each individual model to solve various multimodal problems in a zero-shot manner. We use pre-trained models as \"generators\" ","authors_text":"Antonio Torralba, Igor Mordatch, Joshua B. Tenenbaum, Shuang Li, Yilun Du","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-20T18:46:31Z","title":"Composing Ensembles of Pre-trained Models via Iterative Consensus"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.11522","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":"sha256:0c28f017baebb8bdfec8d59ecb816e328d0b4cd57de4d5dfc0c71a181f7942ff","target":"record","created_at":"2026-07-05T05:08:54Z","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":"6bf55e1984bbc8a8fe9b9a3f2c7e1d6cebe2cca5a8d5e7c51d637b9929818cb3","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-20T18:46:31Z","title_canon_sha256":"c5880cbf8be4e472c1fcd123564e85fed769ea6e7398a55986755044618e1d5a"},"schema_version":"1.0","source":{"id":"2210.11522","kind":"arxiv","version":1}},"canonical_sha256":"0f8c519d0cfbdf5e9de6a34f631dc2e1032089f406919ded733e523fcbf7ef21","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f8c519d0cfbdf5e9de6a34f631dc2e1032089f406919ded733e523fcbf7ef21","first_computed_at":"2026-07-05T05:08:54.459608Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:08:54.459608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GmHmC38CMiiD17v2ncO/31sFpUWMSk75cQOfNVNw4OtuBdHtWOHSvrgyEDHuh9CxUAxfsaUnEleNBToCHXJICA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:08:54.460008Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.11522","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c28f017baebb8bdfec8d59ecb816e328d0b4cd57de4d5dfc0c71a181f7942ff","sha256:0014bb8d5469966860ee0127958f714b76857ba784e37f9740640bb7a9d520d5"],"state_sha256":"ee5fe73a0141ecb13a006c95b3bd35e97ed08626bcf4f80e7b0d3e9fcb1c7e6e"}