{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:B6GFDHIM7PPV5HPGUNHWGHOC4E","short_pith_number":"pith:B6GFDHIM","canonical_record":{"source":{"id":"2210.11522","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-20T18:46:31Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c5880cbf8be4e472c1fcd123564e85fed769ea6e7398a55986755044618e1d5a","abstract_canon_sha256":"6bf55e1984bbc8a8fe9b9a3f2c7e1d6cebe2cca5a8d5e7c51d637b9929818cb3"},"schema_version":"1.0"},"canonical_sha256":"0f8c519d0cfbdf5e9de6a34f631dc2e1032089f406919ded733e523fcbf7ef21","source":{"kind":"arxiv","id":"2210.11522","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:B6GFDHIM7PPV5HPGUNHWGHOC4E","target":"record","payload":{"canonical_record":{"source":{"id":"2210.11522","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-20T18:46:31Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c5880cbf8be4e472c1fcd123564e85fed769ea6e7398a55986755044618e1d5a","abstract_canon_sha256":"6bf55e1984bbc8a8fe9b9a3f2c7e1d6cebe2cca5a8d5e7c51d637b9929818cb3"},"schema_version":"1.0"},"canonical_sha256":"0f8c519d0cfbdf5e9de6a34f631dc2e1032089f406919ded733e523fcbf7ef21","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:08:54.460008Z","signature_b64":"GmHmC38CMiiD17v2ncO/31sFpUWMSk75cQOfNVNw4OtuBdHtWOHSvrgyEDHuh9CxUAxfsaUnEleNBToCHXJICA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f8c519d0cfbdf5e9de6a34f631dc2e1032089f406919ded733e523fcbf7ef21","last_reissued_at":"2026-07-05T05:08:54.459608Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:08:54.459608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.11522","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:08:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oXsPCvitpFgCZvSxofxTlCPT0mplXZ+94WC5J/6N8y/eERJzx6QJaMbqdV4W2HN+l7SaZqMXhj1+W1hs3lagCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:40:26.763404Z"},"content_sha256":"0c28f017baebb8bdfec8d59ecb816e328d0b4cd57de4d5dfc0c71a181f7942ff","schema_version":"1.0","event_id":"sha256:0c28f017baebb8bdfec8d59ecb816e328d0b4cd57de4d5dfc0c71a181f7942ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:B6GFDHIM7PPV5HPGUNHWGHOC4E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Composing Ensembles of Pre-trained Models via Iterative Consensus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Antonio Torralba, Igor Mordatch, Joshua B. Tenenbaum, Shuang Li, Yilun Du","submitted_at":"2022-10-20T18:46:31Z","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\" "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.11522","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2210.11522/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:08:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CmGFTS/cLBpl+PWPg19sQb5h0AVZZWwNbsmbvS0SmxKIvbiVR7wA0tE3Q6Pr6QAvhXPdYoWDyhunphc3W6lXAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:40:26.763931Z"},"content_sha256":"0014bb8d5469966860ee0127958f714b76857ba784e37f9740640bb7a9d520d5","schema_version":"1.0","event_id":"sha256:0014bb8d5469966860ee0127958f714b76857ba784e37f9740640bb7a9d520d5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B6GFDHIM7PPV5HPGUNHWGHOC4E/bundle.json","state_url":"https://pith.science/pith/B6GFDHIM7PPV5HPGUNHWGHOC4E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B6GFDHIM7PPV5HPGUNHWGHOC4E/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T19:40:26Z","links":{"resolver":"https://pith.science/pith/B6GFDHIM7PPV5HPGUNHWGHOC4E","bundle":"https://pith.science/pith/B6GFDHIM7PPV5HPGUNHWGHOC4E/bundle.json","state":"https://pith.science/pith/B6GFDHIM7PPV5HPGUNHWGHOC4E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B6GFDHIM7PPV5HPGUNHWGHOC4E/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a6txtQSdejzO9vy1p3KknO76CxRx6U4xGG4aNkmrfZ3RCG0FI3VWVPm85xoP8DUDouJcsTEsLV5kBcIghHxICw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:40:26.771015Z","bundle_sha256":"fe83df44644cb6a8e52fac9f7a98b3add73b204e0654f7b7c2c8c548cfd6643e"}}