{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:TTNY2ODJEGWATHHS3VDQJ3QXF2","short_pith_number":"pith:TTNY2ODJ","canonical_record":{"source":{"id":"2205.01917","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-04T07:01:14Z","cross_cats_sorted":["cs.LG","cs.MM"],"title_canon_sha256":"979368834a9c1c63162fa1ef78acefae237399dabc836024cbfc08aa7f9b530b","abstract_canon_sha256":"33c64576bd99d3220fac09e2275b95093c5fe2928a27639a33ad2c3ad2b5f166"},"schema_version":"1.0"},"canonical_sha256":"9cdb8d386921ac099cf2dd4704ee172ea655464ac80816bd7db093177d342562","source":{"kind":"arxiv","id":"2205.01917","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.01917","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"arxiv_version","alias_value":"2205.01917v2","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.01917","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"pith_short_12","alias_value":"TTNY2ODJEGWA","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"TTNY2ODJEGWATHHS","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"TTNY2ODJ","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:TTNY2ODJEGWATHHS3VDQJ3QXF2","target":"record","payload":{"canonical_record":{"source":{"id":"2205.01917","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-04T07:01:14Z","cross_cats_sorted":["cs.LG","cs.MM"],"title_canon_sha256":"979368834a9c1c63162fa1ef78acefae237399dabc836024cbfc08aa7f9b530b","abstract_canon_sha256":"33c64576bd99d3220fac09e2275b95093c5fe2928a27639a33ad2c3ad2b5f166"},"schema_version":"1.0"},"canonical_sha256":"9cdb8d386921ac099cf2dd4704ee172ea655464ac80816bd7db093177d342562","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:52.733484Z","signature_b64":"C5Pcho8EEjN+C+/arzBA+CER32b6WpIrC3Ht08S35YbnRDKr9RCu25CXCm0bFp9ES6oGP39X6/UhJ1h4R+PhBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9cdb8d386921ac099cf2dd4704ee172ea655464ac80816bd7db093177d342562","last_reissued_at":"2026-05-17T23:38:52.732937Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:52.732937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.01917","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uaLXG5QLMzQ/06erWycZS7tv0whCpTIte1EpUlVPmbspQNnaY5JB6YSeJHV8rJAfyx503dmDlRwzN2ooHFygBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T19:54:44.179771Z"},"content_sha256":"79cf16091348188eba1f05a6ff62bb41f25814977588002d4489acf5118b0961","schema_version":"1.0","event_id":"sha256:79cf16091348188eba1f05a6ff62bb41f25814977588002d4489acf5118b0961"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:TTNY2ODJEGWATHHS3VDQJ3QXF2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"CoCa jointly trains contrastive and captioning losses in one encoder-decoder to create image-text foundation models that reach new state-of-the-art on ImageNet and multimodal tasks.","cross_cats":["cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Jiahui Yu, Legg Yeung, Mojtaba Seyedhosseini, Vijay Vasudevan, Yonghui Wu, Zirui Wang","submitted_at":"2022-05-04T07:01:14Z","abstract_excerpt":"Exploring large-scale pretrained foundation models is of significant interest in computer vision because these models can be quickly transferred to many downstream tasks. This paper presents Contrastive Captioner (CoCa), a minimalist design to pretrain an image-text encoder-decoder foundation model jointly with contrastive loss and captioning loss, thereby subsuming model capabilities from contrastive approaches like CLIP and generative methods like SimVLM. In contrast to standard encoder-decoder transformers where all decoder layers attend to encoder outputs, CoCa omits cross-attention in the"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"CoCa obtains 86.3% zero-shot top-1 accuracy on ImageNet, 90.6% with a frozen encoder and learned classification head, and new state-of-the-art 91.0% top-1 accuracy on ImageNet with a finetuned encoder, while also leading on Kinetics, MSCOCO, VQA, and other tasks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That omitting cross-attention in the first half of the decoder layers cleanly separates unimodal text representations from multimodal ones without harming overall capacity or optimization stability.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CoCa unifies contrastive and generative pretraining in one image-text model to reach 86.3% zero-shot ImageNet accuracy and new state-of-the-art results on multiple downstream benchmarks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"CoCa jointly trains contrastive and captioning losses in one encoder-decoder to create image-text foundation models that reach new state-of-the-art on ImageNet and multimodal tasks.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"62f230de0b1498c62f4242da007033c4a6474eba7ea984251c75c03889628f78"},"source":{"id":"2205.01917","kind":"arxiv","version":2},"verdict":{"id":"1f439bdc-a6c5-418f-9c37-c73563009d9e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T10:48:13.746831Z","strongest_claim":"CoCa obtains 86.3% zero-shot top-1 accuracy on ImageNet, 90.6% with a frozen encoder and learned classification head, and new state-of-the-art 91.0% top-1 accuracy on ImageNet with a finetuned encoder, while also leading on Kinetics, MSCOCO, VQA, and other tasks.","one_line_summary":"CoCa unifies contrastive and generative pretraining in one image-text model to reach 86.3% zero-shot ImageNet accuracy and new state-of-the-art results on multiple downstream benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That omitting cross-attention in the first half of the decoder layers cleanly separates unimodal text representations from multimodal ones without harming overall capacity or optimization stability.","pith_extraction_headline":"CoCa jointly trains contrastive and captioning losses in one encoder-decoder to create image-text foundation models that reach new state-of-the-art on ImageNet and multimodal tasks."},"references":{"count":80,"sample":[{"doi":"","year":2021,"title":"On the Opportunities and Risks of Foundation Models","work_id":"a18039e9-928d-47c9-a836-32656a71bf71","ref_index":1,"cited_arxiv_id":"2108.07258","is_internal_anchor":true},{"doi":"","year":2018,"title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","work_id":"ed240a10-5b19-406c-baa5-30803f465785","ref_index":2,"cited_arxiv_id":"1810.04805","is_internal_anchor":true},{"doi":"","year":1910,"title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","work_id":"50e3b368-0243-4726-8186-233869802ad1","ref_index":3,"cited_arxiv_id":"1910.10683","is_internal_anchor":true},{"doi":"","year":1901,"title":"Language models are few-shot learners","work_id":"04bc68bc-b7df-4ec1-8599-da037bd4f085","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Thekkath, and Yonghui Wu","work_id":"6192fe03-df78-42e3-88fa-002af7197669","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":80,"snapshot_sha256":"15f6ce8074fb38f0cdc4f7262d52056ff86535f1620fd10356acbefe97446259","internal_anchors":15},"formal_canon":{"evidence_count":2,"snapshot_sha256":"ef2818b7fe9617f272021a3d4e2a136215e8d7bade34bf7398fd12bf60a5724f"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"1f439bdc-a6c5-418f-9c37-c73563009d9e"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zDUkq74Bxr/Nb+PtdFN7m54FL3/kMNrss3jhq2JK6M9mX3blEaivfm1uME383QDdOhtt9yrbTK+Fd+irW6oNBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T19:54:44.180399Z"},"content_sha256":"db520f83a7217f85249df36e37254024bebfa57e072e6d68b7cd0e13a77710c3","schema_version":"1.0","event_id":"sha256:db520f83a7217f85249df36e37254024bebfa57e072e6d68b7cd0e13a77710c3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TTNY2ODJEGWATHHS3VDQJ3QXF2/bundle.json","state_url":"https://pith.science/pith/TTNY2ODJEGWATHHS3VDQJ3QXF2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TTNY2ODJEGWATHHS3VDQJ3QXF2/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":"2026-05-29T19:54:44Z","links":{"resolver":"https://pith.science/pith/TTNY2ODJEGWATHHS3VDQJ3QXF2","bundle":"https://pith.science/pith/TTNY2ODJEGWATHHS3VDQJ3QXF2/bundle.json","state":"https://pith.science/pith/TTNY2ODJEGWATHHS3VDQJ3QXF2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TTNY2ODJEGWATHHS3VDQJ3QXF2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:TTNY2ODJEGWATHHS3VDQJ3QXF2","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":"33c64576bd99d3220fac09e2275b95093c5fe2928a27639a33ad2c3ad2b5f166","cross_cats_sorted":["cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-04T07:01:14Z","title_canon_sha256":"979368834a9c1c63162fa1ef78acefae237399dabc836024cbfc08aa7f9b530b"},"schema_version":"1.0","source":{"id":"2205.01917","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.01917","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"arxiv_version","alias_value":"2205.01917v2","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.01917","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"pith_short_12","alias_value":"TTNY2ODJEGWA","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"TTNY2ODJEGWATHHS","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"TTNY2ODJ","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:db520f83a7217f85249df36e37254024bebfa57e072e6d68b7cd0e13a77710c3","target":"graph","created_at":"2026-05-17T23:38:52Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"CoCa obtains 86.3% zero-shot top-1 accuracy on ImageNet, 90.6% with a frozen encoder and learned classification head, and new state-of-the-art 91.0% top-1 accuracy on ImageNet with a finetuned encoder, while also leading on Kinetics, MSCOCO, VQA, and other tasks."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That omitting cross-attention in the first half of the decoder layers cleanly separates unimodal text representations from multimodal ones without harming overall capacity or optimization stability."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"CoCa unifies contrastive and generative pretraining in one image-text model to reach 86.3% zero-shot ImageNet accuracy and new state-of-the-art results on multiple downstream benchmarks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"CoCa jointly trains contrastive and captioning losses in one encoder-decoder to create image-text foundation models that reach new state-of-the-art on ImageNet and multimodal tasks."}],"snapshot_sha256":"62f230de0b1498c62f4242da007033c4a6474eba7ea984251c75c03889628f78"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"ef2818b7fe9617f272021a3d4e2a136215e8d7bade34bf7398fd12bf60a5724f"},"paper":{"abstract_excerpt":"Exploring large-scale pretrained foundation models is of significant interest in computer vision because these models can be quickly transferred to many downstream tasks. This paper presents Contrastive Captioner (CoCa), a minimalist design to pretrain an image-text encoder-decoder foundation model jointly with contrastive loss and captioning loss, thereby subsuming model capabilities from contrastive approaches like CLIP and generative methods like SimVLM. In contrast to standard encoder-decoder transformers where all decoder layers attend to encoder outputs, CoCa omits cross-attention in the","authors_text":"Jiahui Yu, Legg Yeung, Mojtaba Seyedhosseini, Vijay Vasudevan, Yonghui Wu, Zirui Wang","cross_cats":["cs.LG","cs.MM"],"headline":"CoCa jointly trains contrastive and captioning losses in one encoder-decoder to create image-text foundation models that reach new state-of-the-art on ImageNet and multimodal tasks.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-04T07:01:14Z","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models"},"references":{"count":80,"internal_anchors":15,"resolved_work":80,"sample":[{"cited_arxiv_id":"2108.07258","doi":"","is_internal_anchor":true,"ref_index":1,"title":"On the Opportunities and Risks of Foundation Models","work_id":"a18039e9-928d-47c9-a836-32656a71bf71","year":2021},{"cited_arxiv_id":"1810.04805","doi":"","is_internal_anchor":true,"ref_index":2,"title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","work_id":"ed240a10-5b19-406c-baa5-30803f465785","year":2018},{"cited_arxiv_id":"1910.10683","doi":"","is_internal_anchor":true,"ref_index":3,"title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","work_id":"50e3b368-0243-4726-8186-233869802ad1","year":1910},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Language models are few-shot learners","work_id":"04bc68bc-b7df-4ec1-8599-da037bd4f085","year":1901},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Thekkath, and Yonghui Wu","work_id":"6192fe03-df78-42e3-88fa-002af7197669","year":2022}],"snapshot_sha256":"15f6ce8074fb38f0cdc4f7262d52056ff86535f1620fd10356acbefe97446259"},"source":{"id":"2205.01917","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-15T10:48:13.746831Z","id":"1f439bdc-a6c5-418f-9c37-c73563009d9e","model_set":{"reader":"grok-4.3"},"one_line_summary":"CoCa unifies contrastive and generative pretraining in one image-text model to reach 86.3% zero-shot ImageNet accuracy and new state-of-the-art results on multiple downstream benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"CoCa jointly trains contrastive and captioning losses in one encoder-decoder to create image-text foundation models that reach new state-of-the-art on ImageNet and multimodal tasks.","strongest_claim":"CoCa obtains 86.3% zero-shot top-1 accuracy on ImageNet, 90.6% with a frozen encoder and learned classification head, and new state-of-the-art 91.0% top-1 accuracy on ImageNet with a finetuned encoder, while also leading on Kinetics, MSCOCO, VQA, and other tasks.","weakest_assumption":"That omitting cross-attention in the first half of the decoder layers cleanly separates unimodal text representations from multimodal ones without harming overall capacity or optimization stability."}},"verdict_id":"1f439bdc-a6c5-418f-9c37-c73563009d9e"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:79cf16091348188eba1f05a6ff62bb41f25814977588002d4489acf5118b0961","target":"record","created_at":"2026-05-17T23:38:52Z","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":"33c64576bd99d3220fac09e2275b95093c5fe2928a27639a33ad2c3ad2b5f166","cross_cats_sorted":["cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-04T07:01:14Z","title_canon_sha256":"979368834a9c1c63162fa1ef78acefae237399dabc836024cbfc08aa7f9b530b"},"schema_version":"1.0","source":{"id":"2205.01917","kind":"arxiv","version":2}},"canonical_sha256":"9cdb8d386921ac099cf2dd4704ee172ea655464ac80816bd7db093177d342562","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9cdb8d386921ac099cf2dd4704ee172ea655464ac80816bd7db093177d342562","first_computed_at":"2026-05-17T23:38:52.732937Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:52.732937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C5Pcho8EEjN+C+/arzBA+CER32b6WpIrC3Ht08S35YbnRDKr9RCu25CXCm0bFp9ES6oGP39X6/UhJ1h4R+PhBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:52.733484Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.01917","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:79cf16091348188eba1f05a6ff62bb41f25814977588002d4489acf5118b0961","sha256:db520f83a7217f85249df36e37254024bebfa57e072e6d68b7cd0e13a77710c3"],"state_sha256":"518e87bd880976ac8fbd51547af82f17b582e225acda37da58b509fdf19434ff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P15UlmuhyHxL6qp67A1R1gIPT1Gs4dSHVhvAC0EKMnsgiQRgkAvgaahm1dpvnW3TcPQBO2W8Cc30CwpPzbIvCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T19:54:44.183163Z","bundle_sha256":"dcf2f9142ba1c0d00c3c1afd37efc987e3274875733a59ad5b78811ddb0d7e65"}}