{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:EM3FJITNE6ISPGXOZDNQ3XXNJG","short_pith_number":"pith:EM3FJITN","canonical_record":{"source":{"id":"2102.12092","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-24T06:42:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d8fed5258329bcb50974f59ef498b8b49dee66857162c9241f9695116f4ebbec","abstract_canon_sha256":"7b1b5ca549ba2968b6bbe3695aa883be7800890084b682e1f3e752983ebc93ab"},"schema_version":"1.0"},"canonical_sha256":"233654a26d2791279aeec8db0ddeed49ba362c217843ba32fb756556f27fc44f","source":{"kind":"arxiv","id":"2102.12092","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.12092","created_at":"2026-05-18T04:19:54Z"},{"alias_kind":"arxiv_version","alias_value":"2102.12092v2","created_at":"2026-05-18T04:19:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.12092","created_at":"2026-05-18T04:19:54Z"},{"alias_kind":"pith_short_12","alias_value":"EM3FJITNE6IS","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"EM3FJITNE6ISPGXO","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"EM3FJITN","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:EM3FJITNE6ISPGXOZDNQ3XXNJG","target":"record","payload":{"canonical_record":{"source":{"id":"2102.12092","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-24T06:42:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d8fed5258329bcb50974f59ef498b8b49dee66857162c9241f9695116f4ebbec","abstract_canon_sha256":"7b1b5ca549ba2968b6bbe3695aa883be7800890084b682e1f3e752983ebc93ab"},"schema_version":"1.0"},"canonical_sha256":"233654a26d2791279aeec8db0ddeed49ba362c217843ba32fb756556f27fc44f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:19:54.695463Z","signature_b64":"eHsVQDwY2XUVi9674KmGzDEz78GtLX14VYyCPLV6tvr3pFWrBx0mCeJOKQW+d42UKP4gKEKuLI9eOpivFBF2Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"233654a26d2791279aeec8db0ddeed49ba362c217843ba32fb756556f27fc44f","last_reissued_at":"2026-05-18T04:19:54.694687Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:19:54.694687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.12092","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":"2026-05-18T04:19:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"diACi0f1Z7DlFbgHxknLkQzC4Yd4pKi7A+qBCJTBCJJI/Mb6GLBG32NS+UhHgWHxAAzM0XTbNZBS+PhJWqZrCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T07:31:14.460479Z"},"content_sha256":"3ff1c0091eabf679dcfd9e5dbb7ac6b4413b71d72bb5a82efd042d3fd377f791","schema_version":"1.0","event_id":"sha256:3ff1c0091eabf679dcfd9e5dbb7ac6b4413b71d72bb5a82efd042d3fd377f791"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:EM3FJITNE6ISPGXOZDNQ3XXNJG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Zero-Shot Text-to-Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A transformer that models text and image tokens as one autoregressive stream achieves competitive zero-shot text-to-image generation at sufficient scale.","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aditya Ramesh, Alec Radford, Chelsea Voss, Gabriel Goh, Ilya Sutskever, Mark Chen, Mikhail Pavlov, Scott Gray","submitted_at":"2021-02-24T06:42:31Z","abstract_excerpt":"Text-to-image generation has traditionally focused on finding better modeling assumptions for training on a fixed dataset. These assumptions might involve complex architectures, auxiliary losses, or side information such as object part labels or segmentation masks supplied during training. We describe a simple approach for this task based on a transformer that autoregressively models the text and image tokens as a single stream of data. With sufficient data and scale, our approach is competitive with previous domain-specific models when evaluated in a zero-shot fashion."},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"With sufficient data and scale, our approach is competitive with previous domain-specific models when evaluated in a zero-shot fashion.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That simply increasing model size and data volume will continue to close the gap to specialized models without introducing new failure modes or requiring additional inductive biases.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A transformer autoregressively models text and image tokens as one stream and produces competitive zero-shot text-to-image results at sufficient scale.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A transformer that models text and image tokens as one autoregressive stream achieves competitive zero-shot text-to-image generation at sufficient scale.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"13db172eac172da28dfbbecbfd58e7c97ef70b1dabb61fe7a9acc90130fd22bc"},"source":{"id":"2102.12092","kind":"arxiv","version":2},"verdict":{"id":"d06740f6-2e1e-4b26-9524-ef4eedfd647c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T22:22:00.876735Z","strongest_claim":"With sufficient data and scale, our approach is competitive with previous domain-specific models when evaluated in a zero-shot fashion.","one_line_summary":"A transformer autoregressively models text and image tokens as one stream and produces competitive zero-shot text-to-image results at sufficient scale.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That simply increasing model size and data volume will continue to close the gap to specialized models without introducing new failure modes or requiring additional inductive biases.","pith_extraction_headline":"A transformer that models text and image tokens as one autoregressive stream achieves competitive zero-shot text-to-image generation at sufficient scale."},"references":{"count":23,"sample":[{"doi":"","year":2015,"title":"Bowman et al","work_id":"52301570-311d-400c-a35e-e91c2dafc161","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Using a linear annealing schedule for this typically led to divergence","work_id":"a760669a-0fff-48d1-8242-87dac551d654","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"row, column, row, row","work_id":"0336e6b0-451d-47dc-8d97-1a46d4107b72","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Our model uses 128 gradient scales, one for each of its resblocks","work_id":"acbee4e8-41fd-48e1-b387-4b6685b9e6e2","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"In particular, store all gains, biases, embeddings, and unembeddings in 32-bit precision, with 32-bit gradients (including for remote communication) and 32-bit Adam moments","work_id":"2cbd3bc9-f9b0-4459-902d-4ad616b9d452","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":23,"snapshot_sha256":"20e3e9821b8d8cdb6d7d5423026327248332c552ac100fa4abd9e4fd6b4d7666","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"d12df4dfee20ea1cf31da99d9d8fe14ff7462fb2fce8615d7054987eb1475f96"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"d06740f6-2e1e-4b26-9524-ef4eedfd647c"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T04:19:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uZoSEbecf45BN0E/2urzo4HEKFv5mT+fZO2HUjQadFOeG7W42PZ2stKvk+UIZNPCDq55TawF7pv1W50vr2pSDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T07:31:14.461218Z"},"content_sha256":"2effacf3996bfabce7a5abcf791bee94d04f6165f647dc0e2566bc19ce150900","schema_version":"1.0","event_id":"sha256:2effacf3996bfabce7a5abcf791bee94d04f6165f647dc0e2566bc19ce150900"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EM3FJITNE6ISPGXOZDNQ3XXNJG/bundle.json","state_url":"https://pith.science/pith/EM3FJITNE6ISPGXOZDNQ3XXNJG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EM3FJITNE6ISPGXOZDNQ3XXNJG/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":"2026-08-14T07:31:14Z","links":{"resolver":"https://pith.science/pith/EM3FJITNE6ISPGXOZDNQ3XXNJG","bundle":"https://pith.science/pith/EM3FJITNE6ISPGXOZDNQ3XXNJG/bundle.json","state":"https://pith.science/pith/EM3FJITNE6ISPGXOZDNQ3XXNJG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EM3FJITNE6ISPGXOZDNQ3XXNJG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:EM3FJITNE6ISPGXOZDNQ3XXNJG","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":"7b1b5ca549ba2968b6bbe3695aa883be7800890084b682e1f3e752983ebc93ab","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-24T06:42:31Z","title_canon_sha256":"d8fed5258329bcb50974f59ef498b8b49dee66857162c9241f9695116f4ebbec"},"schema_version":"1.0","source":{"id":"2102.12092","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.12092","created_at":"2026-05-18T04:19:54Z"},{"alias_kind":"arxiv_version","alias_value":"2102.12092v2","created_at":"2026-05-18T04:19:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.12092","created_at":"2026-05-18T04:19:54Z"},{"alias_kind":"pith_short_12","alias_value":"EM3FJITNE6IS","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"EM3FJITNE6ISPGXO","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"EM3FJITN","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:2effacf3996bfabce7a5abcf791bee94d04f6165f647dc0e2566bc19ce150900","target":"graph","created_at":"2026-05-18T04:19:54Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"With sufficient data and scale, our approach is competitive with previous domain-specific models when evaluated in a zero-shot fashion."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That simply increasing model size and data volume will continue to close the gap to specialized models without introducing new failure modes or requiring additional inductive biases."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A transformer autoregressively models text and image tokens as one stream and produces competitive zero-shot text-to-image results at sufficient scale."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A transformer that models text and image tokens as one autoregressive stream achieves competitive zero-shot text-to-image generation at sufficient scale."}],"snapshot_sha256":"13db172eac172da28dfbbecbfd58e7c97ef70b1dabb61fe7a9acc90130fd22bc"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"d12df4dfee20ea1cf31da99d9d8fe14ff7462fb2fce8615d7054987eb1475f96"},"paper":{"abstract_excerpt":"Text-to-image generation has traditionally focused on finding better modeling assumptions for training on a fixed dataset. These assumptions might involve complex architectures, auxiliary losses, or side information such as object part labels or segmentation masks supplied during training. We describe a simple approach for this task based on a transformer that autoregressively models the text and image tokens as a single stream of data. With sufficient data and scale, our approach is competitive with previous domain-specific models when evaluated in a zero-shot fashion.","authors_text":"Aditya Ramesh, Alec Radford, Chelsea Voss, Gabriel Goh, Ilya Sutskever, Mark Chen, Mikhail Pavlov, Scott Gray","cross_cats":["cs.LG"],"headline":"A transformer that models text and image tokens as one autoregressive stream achieves competitive zero-shot text-to-image generation at sufficient scale.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-24T06:42:31Z","title":"Zero-Shot Text-to-Image Generation"},"references":{"count":23,"internal_anchors":0,"resolved_work":23,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Bowman et al","work_id":"52301570-311d-400c-a35e-e91c2dafc161","year":2015},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Using a linear annealing schedule for this typically led to divergence","work_id":"a760669a-0fff-48d1-8242-87dac551d654","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"row, column, row, row","work_id":"0336e6b0-451d-47dc-8d97-1a46d4107b72","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Our model uses 128 gradient scales, one for each of its resblocks","work_id":"acbee4e8-41fd-48e1-b387-4b6685b9e6e2","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"In particular, store all gains, biases, embeddings, and unembeddings in 32-bit precision, with 32-bit gradients (including for remote communication) and 32-bit Adam moments","work_id":"2cbd3bc9-f9b0-4459-902d-4ad616b9d452","year":null}],"snapshot_sha256":"20e3e9821b8d8cdb6d7d5423026327248332c552ac100fa4abd9e4fd6b4d7666"},"source":{"id":"2102.12092","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-13T22:22:00.876735Z","id":"d06740f6-2e1e-4b26-9524-ef4eedfd647c","model_set":{"reader":"grok-4.3"},"one_line_summary":"A transformer autoregressively models text and image tokens as one stream and produces competitive zero-shot text-to-image results at sufficient scale.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A transformer that models text and image tokens as one autoregressive stream achieves competitive zero-shot text-to-image generation at sufficient scale.","strongest_claim":"With sufficient data and scale, our approach is competitive with previous domain-specific models when evaluated in a zero-shot fashion.","weakest_assumption":"That simply increasing model size and data volume will continue to close the gap to specialized models without introducing new failure modes or requiring additional inductive biases."}},"verdict_id":"d06740f6-2e1e-4b26-9524-ef4eedfd647c"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3ff1c0091eabf679dcfd9e5dbb7ac6b4413b71d72bb5a82efd042d3fd377f791","target":"record","created_at":"2026-05-18T04:19:54Z","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":"7b1b5ca549ba2968b6bbe3695aa883be7800890084b682e1f3e752983ebc93ab","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-24T06:42:31Z","title_canon_sha256":"d8fed5258329bcb50974f59ef498b8b49dee66857162c9241f9695116f4ebbec"},"schema_version":"1.0","source":{"id":"2102.12092","kind":"arxiv","version":2}},"canonical_sha256":"233654a26d2791279aeec8db0ddeed49ba362c217843ba32fb756556f27fc44f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"233654a26d2791279aeec8db0ddeed49ba362c217843ba32fb756556f27fc44f","first_computed_at":"2026-05-18T04:19:54.694687Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:19:54.694687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eHsVQDwY2XUVi9674KmGzDEz78GtLX14VYyCPLV6tvr3pFWrBx0mCeJOKQW+d42UKP4gKEKuLI9eOpivFBF2Dw==","signature_status":"signed_v1","signed_at":"2026-05-18T04:19:54.695463Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.12092","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ff1c0091eabf679dcfd9e5dbb7ac6b4413b71d72bb5a82efd042d3fd377f791","sha256:2effacf3996bfabce7a5abcf791bee94d04f6165f647dc0e2566bc19ce150900"],"state_sha256":"91fdeac7143ee14695353a3fd294a9ac56bcd7081fd0f828c870329fd883a08d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wpsGa7lOX4QpkqIyu6c71d7U9HwwrL6B8tmAwu8jzIFomNxXqrULPS+3lFHJ5tLd7HNBY9hDY00OdboTHGuGAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T07:31:14.466999Z","bundle_sha256":"8a79d5e3323097069ea85d81064359858dc5ec17c4f6e32ad281bf87efb5917b"}}