{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:OONDHMZR5BK7RISMQRAIR7JDQZ","short_pith_number":"pith:OONDHMZR","canonical_record":{"source":{"id":"2205.05789","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2022-05-11T22:06:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8306ab7aeb6bbc10e437765a0bdc25945716b23ca8a9502852c2095512765118","abstract_canon_sha256":"9d0fd88418876beb73220e137bb796bed61d58e36432b166ec0d98b1fcaa3460"},"schema_version":"1.0"},"canonical_sha256":"739a33b331e855f8a24c844088fd23867fa7e1111d99c52403ed23f556ba8556","source":{"kind":"arxiv","id":"2205.05789","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.05789","created_at":"2026-07-05T04:40:27Z"},{"alias_kind":"arxiv_version","alias_value":"2205.05789v2","created_at":"2026-07-05T04:40:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.05789","created_at":"2026-07-05T04:40:27Z"},{"alias_kind":"pith_short_12","alias_value":"OONDHMZR5BK7","created_at":"2026-07-05T04:40:27Z"},{"alias_kind":"pith_short_16","alias_value":"OONDHMZR5BK7RISM","created_at":"2026-07-05T04:40:27Z"},{"alias_kind":"pith_short_8","alias_value":"OONDHMZR","created_at":"2026-07-05T04:40:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:OONDHMZR5BK7RISMQRAIR7JDQZ","target":"record","payload":{"canonical_record":{"source":{"id":"2205.05789","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2022-05-11T22:06:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8306ab7aeb6bbc10e437765a0bdc25945716b23ca8a9502852c2095512765118","abstract_canon_sha256":"9d0fd88418876beb73220e137bb796bed61d58e36432b166ec0d98b1fcaa3460"},"schema_version":"1.0"},"canonical_sha256":"739a33b331e855f8a24c844088fd23867fa7e1111d99c52403ed23f556ba8556","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:40:27.277623Z","signature_b64":"1GxNxDECZO3/OJJbtYY3FBtRMvLcLi4AApdhgJ7mMau3yiQQ70Rg9DSno7lcsr8kAvjgq7Mtxz0/6uf2SNNhCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"739a33b331e855f8a24c844088fd23867fa7e1111d99c52403ed23f556ba8556","last_reissued_at":"2026-07-05T04:40:27.277090Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:40:27.277090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.05789","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":"2026-07-05T04:40:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kHbOl/Rw1+M3z6t7jVf5Ds+49j7jqhH6/3HGCUXR4Go/U+lwuvUIbnYaOEgZ+E0xgUtKcLqixSw4HXfGuwGcAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T22:58:53.663324Z"},"content_sha256":"4db55aa5d67ba309edf49b6a9bd788547ffab86004d2e755b9ca57a7ba323e42","schema_version":"1.0","event_id":"sha256:4db55aa5d67ba309edf49b6a9bd788547ffab86004d2e755b9ca57a7ba323e42"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:OONDHMZR5BK7RISMQRAIR7JDQZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RITA: a Study on Scaling Up Generative Protein Sequence Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.QM","authors_text":"Daniel Hesslow, Debora Marks, Iacopo Poli, Niccol\\'o Zanichelli, Pascal Notin","submitted_at":"2022-05-11T22:06:03Z","abstract_excerpt":"In this work we introduce RITA: a suite of autoregressive generative models for protein sequences, with up to 1.2 billion parameters, trained on over 280 million protein sequences belonging to the UniRef-100 database. Such generative models hold the promise of greatly accelerating protein design. We conduct the first systematic study of how capabilities evolve with model size for autoregressive transformers in the protein domain: we evaluate RITA models in next amino acid prediction, zero-shot fitness, and enzyme function prediction, showing benefits from increased scale. We release the RITA m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.05789","kind":"arxiv","version":2},"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/2205.05789/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":"2026-07-05T04:40:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pURZ0uW5KT+HqKrgUOzSsWGIldHOd78KySNIAFiRSeDpI1oMctvn3NY9ACLqMJwrNHrnYirRX4JHyTpigrL2Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T22:58:53.663699Z"},"content_sha256":"cf3bedf00547855869de3e353ec53b53fbf536a3b74b470871509ec1f122ffdc","schema_version":"1.0","event_id":"sha256:cf3bedf00547855869de3e353ec53b53fbf536a3b74b470871509ec1f122ffdc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OONDHMZR5BK7RISMQRAIR7JDQZ/bundle.json","state_url":"https://pith.science/pith/OONDHMZR5BK7RISMQRAIR7JDQZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OONDHMZR5BK7RISMQRAIR7JDQZ/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":"2026-07-25T22:58:53Z","links":{"resolver":"https://pith.science/pith/OONDHMZR5BK7RISMQRAIR7JDQZ","bundle":"https://pith.science/pith/OONDHMZR5BK7RISMQRAIR7JDQZ/bundle.json","state":"https://pith.science/pith/OONDHMZR5BK7RISMQRAIR7JDQZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OONDHMZR5BK7RISMQRAIR7JDQZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:OONDHMZR5BK7RISMQRAIR7JDQZ","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":"9d0fd88418876beb73220e137bb796bed61d58e36432b166ec0d98b1fcaa3460","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2022-05-11T22:06:03Z","title_canon_sha256":"8306ab7aeb6bbc10e437765a0bdc25945716b23ca8a9502852c2095512765118"},"schema_version":"1.0","source":{"id":"2205.05789","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.05789","created_at":"2026-07-05T04:40:27Z"},{"alias_kind":"arxiv_version","alias_value":"2205.05789v2","created_at":"2026-07-05T04:40:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.05789","created_at":"2026-07-05T04:40:27Z"},{"alias_kind":"pith_short_12","alias_value":"OONDHMZR5BK7","created_at":"2026-07-05T04:40:27Z"},{"alias_kind":"pith_short_16","alias_value":"OONDHMZR5BK7RISM","created_at":"2026-07-05T04:40:27Z"},{"alias_kind":"pith_short_8","alias_value":"OONDHMZR","created_at":"2026-07-05T04:40:27Z"}],"graph_snapshots":[{"event_id":"sha256:cf3bedf00547855869de3e353ec53b53fbf536a3b74b470871509ec1f122ffdc","target":"graph","created_at":"2026-07-05T04:40:27Z","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/2205.05789/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work we introduce RITA: a suite of autoregressive generative models for protein sequences, with up to 1.2 billion parameters, trained on over 280 million protein sequences belonging to the UniRef-100 database. Such generative models hold the promise of greatly accelerating protein design. We conduct the first systematic study of how capabilities evolve with model size for autoregressive transformers in the protein domain: we evaluate RITA models in next amino acid prediction, zero-shot fitness, and enzyme function prediction, showing benefits from increased scale. We release the RITA m","authors_text":"Daniel Hesslow, Debora Marks, Iacopo Poli, Niccol\\'o Zanichelli, Pascal Notin","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2022-05-11T22:06:03Z","title":"RITA: a Study on Scaling Up Generative Protein Sequence Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.05789","kind":"arxiv","version":2},"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":"sha256:4db55aa5d67ba309edf49b6a9bd788547ffab86004d2e755b9ca57a7ba323e42","target":"record","created_at":"2026-07-05T04:40:27Z","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":"9d0fd88418876beb73220e137bb796bed61d58e36432b166ec0d98b1fcaa3460","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2022-05-11T22:06:03Z","title_canon_sha256":"8306ab7aeb6bbc10e437765a0bdc25945716b23ca8a9502852c2095512765118"},"schema_version":"1.0","source":{"id":"2205.05789","kind":"arxiv","version":2}},"canonical_sha256":"739a33b331e855f8a24c844088fd23867fa7e1111d99c52403ed23f556ba8556","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"739a33b331e855f8a24c844088fd23867fa7e1111d99c52403ed23f556ba8556","first_computed_at":"2026-07-05T04:40:27.277090Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:40:27.277090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1GxNxDECZO3/OJJbtYY3FBtRMvLcLi4AApdhgJ7mMau3yiQQ70Rg9DSno7lcsr8kAvjgq7Mtxz0/6uf2SNNhCw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:40:27.277623Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.05789","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4db55aa5d67ba309edf49b6a9bd788547ffab86004d2e755b9ca57a7ba323e42","sha256:cf3bedf00547855869de3e353ec53b53fbf536a3b74b470871509ec1f122ffdc"],"state_sha256":"449d394f7d68036e91020c066548bf0f8a333b9fb4fe2588d7c7dad54281b275"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OBESuqAc/zZxP71t0lvN2vyn5bEiopzew15pghAVuw+1BD2srpaxqCBwsT14vCY2kdhY14IxcPyXsT2QVDqPCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-25T22:58:53.666131Z","bundle_sha256":"dde5398b0307075c34fff3bf730c7bd7b2bcf09ac95d399844863fd431ed0c28"}}