{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:DOPE75Z7VACDO2YCEBNEW2WDRB","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":"9a26ada6ab4f9b5ff7b9521192a1fb38f3375b2e8afcd781fb59ce5ff8c35768","cross_cats_sorted":["q-bio.QM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-27T17:55:02Z","title_canon_sha256":"343359ac1a916ed2ce35ac7479604ed2dc7ab75ffa8e2dd269c0a7c2dc57917f"},"schema_version":"1.0","source":{"id":"2206.13517","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.13517","created_at":"2026-07-05T04:35:51Z"},{"alias_kind":"arxiv_version","alias_value":"2206.13517v1","created_at":"2026-07-05T04:35:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.13517","created_at":"2026-07-05T04:35:51Z"},{"alias_kind":"pith_short_12","alias_value":"DOPE75Z7VACD","created_at":"2026-07-05T04:35:51Z"},{"alias_kind":"pith_short_16","alias_value":"DOPE75Z7VACDO2YC","created_at":"2026-07-05T04:35:51Z"},{"alias_kind":"pith_short_8","alias_value":"DOPE75Z7","created_at":"2026-07-05T04:35:51Z"}],"graph_snapshots":[{"event_id":"sha256:6c37beaf5626a6fc7d5d36a4fc4744be17fb49609297b61e90cf4c2a979df68b","target":"graph","created_at":"2026-07-05T04:35:51Z","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/2206.13517/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Attention-based models trained on protein sequences have demonstrated incredible success at classification and generation tasks relevant for artificial intelligence-driven protein design. However, we lack a sufficient understanding of how very large-scale models and data play a role in effective protein model development. We introduce a suite of protein language models, named ProGen2, that are scaled up to 6.4B parameters and trained on different sequence datasets drawn from over a billion proteins from genomic, metagenomic, and immune repertoire databases. ProGen2 models show state-of-the-art","authors_text":"Ali Madani, Eli N. Weinstein, Erik Nijkamp, Jeffrey Ruffolo, Nikhil Naik","cross_cats":["q-bio.QM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-27T17:55:02Z","title":"ProGen2: Exploring the Boundaries of Protein Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.13517","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:d6c8e67c2793be1a4150acdba7ca1c295b9eef22d007d26812681dcf9397a0a8","target":"record","created_at":"2026-07-05T04:35:51Z","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":"9a26ada6ab4f9b5ff7b9521192a1fb38f3375b2e8afcd781fb59ce5ff8c35768","cross_cats_sorted":["q-bio.QM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-27T17:55:02Z","title_canon_sha256":"343359ac1a916ed2ce35ac7479604ed2dc7ab75ffa8e2dd269c0a7c2dc57917f"},"schema_version":"1.0","source":{"id":"2206.13517","kind":"arxiv","version":1}},"canonical_sha256":"1b9e4ff73fa804376b02205a4b6ac3884c09b2bb94649c3785b0bf4a0e99439d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b9e4ff73fa804376b02205a4b6ac3884c09b2bb94649c3785b0bf4a0e99439d","first_computed_at":"2026-07-05T04:35:51.790294Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:35:51.790294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YNv2wvPWTcaJhBj1IuXTbnqsAfHZ7c9WQFHKX43re9Jccdofsi7RTn6uWP0mGU90GW2fRCwuQMoOKGJBz/S+Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:35:51.790755Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.13517","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6c8e67c2793be1a4150acdba7ca1c295b9eef22d007d26812681dcf9397a0a8","sha256:6c37beaf5626a6fc7d5d36a4fc4744be17fb49609297b61e90cf4c2a979df68b"],"state_sha256":"5a19309af938bfc3ecb882f573f7a16bc630bb5373860244d7b8ad310c099473"}