{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:KMYKXUJ2GHVXZJUJQP7JIRKAXH","short_pith_number":"pith:KMYKXUJ2","canonical_record":{"source":{"id":"2004.03497","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2020-03-08T04:27:16Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"214b46455e91fad9ec9fc8d65da29ca75a7e995a24d0abf1f89a9150d136b432","abstract_canon_sha256":"b2d363e4ef0a5328861a0c5df13b7799510cda78bd7e00d7ac9e355874476e2e"},"schema_version":"1.0"},"canonical_sha256":"5330abd13a31eb7ca68983fe944540b9fd2888fcdc0f23e6766cb124e89f94b7","source":{"kind":"arxiv","id":"2004.03497","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.03497","created_at":"2026-07-05T00:53:26Z"},{"alias_kind":"arxiv_version","alias_value":"2004.03497v1","created_at":"2026-07-05T00:53:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.03497","created_at":"2026-07-05T00:53:26Z"},{"alias_kind":"pith_short_12","alias_value":"KMYKXUJ2GHVX","created_at":"2026-07-05T00:53:26Z"},{"alias_kind":"pith_short_16","alias_value":"KMYKXUJ2GHVXZJUJ","created_at":"2026-07-05T00:53:26Z"},{"alias_kind":"pith_short_8","alias_value":"KMYKXUJ2","created_at":"2026-07-05T00:53:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:KMYKXUJ2GHVXZJUJQP7JIRKAXH","target":"record","payload":{"canonical_record":{"source":{"id":"2004.03497","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2020-03-08T04:27:16Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"214b46455e91fad9ec9fc8d65da29ca75a7e995a24d0abf1f89a9150d136b432","abstract_canon_sha256":"b2d363e4ef0a5328861a0c5df13b7799510cda78bd7e00d7ac9e355874476e2e"},"schema_version":"1.0"},"canonical_sha256":"5330abd13a31eb7ca68983fe944540b9fd2888fcdc0f23e6766cb124e89f94b7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:53:26.781136Z","signature_b64":"fNuNd5i4gDOB81hd64kGpcNdWP3XHvbRlchA78V785K7gH7tEOWmabdIGzvclWzHN7aCkelCeNsfr8kYIb9RAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5330abd13a31eb7ca68983fe944540b9fd2888fcdc0f23e6766cb124e89f94b7","last_reissued_at":"2026-07-05T00:53:26.780665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:53:26.780665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.03497","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":"2026-07-05T00:53:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l35Cn3SZa2If7+T+BFFDBj5rteMdpWaPbA9LNnjWS/xa+rY60d9l4DrEO4MXxjBu4PtwnRex6k63P4z+m6GYCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:48:42.120158Z"},"content_sha256":"793cce9fb5e2591e8586d803fb05c292d63c78e0537e98fa53472efa37368adb","schema_version":"1.0","event_id":"sha256:793cce9fb5e2591e8586d803fb05c292d63c78e0537e98fa53472efa37368adb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:KMYKXUJ2GHVXZJUJQP7JIRKAXH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ProGen: Language Modeling for Protein Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"q-bio.BM","authors_text":"Ali Madani, Bryan McCann, Namrata Anand, Nikhil Naik, Nitish Shirish Keskar, Po-Ssu Huang, Raphael R. Eguchi, Richard Socher","submitted_at":"2020-03-08T04:27:16Z","abstract_excerpt":"Generative modeling for protein engineering is key to solving fundamental problems in synthetic biology, medicine, and material science. We pose protein engineering as an unsupervised sequence generation problem in order to leverage the exponentially growing set of proteins that lack costly, structural annotations. We train a 1.2B-parameter language model, ProGen, on ~280M protein sequences conditioned on taxonomic and keyword tags such as molecular function and cellular component. This provides ProGen with an unprecedented range of evolutionary sequence diversity and allows it to generate wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.03497","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/2004.03497/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":"2026-07-05T00:53:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gaf66hLBVUrIqfU7HoXrcPu9OlYMi45/O9+pBTz1cpI4OXhUkS96AS3zGkch2z3RK/dc8HoCWji/ubM34lTBAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:48:42.120627Z"},"content_sha256":"6bf37a60c1594eeace33821420abcf02a883d0c736e184c2e98c931b06a51fd3","schema_version":"1.0","event_id":"sha256:6bf37a60c1594eeace33821420abcf02a883d0c736e184c2e98c931b06a51fd3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KMYKXUJ2GHVXZJUJQP7JIRKAXH/bundle.json","state_url":"https://pith.science/pith/KMYKXUJ2GHVXZJUJQP7JIRKAXH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KMYKXUJ2GHVXZJUJQP7JIRKAXH/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":"2026-08-05T01:48:42Z","links":{"resolver":"https://pith.science/pith/KMYKXUJ2GHVXZJUJQP7JIRKAXH","bundle":"https://pith.science/pith/KMYKXUJ2GHVXZJUJQP7JIRKAXH/bundle.json","state":"https://pith.science/pith/KMYKXUJ2GHVXZJUJQP7JIRKAXH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KMYKXUJ2GHVXZJUJQP7JIRKAXH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:KMYKXUJ2GHVXZJUJQP7JIRKAXH","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":"b2d363e4ef0a5328861a0c5df13b7799510cda78bd7e00d7ac9e355874476e2e","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2020-03-08T04:27:16Z","title_canon_sha256":"214b46455e91fad9ec9fc8d65da29ca75a7e995a24d0abf1f89a9150d136b432"},"schema_version":"1.0","source":{"id":"2004.03497","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.03497","created_at":"2026-07-05T00:53:26Z"},{"alias_kind":"arxiv_version","alias_value":"2004.03497v1","created_at":"2026-07-05T00:53:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.03497","created_at":"2026-07-05T00:53:26Z"},{"alias_kind":"pith_short_12","alias_value":"KMYKXUJ2GHVX","created_at":"2026-07-05T00:53:26Z"},{"alias_kind":"pith_short_16","alias_value":"KMYKXUJ2GHVXZJUJ","created_at":"2026-07-05T00:53:26Z"},{"alias_kind":"pith_short_8","alias_value":"KMYKXUJ2","created_at":"2026-07-05T00:53:26Z"}],"graph_snapshots":[{"event_id":"sha256:6bf37a60c1594eeace33821420abcf02a883d0c736e184c2e98c931b06a51fd3","target":"graph","created_at":"2026-07-05T00:53:26Z","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/2004.03497/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative modeling for protein engineering is key to solving fundamental problems in synthetic biology, medicine, and material science. We pose protein engineering as an unsupervised sequence generation problem in order to leverage the exponentially growing set of proteins that lack costly, structural annotations. We train a 1.2B-parameter language model, ProGen, on ~280M protein sequences conditioned on taxonomic and keyword tags such as molecular function and cellular component. This provides ProGen with an unprecedented range of evolutionary sequence diversity and allows it to generate wit","authors_text":"Ali Madani, Bryan McCann, Namrata Anand, Nikhil Naik, Nitish Shirish Keskar, Po-Ssu Huang, Raphael R. Eguchi, Richard Socher","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2020-03-08T04:27:16Z","title":"ProGen: Language Modeling for Protein Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.03497","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":"sha256:793cce9fb5e2591e8586d803fb05c292d63c78e0537e98fa53472efa37368adb","target":"record","created_at":"2026-07-05T00:53:26Z","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":"b2d363e4ef0a5328861a0c5df13b7799510cda78bd7e00d7ac9e355874476e2e","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2020-03-08T04:27:16Z","title_canon_sha256":"214b46455e91fad9ec9fc8d65da29ca75a7e995a24d0abf1f89a9150d136b432"},"schema_version":"1.0","source":{"id":"2004.03497","kind":"arxiv","version":1}},"canonical_sha256":"5330abd13a31eb7ca68983fe944540b9fd2888fcdc0f23e6766cb124e89f94b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5330abd13a31eb7ca68983fe944540b9fd2888fcdc0f23e6766cb124e89f94b7","first_computed_at":"2026-07-05T00:53:26.780665Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:53:26.780665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fNuNd5i4gDOB81hd64kGpcNdWP3XHvbRlchA78V785K7gH7tEOWmabdIGzvclWzHN7aCkelCeNsfr8kYIb9RAA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:53:26.781136Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.03497","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:793cce9fb5e2591e8586d803fb05c292d63c78e0537e98fa53472efa37368adb","sha256:6bf37a60c1594eeace33821420abcf02a883d0c736e184c2e98c931b06a51fd3"],"state_sha256":"0d2baa5f475e41afd7d1c5fbbf8b2899f32a5fde6376cb6c5bf3fe2d5e7c80bc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aktqX0NTIHCrLjvsNz5eKrfrQHCcch61gTM6p00970YVOXnxDUXhCz9l6buLrD9THL6a/Mn1CDCIEtcb41uXCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T01:48:42.123741Z","bundle_sha256":"04670e28da7303aca25b6738da2e149745c1033f69aee1d5ee0ad284b5b08078"}}