{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:RDGRD6JIM563PUXQMQQ52COJN6","short_pith_number":"pith:RDGRD6JI","canonical_record":{"source":{"id":"2308.05326","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2023-08-10T04:01:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f60af4fb7a1c15c016e340ce641e03a16f259d22a5e57efbfa7ed15eb4c385f8","abstract_canon_sha256":"ebde9c136d9e4692df4cd8330d97b32f11efff0a531d13f3f4d956526555f647"},"schema_version":"1.0"},"canonical_sha256":"88cd11f928677db7d2f06421dd09c96fa8600c39b23a631812020f045d75760f","source":{"kind":"arxiv","id":"2308.05326","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.05326","created_at":"2026-07-05T06:39:58Z"},{"alias_kind":"arxiv_version","alias_value":"2308.05326v1","created_at":"2026-07-05T06:39:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.05326","created_at":"2026-07-05T06:39:58Z"},{"alias_kind":"pith_short_12","alias_value":"RDGRD6JIM563","created_at":"2026-07-05T06:39:58Z"},{"alias_kind":"pith_short_16","alias_value":"RDGRD6JIM563PUXQ","created_at":"2026-07-05T06:39:58Z"},{"alias_kind":"pith_short_8","alias_value":"RDGRD6JI","created_at":"2026-07-05T06:39:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:RDGRD6JIM563PUXQMQQ52COJN6","target":"record","payload":{"canonical_record":{"source":{"id":"2308.05326","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2023-08-10T04:01:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f60af4fb7a1c15c016e340ce641e03a16f259d22a5e57efbfa7ed15eb4c385f8","abstract_canon_sha256":"ebde9c136d9e4692df4cd8330d97b32f11efff0a531d13f3f4d956526555f647"},"schema_version":"1.0"},"canonical_sha256":"88cd11f928677db7d2f06421dd09c96fa8600c39b23a631812020f045d75760f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:39:58.947265Z","signature_b64":"rCrswDFxYYUvh31a7/TZmgnKvxVsvvCwfR/P7i2JwJ1iEVoGHD6yps/DpPzy2jDfbJrsJGRramTMIeyExXemBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88cd11f928677db7d2f06421dd09c96fa8600c39b23a631812020f045d75760f","last_reissued_at":"2026-07-05T06:39:58.946768Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:39:58.946768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.05326","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":"2026-07-05T06:39:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qjKirtZJFiV25aP+MSSQ441mCcP0hEwpGFzcjUxubA9SpDp5/8ip7+FKd9EmEpchETc9waZ2o98y1sN2b0NRAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T17:53:02.165843Z"},"content_sha256":"ef71583aa713cdcd74308cc0ee63e3d8aa4dd2cbbd245b42ca36e4a3cd73b8f7","schema_version":"1.0","event_id":"sha256:ef71583aa713cdcd74308cc0ee63e3d8aa4dd2cbbd245b42ca36e4a3cd73b8f7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:RDGRD6JIM563PUXQMQQ52COJN6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OpenProteinSet: Training data for structural biology at scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.BM","authors_text":"Andrew M. Watkins, Daniel Berenberg, Gustaf Ahdritz, Ian Fisk, Lukas Jarosch, Mohammed AlQuraishi, Nazim Bouatta, Richard Bonneau, Sachin Kadyan, Stephen Ra","submitted_at":"2023-08-10T04:01:04Z","abstract_excerpt":"Multiple sequence alignments (MSAs) of proteins encode rich biological information and have been workhorses in bioinformatic methods for tasks like protein design and protein structure prediction for decades. Recent breakthroughs like AlphaFold2 that use transformers to attend directly over large quantities of raw MSAs have reaffirmed their importance. Generation of MSAs is highly computationally intensive, however, and no datasets comparable to those used to train AlphaFold2 have been made available to the research community, hindering progress in machine learning for proteins. To remedy this"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.05326","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/2308.05326/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":"2026-07-05T06:39:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fMoiomNMnOcV676bIKTY4B9nKn07tO5+ZNnhaDEmcAk4rAfC7QMpbPrWUtIuHrwqxfW9kfdUSOEczkfc8czyDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T17:53:02.166436Z"},"content_sha256":"eace38c73034c9d8f740d22dc913a0fd0548714b5c203fe65495e584d3a9f868","schema_version":"1.0","event_id":"sha256:eace38c73034c9d8f740d22dc913a0fd0548714b5c203fe65495e584d3a9f868"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RDGRD6JIM563PUXQMQQ52COJN6/bundle.json","state_url":"https://pith.science/pith/RDGRD6JIM563PUXQMQQ52COJN6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RDGRD6JIM563PUXQMQQ52COJN6/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":"2026-08-19T17:53:02Z","links":{"resolver":"https://pith.science/pith/RDGRD6JIM563PUXQMQQ52COJN6","bundle":"https://pith.science/pith/RDGRD6JIM563PUXQMQQ52COJN6/bundle.json","state":"https://pith.science/pith/RDGRD6JIM563PUXQMQQ52COJN6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RDGRD6JIM563PUXQMQQ52COJN6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RDGRD6JIM563PUXQMQQ52COJN6","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":"ebde9c136d9e4692df4cd8330d97b32f11efff0a531d13f3f4d956526555f647","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2023-08-10T04:01:04Z","title_canon_sha256":"f60af4fb7a1c15c016e340ce641e03a16f259d22a5e57efbfa7ed15eb4c385f8"},"schema_version":"1.0","source":{"id":"2308.05326","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.05326","created_at":"2026-07-05T06:39:58Z"},{"alias_kind":"arxiv_version","alias_value":"2308.05326v1","created_at":"2026-07-05T06:39:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.05326","created_at":"2026-07-05T06:39:58Z"},{"alias_kind":"pith_short_12","alias_value":"RDGRD6JIM563","created_at":"2026-07-05T06:39:58Z"},{"alias_kind":"pith_short_16","alias_value":"RDGRD6JIM563PUXQ","created_at":"2026-07-05T06:39:58Z"},{"alias_kind":"pith_short_8","alias_value":"RDGRD6JI","created_at":"2026-07-05T06:39:58Z"}],"graph_snapshots":[{"event_id":"sha256:eace38c73034c9d8f740d22dc913a0fd0548714b5c203fe65495e584d3a9f868","target":"graph","created_at":"2026-07-05T06:39:58Z","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/2308.05326/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multiple sequence alignments (MSAs) of proteins encode rich biological information and have been workhorses in bioinformatic methods for tasks like protein design and protein structure prediction for decades. Recent breakthroughs like AlphaFold2 that use transformers to attend directly over large quantities of raw MSAs have reaffirmed their importance. Generation of MSAs is highly computationally intensive, however, and no datasets comparable to those used to train AlphaFold2 have been made available to the research community, hindering progress in machine learning for proteins. To remedy this","authors_text":"Andrew M. Watkins, Daniel Berenberg, Gustaf Ahdritz, Ian Fisk, Lukas Jarosch, Mohammed AlQuraishi, Nazim Bouatta, Richard Bonneau, Sachin Kadyan, Stephen Ra","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2023-08-10T04:01:04Z","title":"OpenProteinSet: Training data for structural biology at scale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.05326","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:ef71583aa713cdcd74308cc0ee63e3d8aa4dd2cbbd245b42ca36e4a3cd73b8f7","target":"record","created_at":"2026-07-05T06:39:58Z","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":"ebde9c136d9e4692df4cd8330d97b32f11efff0a531d13f3f4d956526555f647","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2023-08-10T04:01:04Z","title_canon_sha256":"f60af4fb7a1c15c016e340ce641e03a16f259d22a5e57efbfa7ed15eb4c385f8"},"schema_version":"1.0","source":{"id":"2308.05326","kind":"arxiv","version":1}},"canonical_sha256":"88cd11f928677db7d2f06421dd09c96fa8600c39b23a631812020f045d75760f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88cd11f928677db7d2f06421dd09c96fa8600c39b23a631812020f045d75760f","first_computed_at":"2026-07-05T06:39:58.946768Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:39:58.946768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rCrswDFxYYUvh31a7/TZmgnKvxVsvvCwfR/P7i2JwJ1iEVoGHD6yps/DpPzy2jDfbJrsJGRramTMIeyExXemBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:39:58.947265Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.05326","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef71583aa713cdcd74308cc0ee63e3d8aa4dd2cbbd245b42ca36e4a3cd73b8f7","sha256:eace38c73034c9d8f740d22dc913a0fd0548714b5c203fe65495e584d3a9f868"],"state_sha256":"9f08471262a69cc5c990a1052b805ab9e7f665897172a78051e8d7f22f7fd7d4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kn5IXDM6OQ0U6RMfjDtEGlghdx8sQEiT/oaampyn1XDF0oqKrMw2kLikxlAyYUcvklu1XPE0v9C96PmKks6eAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T17:53:02.173999Z","bundle_sha256":"d4b214f28ec9679a3b0268dceff32f04cd3d85d7578bfa014303db6582d90283"}}