{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:GDMC75DKZUSXWOOZL7HH7OUEQ4","short_pith_number":"pith:GDMC75DK","canonical_record":{"source":{"id":"2204.07110","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2022-04-14T16:59:05Z","cross_cats_sorted":["cs.LG","q-bio.QM"],"title_canon_sha256":"cf704563b03b0df60688e11e1834854ddc84640a3fc16e57117189c8ef87492e","abstract_canon_sha256":"3cd2141133ba6c991ead6a756c3fae0b56ba6d46efd27e775da25c9f38779234"},"schema_version":"1.0"},"canonical_sha256":"30d82ff46acd257b39d95fce7fba8487341fa8eb7691f9fa370e583f540dfb23","source":{"kind":"arxiv","id":"2204.07110","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.07110","created_at":"2026-07-05T09:54:22Z"},{"alias_kind":"arxiv_version","alias_value":"2204.07110v2","created_at":"2026-07-05T09:54:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.07110","created_at":"2026-07-05T09:54:22Z"},{"alias_kind":"pith_short_12","alias_value":"GDMC75DKZUSX","created_at":"2026-07-05T09:54:22Z"},{"alias_kind":"pith_short_16","alias_value":"GDMC75DKZUSXWOOZ","created_at":"2026-07-05T09:54:22Z"},{"alias_kind":"pith_short_8","alias_value":"GDMC75DK","created_at":"2026-07-05T09:54:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:GDMC75DKZUSXWOOZL7HH7OUEQ4","target":"record","payload":{"canonical_record":{"source":{"id":"2204.07110","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2022-04-14T16:59:05Z","cross_cats_sorted":["cs.LG","q-bio.QM"],"title_canon_sha256":"cf704563b03b0df60688e11e1834854ddc84640a3fc16e57117189c8ef87492e","abstract_canon_sha256":"3cd2141133ba6c991ead6a756c3fae0b56ba6d46efd27e775da25c9f38779234"},"schema_version":"1.0"},"canonical_sha256":"30d82ff46acd257b39d95fce7fba8487341fa8eb7691f9fa370e583f540dfb23","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:22.173070Z","signature_b64":"tnvvGh4M/JMmufZfz1TLDrsCmEcjvuiD6tNQBqeLvKptDtvqa6zbT4JWAUlVzr5TgWbG9Kh7EMChOhBODbO+Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30d82ff46acd257b39d95fce7fba8487341fa8eb7691f9fa370e583f540dfb23","last_reissued_at":"2026-07-05T09:54:22.172614Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:22.172614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.07110","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":"2026-07-05T09:54:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r/klm0WYYSrFDMCC5RO51QgXwh4YXO5SK/ftdalcTsavmJhkzozM5hqdLMNbWBJvQRMKctbokCKVpGgHcC2hDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:39:29.231508Z"},"content_sha256":"73a8083b5e2032909d8f011404ab4b2aa7035f585e5b73c6ef6228ee12a31630","schema_version":"1.0","event_id":"sha256:73a8083b5e2032909d8f011404ab4b2aa7035f585e5b73c6ef6228ee12a31630"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:GDMC75DKZUSXWOOZL7HH7OUEQ4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generative power of a protein language model trained on multiple sequence alignments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","q-bio.QM"],"primary_cat":"q-bio.BM","authors_text":"Anne-Florence Bitbol, Damiano Sgarbossa, Umberto Lupo","submitted_at":"2022-04-14T16:59:05Z","abstract_excerpt":"Computational models starting from large ensembles of evolutionarily related protein sequences capture a representation of protein families and learn constraints associated to protein structure and function. They thus open the possibility for generating novel sequences belonging to protein families. Protein language models trained on multiple sequence alignments, such as MSA Transformer, are highly attractive candidates to this end. We propose and test an iterative method that directly employs the masked language modeling objective to generate sequences using MSA Transformer. We demonstrate th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.07110","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/2204.07110/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":"2026-07-05T09:54:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jNTCyI+ScB5UiLszcH53Xj1QPEp8mz5XeHBDqyV4Jx+oVzqTSEYYos1lY/YTv3DJckUpxdxIYh0WBUAEpMXACw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:39:29.231881Z"},"content_sha256":"0f2afb664094b9d2f629404747bd6d44ab6d412caf9ee4ab2e6cff512410041d","schema_version":"1.0","event_id":"sha256:0f2afb664094b9d2f629404747bd6d44ab6d412caf9ee4ab2e6cff512410041d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GDMC75DKZUSXWOOZL7HH7OUEQ4/bundle.json","state_url":"https://pith.science/pith/GDMC75DKZUSXWOOZL7HH7OUEQ4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GDMC75DKZUSXWOOZL7HH7OUEQ4/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":"2026-07-07T14:39:29Z","links":{"resolver":"https://pith.science/pith/GDMC75DKZUSXWOOZL7HH7OUEQ4","bundle":"https://pith.science/pith/GDMC75DKZUSXWOOZL7HH7OUEQ4/bundle.json","state":"https://pith.science/pith/GDMC75DKZUSXWOOZL7HH7OUEQ4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GDMC75DKZUSXWOOZL7HH7OUEQ4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GDMC75DKZUSXWOOZL7HH7OUEQ4","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":"3cd2141133ba6c991ead6a756c3fae0b56ba6d46efd27e775da25c9f38779234","cross_cats_sorted":["cs.LG","q-bio.QM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2022-04-14T16:59:05Z","title_canon_sha256":"cf704563b03b0df60688e11e1834854ddc84640a3fc16e57117189c8ef87492e"},"schema_version":"1.0","source":{"id":"2204.07110","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.07110","created_at":"2026-07-05T09:54:22Z"},{"alias_kind":"arxiv_version","alias_value":"2204.07110v2","created_at":"2026-07-05T09:54:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.07110","created_at":"2026-07-05T09:54:22Z"},{"alias_kind":"pith_short_12","alias_value":"GDMC75DKZUSX","created_at":"2026-07-05T09:54:22Z"},{"alias_kind":"pith_short_16","alias_value":"GDMC75DKZUSXWOOZ","created_at":"2026-07-05T09:54:22Z"},{"alias_kind":"pith_short_8","alias_value":"GDMC75DK","created_at":"2026-07-05T09:54:22Z"}],"graph_snapshots":[{"event_id":"sha256:0f2afb664094b9d2f629404747bd6d44ab6d412caf9ee4ab2e6cff512410041d","target":"graph","created_at":"2026-07-05T09:54:22Z","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/2204.07110/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Computational models starting from large ensembles of evolutionarily related protein sequences capture a representation of protein families and learn constraints associated to protein structure and function. They thus open the possibility for generating novel sequences belonging to protein families. Protein language models trained on multiple sequence alignments, such as MSA Transformer, are highly attractive candidates to this end. We propose and test an iterative method that directly employs the masked language modeling objective to generate sequences using MSA Transformer. We demonstrate th","authors_text":"Anne-Florence Bitbol, Damiano Sgarbossa, Umberto Lupo","cross_cats":["cs.LG","q-bio.QM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2022-04-14T16:59:05Z","title":"Generative power of a protein language model trained on multiple sequence alignments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.07110","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":"sha256:73a8083b5e2032909d8f011404ab4b2aa7035f585e5b73c6ef6228ee12a31630","target":"record","created_at":"2026-07-05T09:54:22Z","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":"3cd2141133ba6c991ead6a756c3fae0b56ba6d46efd27e775da25c9f38779234","cross_cats_sorted":["cs.LG","q-bio.QM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2022-04-14T16:59:05Z","title_canon_sha256":"cf704563b03b0df60688e11e1834854ddc84640a3fc16e57117189c8ef87492e"},"schema_version":"1.0","source":{"id":"2204.07110","kind":"arxiv","version":2}},"canonical_sha256":"30d82ff46acd257b39d95fce7fba8487341fa8eb7691f9fa370e583f540dfb23","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30d82ff46acd257b39d95fce7fba8487341fa8eb7691f9fa370e583f540dfb23","first_computed_at":"2026-07-05T09:54:22.172614Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:22.172614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tnvvGh4M/JMmufZfz1TLDrsCmEcjvuiD6tNQBqeLvKptDtvqa6zbT4JWAUlVzr5TgWbG9Kh7EMChOhBODbO+Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:22.173070Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.07110","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73a8083b5e2032909d8f011404ab4b2aa7035f585e5b73c6ef6228ee12a31630","sha256:0f2afb664094b9d2f629404747bd6d44ab6d412caf9ee4ab2e6cff512410041d"],"state_sha256":"479da1dd2b205e9cf7a3e76dd2f281c030d0e0df0cbbd0cc3aaa1b6562eb9e94"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wIxUMYcGLFPTKBO+SbqYcCwOxLCMfT3t3fUcN95eQk/9ZmnYtECNN1Wb0BjLpQnnOgNfx9emsBw1LgxlCtZiBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T14:39:29.233789Z","bundle_sha256":"5284e81b866b44a9dcac0cb265adcede66542fe54f28daead1ec2137afa4004b"}}