{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:AGUKU2RQWRQLQOTNLY3KTZPHWV","short_pith_number":"pith:AGUKU2RQ","canonical_record":{"source":{"id":"2108.07435","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-17T04:13:11Z","cross_cats_sorted":["cs.CL","q-bio.BM"],"title_canon_sha256":"e16e75a48f9adcffcd3c4d0db8cc00676beb20d508c5608f507e682d551c4a9b","abstract_canon_sha256":"daa15f63525a7e200b69b080690858cd96a82bae61f1a2cc5554189a7f5f751b"},"schema_version":"1.0"},"canonical_sha256":"01a8aa6a30b460b83a6d5e36a9e5e7b5468c05fbcb3afd78039ab5f65f86f1e0","source":{"kind":"arxiv","id":"2108.07435","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.07435","created_at":"2026-07-05T03:38:28Z"},{"alias_kind":"arxiv_version","alias_value":"2108.07435v2","created_at":"2026-07-05T03:38:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.07435","created_at":"2026-07-05T03:38:28Z"},{"alias_kind":"pith_short_12","alias_value":"AGUKU2RQWRQL","created_at":"2026-07-05T03:38:28Z"},{"alias_kind":"pith_short_16","alias_value":"AGUKU2RQWRQLQOTN","created_at":"2026-07-05T03:38:28Z"},{"alias_kind":"pith_short_8","alias_value":"AGUKU2RQ","created_at":"2026-07-05T03:38:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:AGUKU2RQWRQLQOTNLY3KTZPHWV","target":"record","payload":{"canonical_record":{"source":{"id":"2108.07435","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-17T04:13:11Z","cross_cats_sorted":["cs.CL","q-bio.BM"],"title_canon_sha256":"e16e75a48f9adcffcd3c4d0db8cc00676beb20d508c5608f507e682d551c4a9b","abstract_canon_sha256":"daa15f63525a7e200b69b080690858cd96a82bae61f1a2cc5554189a7f5f751b"},"schema_version":"1.0"},"canonical_sha256":"01a8aa6a30b460b83a6d5e36a9e5e7b5468c05fbcb3afd78039ab5f65f86f1e0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:38:28.170710Z","signature_b64":"VVZ/W17fdy1RRYJAQ/LnKSQK6U8j+v++59HwNy4NUlGttT41Y6VzBjzUos9jnZhzidPkuZc1j2VcQO24YV1zAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01a8aa6a30b460b83a6d5e36a9e5e7b5468c05fbcb3afd78039ab5f65f86f1e0","last_reissued_at":"2026-07-05T03:38:28.170230Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:38:28.170230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.07435","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":"2026-07-05T03:38:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LPThioXcjfM0u1VWCHINPMUyhOG+gXzIUyA1XUt/Z0VHMDf9h/1A4KsyCInzTKsSk/93CtjI2mM8ghbdbYbvCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:12:37.614528Z"},"content_sha256":"b41880f56effa565031c19d08f7942e99080ca0f005210ecb04838c9d753f325","schema_version":"1.0","event_id":"sha256:b41880f56effa565031c19d08f7942e99080ca0f005210ecb04838c9d753f325"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:AGUKU2RQWRQLQOTNLY3KTZPHWV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Modeling Protein Using Large-scale Pretrain Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Chang-Yu Hsieh, Jie Tang, Jiezhong Qiu, Yijia Xiao, Ziang Li","submitted_at":"2021-08-17T04:13:11Z","abstract_excerpt":"Protein is linked to almost every life process. Therefore, analyzing the biological structure and property of protein sequences is critical to the exploration of life, as well as disease detection and drug discovery. Traditional protein analysis methods tend to be labor-intensive and time-consuming. The emergence of deep learning models makes modeling data patterns in large quantities of data possible. Interdisciplinary researchers have begun to leverage deep learning methods to model large biological datasets, e.g. using long short-term memory and convolutional neural network for protein sequ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.07435","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/2108.07435/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":"2026-07-05T03:38:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KIQeUo0BGjfEjT6j0kQJ8nkhp2CvUkQmmO2+hwJuz9OKZh9Oe1C4KRB6iI5ujh2KV5oC3bNOmu0Mh5an2Wt6BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:12:37.615465Z"},"content_sha256":"6d37d9b456f87c2dbd82079a4e4e81807c8901d88241170ba690bce35d8eb723","schema_version":"1.0","event_id":"sha256:6d37d9b456f87c2dbd82079a4e4e81807c8901d88241170ba690bce35d8eb723"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AGUKU2RQWRQLQOTNLY3KTZPHWV/bundle.json","state_url":"https://pith.science/pith/AGUKU2RQWRQLQOTNLY3KTZPHWV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AGUKU2RQWRQLQOTNLY3KTZPHWV/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":"2026-08-06T09:12:37Z","links":{"resolver":"https://pith.science/pith/AGUKU2RQWRQLQOTNLY3KTZPHWV","bundle":"https://pith.science/pith/AGUKU2RQWRQLQOTNLY3KTZPHWV/bundle.json","state":"https://pith.science/pith/AGUKU2RQWRQLQOTNLY3KTZPHWV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AGUKU2RQWRQLQOTNLY3KTZPHWV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:AGUKU2RQWRQLQOTNLY3KTZPHWV","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":"daa15f63525a7e200b69b080690858cd96a82bae61f1a2cc5554189a7f5f751b","cross_cats_sorted":["cs.CL","q-bio.BM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-17T04:13:11Z","title_canon_sha256":"e16e75a48f9adcffcd3c4d0db8cc00676beb20d508c5608f507e682d551c4a9b"},"schema_version":"1.0","source":{"id":"2108.07435","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.07435","created_at":"2026-07-05T03:38:28Z"},{"alias_kind":"arxiv_version","alias_value":"2108.07435v2","created_at":"2026-07-05T03:38:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.07435","created_at":"2026-07-05T03:38:28Z"},{"alias_kind":"pith_short_12","alias_value":"AGUKU2RQWRQL","created_at":"2026-07-05T03:38:28Z"},{"alias_kind":"pith_short_16","alias_value":"AGUKU2RQWRQLQOTN","created_at":"2026-07-05T03:38:28Z"},{"alias_kind":"pith_short_8","alias_value":"AGUKU2RQ","created_at":"2026-07-05T03:38:28Z"}],"graph_snapshots":[{"event_id":"sha256:6d37d9b456f87c2dbd82079a4e4e81807c8901d88241170ba690bce35d8eb723","target":"graph","created_at":"2026-07-05T03:38:28Z","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/2108.07435/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Protein is linked to almost every life process. Therefore, analyzing the biological structure and property of protein sequences is critical to the exploration of life, as well as disease detection and drug discovery. Traditional protein analysis methods tend to be labor-intensive and time-consuming. The emergence of deep learning models makes modeling data patterns in large quantities of data possible. Interdisciplinary researchers have begun to leverage deep learning methods to model large biological datasets, e.g. using long short-term memory and convolutional neural network for protein sequ","authors_text":"Chang-Yu Hsieh, Jie Tang, Jiezhong Qiu, Yijia Xiao, Ziang Li","cross_cats":["cs.CL","q-bio.BM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-17T04:13:11Z","title":"Modeling Protein Using Large-scale Pretrain Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.07435","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:b41880f56effa565031c19d08f7942e99080ca0f005210ecb04838c9d753f325","target":"record","created_at":"2026-07-05T03:38:28Z","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":"daa15f63525a7e200b69b080690858cd96a82bae61f1a2cc5554189a7f5f751b","cross_cats_sorted":["cs.CL","q-bio.BM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-17T04:13:11Z","title_canon_sha256":"e16e75a48f9adcffcd3c4d0db8cc00676beb20d508c5608f507e682d551c4a9b"},"schema_version":"1.0","source":{"id":"2108.07435","kind":"arxiv","version":2}},"canonical_sha256":"01a8aa6a30b460b83a6d5e36a9e5e7b5468c05fbcb3afd78039ab5f65f86f1e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"01a8aa6a30b460b83a6d5e36a9e5e7b5468c05fbcb3afd78039ab5f65f86f1e0","first_computed_at":"2026-07-05T03:38:28.170230Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:38:28.170230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VVZ/W17fdy1RRYJAQ/LnKSQK6U8j+v++59HwNy4NUlGttT41Y6VzBjzUos9jnZhzidPkuZc1j2VcQO24YV1zAw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:38:28.170710Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.07435","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b41880f56effa565031c19d08f7942e99080ca0f005210ecb04838c9d753f325","sha256:6d37d9b456f87c2dbd82079a4e4e81807c8901d88241170ba690bce35d8eb723"],"state_sha256":"210b3f92da160a8e751be8956e31b7993a9bb854a6caf0dce7dc0803ffacd063"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gs8e45u062u+VYFVT3limJJZTaAFYrisZhApKtYRk+ry4i7EKxvRu6I5OIeedsdIwrlLh07TjS6JQN1kkW4hCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T09:12:37.622662Z","bundle_sha256":"149b5c59e537adc0d0a9f26e6d01beec5dcc1a86bce4ed53cd5219dc06e950bd"}}