{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:RF25GQMOM7KRV6SFH6HV5UIWWF","short_pith_number":"pith:RF25GQMO","canonical_record":{"source":{"id":"2201.11147","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2022-01-23T14:49:49Z","cross_cats_sorted":["cs.AI","cs.CL","cs.IR","cs.LG"],"title_canon_sha256":"58b0289db5bbed9e2d5f50a775e2e63c94d4dbd8316d624c09efafc6b7f25908","abstract_canon_sha256":"cee7420400c7d5f06a4c3de7f604b0e18fb0f4ad3cfcd0cd71bdc3d62f948195"},"schema_version":"1.0"},"canonical_sha256":"8975d3418e67d51afa453f8f5ed116b16b2cd3c27326b1edd67b53ba84e38aad","source":{"kind":"arxiv","id":"2201.11147","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.11147","created_at":"2026-07-05T05:12:10Z"},{"alias_kind":"arxiv_version","alias_value":"2201.11147v6","created_at":"2026-07-05T05:12:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.11147","created_at":"2026-07-05T05:12:10Z"},{"alias_kind":"pith_short_12","alias_value":"RF25GQMOM7KR","created_at":"2026-07-05T05:12:10Z"},{"alias_kind":"pith_short_16","alias_value":"RF25GQMOM7KRV6SF","created_at":"2026-07-05T05:12:10Z"},{"alias_kind":"pith_short_8","alias_value":"RF25GQMO","created_at":"2026-07-05T05:12:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:RF25GQMOM7KRV6SFH6HV5UIWWF","target":"record","payload":{"canonical_record":{"source":{"id":"2201.11147","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2022-01-23T14:49:49Z","cross_cats_sorted":["cs.AI","cs.CL","cs.IR","cs.LG"],"title_canon_sha256":"58b0289db5bbed9e2d5f50a775e2e63c94d4dbd8316d624c09efafc6b7f25908","abstract_canon_sha256":"cee7420400c7d5f06a4c3de7f604b0e18fb0f4ad3cfcd0cd71bdc3d62f948195"},"schema_version":"1.0"},"canonical_sha256":"8975d3418e67d51afa453f8f5ed116b16b2cd3c27326b1edd67b53ba84e38aad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:12:10.339012Z","signature_b64":"4sRM43ZGVJUjS6GROhfL12+FkTJmuD9isDrkPdWpXQcn8yajKEWg1PXOrdreVCVbEpHASH85bLk6Xl+QDpt7DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8975d3418e67d51afa453f8f5ed116b16b2cd3c27326b1edd67b53ba84e38aad","last_reissued_at":"2026-07-05T05:12:10.338445Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:12:10.338445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.11147","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:12:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hYRVoHLJ7hf+gzsz6RajhZE1bi34YJkk7hb+EIAyvJpNVRxoHOPVxdQAl0vVgHdeZzQDpfDFLXGGHslse2sSAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:34:07.669886Z"},"content_sha256":"29388096e697c9c1788f44dc79eb4a32c2cb22984eb68cc37cf58e6929deac87","schema_version":"1.0","event_id":"sha256:29388096e697c9c1788f44dc79eb4a32c2cb22984eb68cc37cf58e6929deac87"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:RF25GQMOM7KRV6SFH6HV5UIWWF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OntoProtein: Protein Pretraining With Gene Ontology Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.IR","cs.LG"],"primary_cat":"q-bio.BM","authors_text":"Haosen Hong, Huajun Chen, Jiazhang Lian, Ningyu Zhang, Qiang Zhang, Shumin Deng, Siyuan Cheng, Xiaozhuan Liang, Zhen Bi","submitted_at":"2022-01-23T14:49:49Z","abstract_excerpt":"Self-supervised protein language models have proved their effectiveness in learning the proteins representations. With the increasing computational power, current protein language models pre-trained with millions of diverse sequences can advance the parameter scale from million-level to billion-level and achieve remarkable improvement. However, those prevailing approaches rarely consider incorporating knowledge graphs (KGs), which can provide rich structured knowledge facts for better protein representations. We argue that informative biology knowledge in KGs can enhance protein representation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.11147","kind":"arxiv","version":6},"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/2201.11147/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":"2026-07-05T05:12:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FHvDqhb1246aWiP9X33UzItNnKU/5Tf4E0CAChGqegg+cz4oIXOfmChHLwstj3uuZNGWLuEes0/C044Ggi+fCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:34:07.670454Z"},"content_sha256":"2f3533254c7644cb39658b6d1399ea329111d011dbccd10056bba48156b158ab","schema_version":"1.0","event_id":"sha256:2f3533254c7644cb39658b6d1399ea329111d011dbccd10056bba48156b158ab"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RF25GQMOM7KRV6SFH6HV5UIWWF/bundle.json","state_url":"https://pith.science/pith/RF25GQMOM7KRV6SFH6HV5UIWWF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RF25GQMOM7KRV6SFH6HV5UIWWF/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":"2026-08-08T01:34:07Z","links":{"resolver":"https://pith.science/pith/RF25GQMOM7KRV6SFH6HV5UIWWF","bundle":"https://pith.science/pith/RF25GQMOM7KRV6SFH6HV5UIWWF/bundle.json","state":"https://pith.science/pith/RF25GQMOM7KRV6SFH6HV5UIWWF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RF25GQMOM7KRV6SFH6HV5UIWWF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:RF25GQMOM7KRV6SFH6HV5UIWWF","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":"cee7420400c7d5f06a4c3de7f604b0e18fb0f4ad3cfcd0cd71bdc3d62f948195","cross_cats_sorted":["cs.AI","cs.CL","cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2022-01-23T14:49:49Z","title_canon_sha256":"58b0289db5bbed9e2d5f50a775e2e63c94d4dbd8316d624c09efafc6b7f25908"},"schema_version":"1.0","source":{"id":"2201.11147","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.11147","created_at":"2026-07-05T05:12:10Z"},{"alias_kind":"arxiv_version","alias_value":"2201.11147v6","created_at":"2026-07-05T05:12:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.11147","created_at":"2026-07-05T05:12:10Z"},{"alias_kind":"pith_short_12","alias_value":"RF25GQMOM7KR","created_at":"2026-07-05T05:12:10Z"},{"alias_kind":"pith_short_16","alias_value":"RF25GQMOM7KRV6SF","created_at":"2026-07-05T05:12:10Z"},{"alias_kind":"pith_short_8","alias_value":"RF25GQMO","created_at":"2026-07-05T05:12:10Z"}],"graph_snapshots":[{"event_id":"sha256:2f3533254c7644cb39658b6d1399ea329111d011dbccd10056bba48156b158ab","target":"graph","created_at":"2026-07-05T05:12:10Z","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/2201.11147/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-supervised protein language models have proved their effectiveness in learning the proteins representations. With the increasing computational power, current protein language models pre-trained with millions of diverse sequences can advance the parameter scale from million-level to billion-level and achieve remarkable improvement. However, those prevailing approaches rarely consider incorporating knowledge graphs (KGs), which can provide rich structured knowledge facts for better protein representations. We argue that informative biology knowledge in KGs can enhance protein representation","authors_text":"Haosen Hong, Huajun Chen, Jiazhang Lian, Ningyu Zhang, Qiang Zhang, Shumin Deng, Siyuan Cheng, Xiaozhuan Liang, Zhen Bi","cross_cats":["cs.AI","cs.CL","cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2022-01-23T14:49:49Z","title":"OntoProtein: Protein Pretraining With Gene Ontology Embedding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.11147","kind":"arxiv","version":6},"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":"sha256:29388096e697c9c1788f44dc79eb4a32c2cb22984eb68cc37cf58e6929deac87","target":"record","created_at":"2026-07-05T05:12:10Z","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":"cee7420400c7d5f06a4c3de7f604b0e18fb0f4ad3cfcd0cd71bdc3d62f948195","cross_cats_sorted":["cs.AI","cs.CL","cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2022-01-23T14:49:49Z","title_canon_sha256":"58b0289db5bbed9e2d5f50a775e2e63c94d4dbd8316d624c09efafc6b7f25908"},"schema_version":"1.0","source":{"id":"2201.11147","kind":"arxiv","version":6}},"canonical_sha256":"8975d3418e67d51afa453f8f5ed116b16b2cd3c27326b1edd67b53ba84e38aad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8975d3418e67d51afa453f8f5ed116b16b2cd3c27326b1edd67b53ba84e38aad","first_computed_at":"2026-07-05T05:12:10.338445Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:12:10.338445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4sRM43ZGVJUjS6GROhfL12+FkTJmuD9isDrkPdWpXQcn8yajKEWg1PXOrdreVCVbEpHASH85bLk6Xl+QDpt7DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:12:10.339012Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.11147","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:29388096e697c9c1788f44dc79eb4a32c2cb22984eb68cc37cf58e6929deac87","sha256:2f3533254c7644cb39658b6d1399ea329111d011dbccd10056bba48156b158ab"],"state_sha256":"2051bc2404b7a2285ade8b6495c18ecadfd3dc985cec58c4b55e2d0a05d60c43"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qa+QPxMe5DF8r5+V8gawHIdFdOs+qyR33AmHVXobNM370/LjAVloK84dgZWLwnk8PsPpTpwWk32dzBUfK3YsDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T01:34:07.675923Z","bundle_sha256":"ea9ed65a8c903dcbce02b271161c9035c1d46542795d1b55576dca3b9876086b"}}