{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:Q4QMQH6I433OVIZGSXQMZHUFIQ","short_pith_number":"pith:Q4QMQH6I","canonical_record":{"source":{"id":"2206.12240","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2022-06-24T14:08:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2a386d4f3bd877e78370b2e8926d2d93ff03bdd570cea3b8bdb29fada435d428","abstract_canon_sha256":"b790c8d92d44c73a29ad8bd97c19ede01d4c9fa8d90167dd4281891f2bf59407"},"schema_version":"1.0"},"canonical_sha256":"8720c81fc8e6f6eaa32695e0cc9e85440fc1b084bc2e6fa3f449fc3ef62bddef","source":{"kind":"arxiv","id":"2206.12240","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.12240","created_at":"2026-07-05T04:34:34Z"},{"alias_kind":"arxiv_version","alias_value":"2206.12240v1","created_at":"2026-07-05T04:34:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.12240","created_at":"2026-07-05T04:34:34Z"},{"alias_kind":"pith_short_12","alias_value":"Q4QMQH6I433O","created_at":"2026-07-05T04:34:34Z"},{"alias_kind":"pith_short_16","alias_value":"Q4QMQH6I433OVIZG","created_at":"2026-07-05T04:34:34Z"},{"alias_kind":"pith_short_8","alias_value":"Q4QMQH6I","created_at":"2026-07-05T04:34:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:Q4QMQH6I433OVIZGSXQMZHUFIQ","target":"record","payload":{"canonical_record":{"source":{"id":"2206.12240","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2022-06-24T14:08:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2a386d4f3bd877e78370b2e8926d2d93ff03bdd570cea3b8bdb29fada435d428","abstract_canon_sha256":"b790c8d92d44c73a29ad8bd97c19ede01d4c9fa8d90167dd4281891f2bf59407"},"schema_version":"1.0"},"canonical_sha256":"8720c81fc8e6f6eaa32695e0cc9e85440fc1b084bc2e6fa3f449fc3ef62bddef","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:34:34.434784Z","signature_b64":"RT3W2NG6mmKdHsGmtDcljLYerXUphayphERIiCT5jiEoHg3M5gYx5OIR/jS/nmrCS6Ssa8K9PQ5rm7OX8D8YBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8720c81fc8e6f6eaa32695e0cc9e85440fc1b084bc2e6fa3f449fc3ef62bddef","last_reissued_at":"2026-07-05T04:34:34.434346Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:34:34.434346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.12240","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":"2026-07-05T04:34:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/xqJLaIfcOyFyGIV2/8u0rmOdBE3OH6op2k7ccCYxMSmGAnvX+bisr8RqWQ2ZZO7Qr37UGR6VixUOWpjScxwCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T23:17:21.905715Z"},"content_sha256":"0eeaced6263f56b0fb44fc4f695d15f074bb30d71f62bcf6b6a845e0bb978d81","schema_version":"1.0","event_id":"sha256:0eeaced6263f56b0fb44fc4f695d15f074bb30d71f62bcf6b6a845e0bb978d81"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:Q4QMQH6I433OVIZGSXQMZHUFIQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PSP: Million-level Protein Sequence Dataset for Protein Structure Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.BM","authors_text":"Boxin Xue, Fan Xu, Fan Yu, Haotian Chu, Jialiang Yu, Jie Chen, Jun Zhang, Lei Chen, Lijiang Yang, Mengyun Chen, Min Wang, Ningxi Ni, Piya Patra, Sirui Liu, Yi Qin Gao, Yuan Liu, Yuhao Xie, Zhenyu Chen, Zidong Wang","submitted_at":"2022-06-24T14:08:44Z","abstract_excerpt":"Proteins are essential component of human life and their structures are important for function and mechanism analysis. Recent work has shown the potential of AI-driven methods for protein structure prediction. However, the development of new models is restricted by the lack of dataset and benchmark training procedure. To the best of our knowledge, the existing open source datasets are far less to satisfy the needs of modern protein sequence-structure related research. To solve this problem, we present the first million-level protein structure prediction dataset with high coverage and diversity"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.12240","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/2206.12240/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":"2026-07-05T04:34:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1MRb0oJ1XhcxDB0cjO0kCjKpAg97XfGFkMIbbqeiuQlIcIMFGCqDkEm7JVVMqF4M8AaXa3crO0gxr+dEnuypBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T23:17:21.907525Z"},"content_sha256":"906f0d5bb1e271e6715d956c20a47f25f5f2861d7af018fd84531bb700fb0ea0","schema_version":"1.0","event_id":"sha256:906f0d5bb1e271e6715d956c20a47f25f5f2861d7af018fd84531bb700fb0ea0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q4QMQH6I433OVIZGSXQMZHUFIQ/bundle.json","state_url":"https://pith.science/pith/Q4QMQH6I433OVIZGSXQMZHUFIQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q4QMQH6I433OVIZGSXQMZHUFIQ/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":"2026-08-22T23:17:21Z","links":{"resolver":"https://pith.science/pith/Q4QMQH6I433OVIZGSXQMZHUFIQ","bundle":"https://pith.science/pith/Q4QMQH6I433OVIZGSXQMZHUFIQ/bundle.json","state":"https://pith.science/pith/Q4QMQH6I433OVIZGSXQMZHUFIQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q4QMQH6I433OVIZGSXQMZHUFIQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:Q4QMQH6I433OVIZGSXQMZHUFIQ","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":"b790c8d92d44c73a29ad8bd97c19ede01d4c9fa8d90167dd4281891f2bf59407","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2022-06-24T14:08:44Z","title_canon_sha256":"2a386d4f3bd877e78370b2e8926d2d93ff03bdd570cea3b8bdb29fada435d428"},"schema_version":"1.0","source":{"id":"2206.12240","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.12240","created_at":"2026-07-05T04:34:34Z"},{"alias_kind":"arxiv_version","alias_value":"2206.12240v1","created_at":"2026-07-05T04:34:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.12240","created_at":"2026-07-05T04:34:34Z"},{"alias_kind":"pith_short_12","alias_value":"Q4QMQH6I433O","created_at":"2026-07-05T04:34:34Z"},{"alias_kind":"pith_short_16","alias_value":"Q4QMQH6I433OVIZG","created_at":"2026-07-05T04:34:34Z"},{"alias_kind":"pith_short_8","alias_value":"Q4QMQH6I","created_at":"2026-07-05T04:34:34Z"}],"graph_snapshots":[{"event_id":"sha256:906f0d5bb1e271e6715d956c20a47f25f5f2861d7af018fd84531bb700fb0ea0","target":"graph","created_at":"2026-07-05T04:34:34Z","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/2206.12240/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Proteins are essential component of human life and their structures are important for function and mechanism analysis. Recent work has shown the potential of AI-driven methods for protein structure prediction. However, the development of new models is restricted by the lack of dataset and benchmark training procedure. To the best of our knowledge, the existing open source datasets are far less to satisfy the needs of modern protein sequence-structure related research. To solve this problem, we present the first million-level protein structure prediction dataset with high coverage and diversity","authors_text":"Boxin Xue, Fan Xu, Fan Yu, Haotian Chu, Jialiang Yu, Jie Chen, Jun Zhang, Lei Chen, Lijiang Yang, Mengyun Chen, Min Wang, Ningxi Ni, Piya Patra, Sirui Liu, Yi Qin Gao, Yuan Liu, Yuhao Xie, Zhenyu Chen, Zidong Wang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2022-06-24T14:08:44Z","title":"PSP: Million-level Protein Sequence Dataset for Protein Structure Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.12240","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":"sha256:0eeaced6263f56b0fb44fc4f695d15f074bb30d71f62bcf6b6a845e0bb978d81","target":"record","created_at":"2026-07-05T04:34:34Z","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":"b790c8d92d44c73a29ad8bd97c19ede01d4c9fa8d90167dd4281891f2bf59407","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2022-06-24T14:08:44Z","title_canon_sha256":"2a386d4f3bd877e78370b2e8926d2d93ff03bdd570cea3b8bdb29fada435d428"},"schema_version":"1.0","source":{"id":"2206.12240","kind":"arxiv","version":1}},"canonical_sha256":"8720c81fc8e6f6eaa32695e0cc9e85440fc1b084bc2e6fa3f449fc3ef62bddef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8720c81fc8e6f6eaa32695e0cc9e85440fc1b084bc2e6fa3f449fc3ef62bddef","first_computed_at":"2026-07-05T04:34:34.434346Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:34:34.434346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RT3W2NG6mmKdHsGmtDcljLYerXUphayphERIiCT5jiEoHg3M5gYx5OIR/jS/nmrCS6Ssa8K9PQ5rm7OX8D8YBw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:34:34.434784Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.12240","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0eeaced6263f56b0fb44fc4f695d15f074bb30d71f62bcf6b6a845e0bb978d81","sha256:906f0d5bb1e271e6715d956c20a47f25f5f2861d7af018fd84531bb700fb0ea0"],"state_sha256":"6488394bef19771b1fdeb334ecbeb6bc7ee813040748a433d11830113232e89a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2ZpvLtfb8cQEsksqYd5tB8aFXHHANgdD6o9DU0iayT2CJWZgS2Tsy3FEORG7MvGOR2IgbuLzHh9Yx1C9yH55Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T23:17:21.914684Z","bundle_sha256":"d4f427e1068bb9dddd3f8d196670c11aaa77d8e833ba98eb3b5770e6e61c4af0"}}