{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:73PXFCYL7BUDZVFN4RDKQH67W4","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":"eb688e868d7b1448174402d047a77500f7f1b420915f6ae219e2665f4c1907fc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-30T08:32:39Z","title_canon_sha256":"aef30f8152fa36493064cc14402e41393e0c2c6fccd28410261e0daa67c596c9"},"schema_version":"1.0","source":{"id":"2507.00087","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00087","created_at":"2026-07-05T11:29:36Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00087v1","created_at":"2026-07-05T11:29:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00087","created_at":"2026-07-05T11:29:36Z"},{"alias_kind":"pith_short_12","alias_value":"73PXFCYL7BUD","created_at":"2026-07-05T11:29:36Z"},{"alias_kind":"pith_short_16","alias_value":"73PXFCYL7BUDZVFN","created_at":"2026-07-05T11:29:36Z"},{"alias_kind":"pith_short_8","alias_value":"73PXFCYL","created_at":"2026-07-05T11:29:36Z"}],"graph_snapshots":[{"event_id":"sha256:74aedba5f0881de1c8723ae103654273767072881d5d4cc1702e0240a99f5a50","target":"graph","created_at":"2026-07-05T11:29:36Z","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/2507.00087/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep learning has advanced mass spectrometry data interpretation, yet most models remain feature extractors rather than unified scoring frameworks. We present pUniFind, the first large-scale multimodal pre-trained model in proteomics that integrates end-to-end peptide-spectrum scoring with open, zero-shot de novo sequencing. Trained on over 100 million open search-derived spectra, pUniFind aligns spectral and peptide modalities via cross modality prediction and outperforms traditional engines across diverse datasets, particularly achieving a 42.6 percent increase in the number of identified pe","authors_text":"Han Wen, Hao Chi, Jiale Zhao, Jiaxiang Ding, Kaifei Wang, Pengzhi Mao, Ranfei Chen, Shuqi Lu, Weijie Zhang, Weinan E, Xiaohong Ji, Xin Zhang, Yaping Peng, Yiming Li, Yucheng Liao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-30T08:32:39Z","title":"pUniFind: a unified large pre-trained deep learning model pushing the limit of mass spectra interpretation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00087","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":"sha256:443bb48d563750d8fb535d792e23572e86e581ade39d9d221bbc6afae41530b9","target":"record","created_at":"2026-07-05T11:29:36Z","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":"eb688e868d7b1448174402d047a77500f7f1b420915f6ae219e2665f4c1907fc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-30T08:32:39Z","title_canon_sha256":"aef30f8152fa36493064cc14402e41393e0c2c6fccd28410261e0daa67c596c9"},"schema_version":"1.0","source":{"id":"2507.00087","kind":"arxiv","version":1}},"canonical_sha256":"fedf728b0bf8683cd4ade446a81fdfb703532f45f2653290f8a15a16b71384d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fedf728b0bf8683cd4ade446a81fdfb703532f45f2653290f8a15a16b71384d2","first_computed_at":"2026-07-05T11:29:36.763638Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:36.763638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0g1Y2VWR9WxE/8r5Qz2lOPbS4yMNm6tnMALZAeFOR8HOfqjQsknEQMXzujRJMVQEmOHHR9onYV+RyvZSjg7UAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:36.764096Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.00087","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:443bb48d563750d8fb535d792e23572e86e581ade39d9d221bbc6afae41530b9","sha256:74aedba5f0881de1c8723ae103654273767072881d5d4cc1702e0240a99f5a50"],"state_sha256":"8bb4081ba629eae8dd1f6a71f224dc5a986893a9417f8bcd18be7f51242f93f7"}