{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:5VDW6U3COMEFRQ5MWMGQ4LXPS7","short_pith_number":"pith:5VDW6U3C","schema_version":"1.0","canonical_sha256":"ed476f5362730858c3acb30d0e2eef97d37c723e1cefa2eec345867e75b1a3fb","source":{"kind":"arxiv","id":"1301.0834","version":1},"attestation_state":"computed","paper":{"title":"An Efficient Algorithm for Clustering of Large-Scale Mass Spectrometry Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.GN","q-bio.QM"],"primary_cat":"cs.DS","authors_text":"Fahad Saeed, Jason D. Hoffert, Mark A. Knepper, Trairak Pisitkun","submitted_at":"2013-01-04T21:09:18Z","abstract_excerpt":"High-throughput spectrometers are capable of producing data sets containing thousands of spectra for a single biological sample. These data sets contain a substantial amount of redundancy from peptides that may get selected multiple times in a LC-MS/MS experiment. In this paper, we present an efficient algorithm, CAMS (Clustering Algorithm for Mass Spectra) for clustering mass spectrometry data which increases both the sensitivity and confidence of spectral assignment. CAMS utilizes a novel metric, called F-set, that allows accurate identification of the spectra that are similar. A graph theor"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1301.0834","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2013-01-04T21:09:18Z","cross_cats_sorted":["q-bio.GN","q-bio.QM"],"title_canon_sha256":"ffc40fcb9bde46816c2e5adc8c3c055d35ef65ab4bd4428591c0cf038ed051e8","abstract_canon_sha256":"0432d38b5565706b58714b10dd4cfd8b2a62233e2d6524e886afe2c26aed1c43"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:37:07.588604Z","signature_b64":"V0qlhlv/GhpaEtbapk2bKkI2dU9DoCGpvS0CZxAhuNUOU/VQ0NAm5vYtmmWJEqiD+Xe6WN3b1Gf/Fd2N1LB6CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed476f5362730858c3acb30d0e2eef97d37c723e1cefa2eec345867e75b1a3fb","last_reissued_at":"2026-05-18T03:37:07.587773Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:37:07.587773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Efficient Algorithm for Clustering of Large-Scale Mass Spectrometry Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.GN","q-bio.QM"],"primary_cat":"cs.DS","authors_text":"Fahad Saeed, Jason D. Hoffert, Mark A. Knepper, Trairak Pisitkun","submitted_at":"2013-01-04T21:09:18Z","abstract_excerpt":"High-throughput spectrometers are capable of producing data sets containing thousands of spectra for a single biological sample. These data sets contain a substantial amount of redundancy from peptides that may get selected multiple times in a LC-MS/MS experiment. In this paper, we present an efficient algorithm, CAMS (Clustering Algorithm for Mass Spectra) for clustering mass spectrometry data which increases both the sensitivity and confidence of spectral assignment. CAMS utilizes a novel metric, called F-set, that allows accurate identification of the spectra that are similar. A graph theor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.0834","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":""},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1301.0834","created_at":"2026-05-18T03:37:07.587905+00:00"},{"alias_kind":"arxiv_version","alias_value":"1301.0834v1","created_at":"2026-05-18T03:37:07.587905+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.0834","created_at":"2026-05-18T03:37:07.587905+00:00"},{"alias_kind":"pith_short_12","alias_value":"5VDW6U3COMEF","created_at":"2026-05-18T12:27:34.582898+00:00"},{"alias_kind":"pith_short_16","alias_value":"5VDW6U3COMEFRQ5M","created_at":"2026-05-18T12:27:34.582898+00:00"},{"alias_kind":"pith_short_8","alias_value":"5VDW6U3C","created_at":"2026-05-18T12:27:34.582898+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5VDW6U3COMEFRQ5MWMGQ4LXPS7","json":"https://pith.science/pith/5VDW6U3COMEFRQ5MWMGQ4LXPS7.json","graph_json":"https://pith.science/api/pith-number/5VDW6U3COMEFRQ5MWMGQ4LXPS7/graph.json","events_json":"https://pith.science/api/pith-number/5VDW6U3COMEFRQ5MWMGQ4LXPS7/events.json","paper":"https://pith.science/paper/5VDW6U3C"},"agent_actions":{"view_html":"https://pith.science/pith/5VDW6U3COMEFRQ5MWMGQ4LXPS7","download_json":"https://pith.science/pith/5VDW6U3COMEFRQ5MWMGQ4LXPS7.json","view_paper":"https://pith.science/paper/5VDW6U3C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1301.0834&json=true","fetch_graph":"https://pith.science/api/pith-number/5VDW6U3COMEFRQ5MWMGQ4LXPS7/graph.json","fetch_events":"https://pith.science/api/pith-number/5VDW6U3COMEFRQ5MWMGQ4LXPS7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5VDW6U3COMEFRQ5MWMGQ4LXPS7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5VDW6U3COMEFRQ5MWMGQ4LXPS7/action/storage_attestation","attest_author":"https://pith.science/pith/5VDW6U3COMEFRQ5MWMGQ4LXPS7/action/author_attestation","sign_citation":"https://pith.science/pith/5VDW6U3COMEFRQ5MWMGQ4LXPS7/action/citation_signature","submit_replication":"https://pith.science/pith/5VDW6U3COMEFRQ5MWMGQ4LXPS7/action/replication_record"}},"created_at":"2026-05-18T03:37:07.587905+00:00","updated_at":"2026-05-18T03:37:07.587905+00:00"}