{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:COC7TKWJDEBMGVKXJD3HHJVJJX","short_pith_number":"pith:COC7TKWJ","schema_version":"1.0","canonical_sha256":"1385f9aac91902c3555748f673a6a94dc478c849ff825aa9ae5dd2cceb0e94f9","source":{"kind":"arxiv","id":"2506.22963","version":1},"attestation_state":"computed","paper":{"title":"CN-SBM: Categorical Block Modelling For Primary and Residual Copy Number Variation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","q-bio.GN"],"primary_cat":"stat.ML","authors_text":"Benjamin Bloem-Reddy, Daniel Lai, J Maxwell Douglas, Kevin Lam, Samuel Aparicio, William Daniels, Yongjin Park","submitted_at":"2025-06-28T17:45:45Z","abstract_excerpt":"Cancer is a genetic disorder whose clonal evolution can be monitored by tracking noisy genome-wide copy number variants. We introduce the Copy Number Stochastic Block Model (CN-SBM), a probabilistic framework that jointly clusters samples and genomic regions based on discrete copy number states using a bipartite categorical block model. Unlike models relying on Gaussian or Poisson assumptions, CN-SBM respects the discrete nature of CNV calls and captures subpopulation-specific patterns through block-wise structure. Using a two-stage approach, CN-SBM decomposes CNV data into primary and residua"},"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":"2506.22963","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-06-28T17:45:45Z","cross_cats_sorted":["cs.LG","q-bio.GN"],"title_canon_sha256":"b52fda3720fb38d25d013331941c34a0e1f7dc375f738026bb2a78985f7a7e1d","abstract_canon_sha256":"1c41c89945a520db6c376513a6d5296c3eec6bb0f4c42f6b49674e49423e26c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:48.406492Z","signature_b64":"XpwG4nySwCB5gsCTsnAyTTq1b62GEyGyKFUAreqnNj6MfeJ2QSfpS5HlQ0GBneooDhuFHy5iO8kiUwFt7BgvAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1385f9aac91902c3555748f673a6a94dc478c849ff825aa9ae5dd2cceb0e94f9","last_reissued_at":"2026-07-05T11:28:48.405971Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:48.405971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CN-SBM: Categorical Block Modelling For Primary and Residual Copy Number Variation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","q-bio.GN"],"primary_cat":"stat.ML","authors_text":"Benjamin Bloem-Reddy, Daniel Lai, J Maxwell Douglas, Kevin Lam, Samuel Aparicio, William Daniels, Yongjin Park","submitted_at":"2025-06-28T17:45:45Z","abstract_excerpt":"Cancer is a genetic disorder whose clonal evolution can be monitored by tracking noisy genome-wide copy number variants. We introduce the Copy Number Stochastic Block Model (CN-SBM), a probabilistic framework that jointly clusters samples and genomic regions based on discrete copy number states using a bipartite categorical block model. Unlike models relying on Gaussian or Poisson assumptions, CN-SBM respects the discrete nature of CNV calls and captures subpopulation-specific patterns through block-wise structure. Using a two-stage approach, CN-SBM decomposes CNV data into primary and residua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22963","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/2506.22963/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.22963","created_at":"2026-07-05T11:28:48.406030+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.22963v1","created_at":"2026-07-05T11:28:48.406030+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22963","created_at":"2026-07-05T11:28:48.406030+00:00"},{"alias_kind":"pith_short_12","alias_value":"COC7TKWJDEBM","created_at":"2026-07-05T11:28:48.406030+00:00"},{"alias_kind":"pith_short_16","alias_value":"COC7TKWJDEBMGVKX","created_at":"2026-07-05T11:28:48.406030+00:00"},{"alias_kind":"pith_short_8","alias_value":"COC7TKWJ","created_at":"2026-07-05T11:28:48.406030+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/COC7TKWJDEBMGVKXJD3HHJVJJX","json":"https://pith.science/pith/COC7TKWJDEBMGVKXJD3HHJVJJX.json","graph_json":"https://pith.science/api/pith-number/COC7TKWJDEBMGVKXJD3HHJVJJX/graph.json","events_json":"https://pith.science/api/pith-number/COC7TKWJDEBMGVKXJD3HHJVJJX/events.json","paper":"https://pith.science/paper/COC7TKWJ"},"agent_actions":{"view_html":"https://pith.science/pith/COC7TKWJDEBMGVKXJD3HHJVJJX","download_json":"https://pith.science/pith/COC7TKWJDEBMGVKXJD3HHJVJJX.json","view_paper":"https://pith.science/paper/COC7TKWJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.22963&json=true","fetch_graph":"https://pith.science/api/pith-number/COC7TKWJDEBMGVKXJD3HHJVJJX/graph.json","fetch_events":"https://pith.science/api/pith-number/COC7TKWJDEBMGVKXJD3HHJVJJX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/COC7TKWJDEBMGVKXJD3HHJVJJX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/COC7TKWJDEBMGVKXJD3HHJVJJX/action/storage_attestation","attest_author":"https://pith.science/pith/COC7TKWJDEBMGVKXJD3HHJVJJX/action/author_attestation","sign_citation":"https://pith.science/pith/COC7TKWJDEBMGVKXJD3HHJVJJX/action/citation_signature","submit_replication":"https://pith.science/pith/COC7TKWJDEBMGVKXJD3HHJVJJX/action/replication_record"}},"created_at":"2026-07-05T11:28:48.406030+00:00","updated_at":"2026-07-05T11:28:48.406030+00:00"}