{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GZIY2NUOLVVXIZMOWAD3SVP4GQ","short_pith_number":"pith:GZIY2NUO","schema_version":"1.0","canonical_sha256":"36518d368e5d6b74658eb007b955fc34262a35a290a11532afa14ac1deeaad4b","source":{"kind":"arxiv","id":"2212.14567","version":1},"attestation_state":"computed","paper":{"title":"Topical Hidden Genome: Discovering Latent Cancer Mutational Topics using a Bayesian Multilevel Context-learning Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.AP","stat.CO"],"primary_cat":"stat.ME","authors_text":"Colin B. Begg, Ronglai Shen, Saptarshi Chakraborty, Zoe Guan","submitted_at":"2022-12-30T06:47:34Z","abstract_excerpt":"Statistical inference on the cancer-site specificities of collective ultra-rare whole genome somatic mutations is an open problem. Traditional statistical methods cannot handle whole-genome mutation data due to their ultra-high-dimensionality and extreme data sparsity -- e.g., >30 million unique variants are observed in the ~1700 whole-genome tumor dataset considered herein, of which >99% variants are encountered only once. To harness information in these rare variants we have recently proposed the \"hidden genome model\", a formal multilevel multi-logistic model that mines information in ultra-"},"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":"2212.14567","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2022-12-30T06:47:34Z","cross_cats_sorted":["stat.AP","stat.CO"],"title_canon_sha256":"f3b9106e4b1185e08b1e126359218eac64d8bff6238662147fc194d13877bf64","abstract_canon_sha256":"25a1f83ab218f3dbeaccdff03dcc9074668e08730b3f8018a7dc94dc8c8412c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:29:11.750360Z","signature_b64":"IhDIWKYhrb2Vct7vuVe/I0rM6gBFvgIBNbWtT1JzDi2LxAJDJybbIkL1/dTPihl07RE8m++BYg5cZoy5gtMQAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36518d368e5d6b74658eb007b955fc34262a35a290a11532afa14ac1deeaad4b","last_reissued_at":"2026-07-05T05:29:11.749909Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:29:11.749909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Topical Hidden Genome: Discovering Latent Cancer Mutational Topics using a Bayesian Multilevel Context-learning Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.AP","stat.CO"],"primary_cat":"stat.ME","authors_text":"Colin B. Begg, Ronglai Shen, Saptarshi Chakraborty, Zoe Guan","submitted_at":"2022-12-30T06:47:34Z","abstract_excerpt":"Statistical inference on the cancer-site specificities of collective ultra-rare whole genome somatic mutations is an open problem. Traditional statistical methods cannot handle whole-genome mutation data due to their ultra-high-dimensionality and extreme data sparsity -- e.g., >30 million unique variants are observed in the ~1700 whole-genome tumor dataset considered herein, of which >99% variants are encountered only once. To harness information in these rare variants we have recently proposed the \"hidden genome model\", a formal multilevel multi-logistic model that mines information in ultra-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.14567","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/2212.14567/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":"2212.14567","created_at":"2026-07-05T05:29:11.749972+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.14567v1","created_at":"2026-07-05T05:29:11.749972+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.14567","created_at":"2026-07-05T05:29:11.749972+00:00"},{"alias_kind":"pith_short_12","alias_value":"GZIY2NUOLVVX","created_at":"2026-07-05T05:29:11.749972+00:00"},{"alias_kind":"pith_short_16","alias_value":"GZIY2NUOLVVXIZMO","created_at":"2026-07-05T05:29:11.749972+00:00"},{"alias_kind":"pith_short_8","alias_value":"GZIY2NUO","created_at":"2026-07-05T05:29:11.749972+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/GZIY2NUOLVVXIZMOWAD3SVP4GQ","json":"https://pith.science/pith/GZIY2NUOLVVXIZMOWAD3SVP4GQ.json","graph_json":"https://pith.science/api/pith-number/GZIY2NUOLVVXIZMOWAD3SVP4GQ/graph.json","events_json":"https://pith.science/api/pith-number/GZIY2NUOLVVXIZMOWAD3SVP4GQ/events.json","paper":"https://pith.science/paper/GZIY2NUO"},"agent_actions":{"view_html":"https://pith.science/pith/GZIY2NUOLVVXIZMOWAD3SVP4GQ","download_json":"https://pith.science/pith/GZIY2NUOLVVXIZMOWAD3SVP4GQ.json","view_paper":"https://pith.science/paper/GZIY2NUO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.14567&json=true","fetch_graph":"https://pith.science/api/pith-number/GZIY2NUOLVVXIZMOWAD3SVP4GQ/graph.json","fetch_events":"https://pith.science/api/pith-number/GZIY2NUOLVVXIZMOWAD3SVP4GQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GZIY2NUOLVVXIZMOWAD3SVP4GQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GZIY2NUOLVVXIZMOWAD3SVP4GQ/action/storage_attestation","attest_author":"https://pith.science/pith/GZIY2NUOLVVXIZMOWAD3SVP4GQ/action/author_attestation","sign_citation":"https://pith.science/pith/GZIY2NUOLVVXIZMOWAD3SVP4GQ/action/citation_signature","submit_replication":"https://pith.science/pith/GZIY2NUOLVVXIZMOWAD3SVP4GQ/action/replication_record"}},"created_at":"2026-07-05T05:29:11.749972+00:00","updated_at":"2026-07-05T05:29:11.749972+00:00"}