{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QBEK7RXNTDKF4LCKFFGQMASYBX","short_pith_number":"pith:QBEK7RXN","schema_version":"1.0","canonical_sha256":"8048afc6ed98d45e2c4a294d0602580dfc30760637f7455afa882390797868ed","source":{"kind":"arxiv","id":"2607.04987","version":1},"attestation_state":"computed","paper":{"title":"Data-Driven Soft Labeling Scales DNA Read Classification to Whole-Body Cell-Type Deconvolution","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["q-bio.GN","q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Dmytro Rizdvanetskyi, Nathan Ross, Pavlo Lutsik","submitted_at":"2026-07-06T12:25:16Z","abstract_excerpt":"Cell-type deconvolution, the task of estimating the proportions of constituent cell types in a heterogeneous biological sample, is a core problem in computational biology. Methods that rely on epigenetic marks such as DNA methylation typically operate on aggregated methylation estimates, discarding the pattern-level information carried by individual DNA reads. Existing read-level approaches that exploit this information are scarce, and all remain restricted to few-class settings; scaling them further is an open problem because, at scale, non-discriminative reads dominate and hard labels confli"},"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":"2607.04987","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-06T12:25:16Z","cross_cats_sorted":["q-bio.GN","q-bio.QM"],"title_canon_sha256":"8541f11bddc803080b885cce86a4602117ac1dea962a5a53a6e97bfd79fdb8de","abstract_canon_sha256":"59b9f8dd9887e9d2c45ecd26fe7d2c532349342d82c336b5e19b0f2650210d52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:20:16.960369Z","signature_b64":"CdRb+VkTk0aVEfIW27qctBTkw2lCJZiq2RRWAZV3fq8vX0wdvjk4f0OdZM+P7chB9kd6H2noTOZsIeK3Y6RnDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8048afc6ed98d45e2c4a294d0602580dfc30760637f7455afa882390797868ed","last_reissued_at":"2026-07-07T02:20:16.959294Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:20:16.959294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-Driven Soft Labeling Scales DNA Read Classification to Whole-Body Cell-Type Deconvolution","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["q-bio.GN","q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Dmytro Rizdvanetskyi, Nathan Ross, Pavlo Lutsik","submitted_at":"2026-07-06T12:25:16Z","abstract_excerpt":"Cell-type deconvolution, the task of estimating the proportions of constituent cell types in a heterogeneous biological sample, is a core problem in computational biology. Methods that rely on epigenetic marks such as DNA methylation typically operate on aggregated methylation estimates, discarding the pattern-level information carried by individual DNA reads. Existing read-level approaches that exploit this information are scarce, and all remain restricted to few-class settings; scaling them further is an open problem because, at scale, non-discriminative reads dominate and hard labels confli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04987","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/2607.04987/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":"2607.04987","created_at":"2026-07-07T02:20:16.959451+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.04987v1","created_at":"2026-07-07T02:20:16.959451+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04987","created_at":"2026-07-07T02:20:16.959451+00:00"},{"alias_kind":"pith_short_12","alias_value":"QBEK7RXNTDKF","created_at":"2026-07-07T02:20:16.959451+00:00"},{"alias_kind":"pith_short_16","alias_value":"QBEK7RXNTDKF4LCK","created_at":"2026-07-07T02:20:16.959451+00:00"},{"alias_kind":"pith_short_8","alias_value":"QBEK7RXN","created_at":"2026-07-07T02:20:16.959451+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/QBEK7RXNTDKF4LCKFFGQMASYBX","json":"https://pith.science/pith/QBEK7RXNTDKF4LCKFFGQMASYBX.json","graph_json":"https://pith.science/api/pith-number/QBEK7RXNTDKF4LCKFFGQMASYBX/graph.json","events_json":"https://pith.science/api/pith-number/QBEK7RXNTDKF4LCKFFGQMASYBX/events.json","paper":"https://pith.science/paper/QBEK7RXN"},"agent_actions":{"view_html":"https://pith.science/pith/QBEK7RXNTDKF4LCKFFGQMASYBX","download_json":"https://pith.science/pith/QBEK7RXNTDKF4LCKFFGQMASYBX.json","view_paper":"https://pith.science/paper/QBEK7RXN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.04987&json=true","fetch_graph":"https://pith.science/api/pith-number/QBEK7RXNTDKF4LCKFFGQMASYBX/graph.json","fetch_events":"https://pith.science/api/pith-number/QBEK7RXNTDKF4LCKFFGQMASYBX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QBEK7RXNTDKF4LCKFFGQMASYBX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QBEK7RXNTDKF4LCKFFGQMASYBX/action/storage_attestation","attest_author":"https://pith.science/pith/QBEK7RXNTDKF4LCKFFGQMASYBX/action/author_attestation","sign_citation":"https://pith.science/pith/QBEK7RXNTDKF4LCKFFGQMASYBX/action/citation_signature","submit_replication":"https://pith.science/pith/QBEK7RXNTDKF4LCKFFGQMASYBX/action/replication_record"}},"created_at":"2026-07-07T02:20:16.959451+00:00","updated_at":"2026-07-07T02:20:16.959451+00:00"}