{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:IL7RPA3BB7QDCC2YLPN52BBPHS","short_pith_number":"pith:IL7RPA3B","schema_version":"1.0","canonical_sha256":"42ff1783610fe0310b585bdbdd042f3c90aeb9df5b10e682505363cdb231cf25","source":{"kind":"arxiv","id":"2109.05541","version":2},"attestation_state":"computed","paper":{"title":"Multiscale Analysis of Count Data through Topic Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.CO"],"primary_cat":"stat.AP","authors_text":"Julia Fukuyama, Kris Sankaran, Laura Symul","submitted_at":"2021-09-12T15:49:37Z","abstract_excerpt":"Topic modeling is a popular method used to describe biological count data. With topic models, the user must specify the number of topics $K$. Since there is no definitive way to choose $K$ and since a true value might not exist, we develop techniques to study the relationships across models with different $K$. This can show how many topics are consistently present across different models, if a topic is only transiently present, or if a topic splits in two when $K$ increases. This strategy gives more insight into the process generating the data than choosing a single value of $K$ would.\n  We de"},"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":"2109.05541","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.AP","submitted_at":"2021-09-12T15:49:37Z","cross_cats_sorted":["stat.CO"],"title_canon_sha256":"c47bd644d5e1ec92b40decc012091f75f81a9ac843812377b9c672d7d97a82f4","abstract_canon_sha256":"1145543b29ef034b4f06da902d0c67fd948ff08aff7d9488113cf9ba6f003a4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:03:12.755239Z","signature_b64":"62oTEkBDvwNV796UzHaB5u06mAArWq48pu0B4MlLiwyd7x1s8e8BkJPqjyH/I+/uMN9Pq8RMMebYAvU9r7TgAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42ff1783610fe0310b585bdbdd042f3c90aeb9df5b10e682505363cdb231cf25","last_reissued_at":"2026-07-05T04:03:12.754400Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:03:12.754400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multiscale Analysis of Count Data through Topic Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.CO"],"primary_cat":"stat.AP","authors_text":"Julia Fukuyama, Kris Sankaran, Laura Symul","submitted_at":"2021-09-12T15:49:37Z","abstract_excerpt":"Topic modeling is a popular method used to describe biological count data. With topic models, the user must specify the number of topics $K$. Since there is no definitive way to choose $K$ and since a true value might not exist, we develop techniques to study the relationships across models with different $K$. This can show how many topics are consistently present across different models, if a topic is only transiently present, or if a topic splits in two when $K$ increases. This strategy gives more insight into the process generating the data than choosing a single value of $K$ would.\n  We de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.05541","kind":"arxiv","version":2},"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/2109.05541/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":"2109.05541","created_at":"2026-07-05T04:03:12.754556+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.05541v2","created_at":"2026-07-05T04:03:12.754556+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.05541","created_at":"2026-07-05T04:03:12.754556+00:00"},{"alias_kind":"pith_short_12","alias_value":"IL7RPA3BB7QD","created_at":"2026-07-05T04:03:12.754556+00:00"},{"alias_kind":"pith_short_16","alias_value":"IL7RPA3BB7QDCC2Y","created_at":"2026-07-05T04:03:12.754556+00:00"},{"alias_kind":"pith_short_8","alias_value":"IL7RPA3B","created_at":"2026-07-05T04:03:12.754556+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.00535","citing_title":"Tensor Topic Modeling Via HOSVD","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IL7RPA3BB7QDCC2YLPN52BBPHS","json":"https://pith.science/pith/IL7RPA3BB7QDCC2YLPN52BBPHS.json","graph_json":"https://pith.science/api/pith-number/IL7RPA3BB7QDCC2YLPN52BBPHS/graph.json","events_json":"https://pith.science/api/pith-number/IL7RPA3BB7QDCC2YLPN52BBPHS/events.json","paper":"https://pith.science/paper/IL7RPA3B"},"agent_actions":{"view_html":"https://pith.science/pith/IL7RPA3BB7QDCC2YLPN52BBPHS","download_json":"https://pith.science/pith/IL7RPA3BB7QDCC2YLPN52BBPHS.json","view_paper":"https://pith.science/paper/IL7RPA3B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.05541&json=true","fetch_graph":"https://pith.science/api/pith-number/IL7RPA3BB7QDCC2YLPN52BBPHS/graph.json","fetch_events":"https://pith.science/api/pith-number/IL7RPA3BB7QDCC2YLPN52BBPHS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IL7RPA3BB7QDCC2YLPN52BBPHS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IL7RPA3BB7QDCC2YLPN52BBPHS/action/storage_attestation","attest_author":"https://pith.science/pith/IL7RPA3BB7QDCC2YLPN52BBPHS/action/author_attestation","sign_citation":"https://pith.science/pith/IL7RPA3BB7QDCC2YLPN52BBPHS/action/citation_signature","submit_replication":"https://pith.science/pith/IL7RPA3BB7QDCC2YLPN52BBPHS/action/replication_record"}},"created_at":"2026-07-05T04:03:12.754556+00:00","updated_at":"2026-07-05T04:03:12.754556+00:00"}