{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IBTIWICWHORHUYCMNGTCPGEDLR","short_pith_number":"pith:IBTIWICW","schema_version":"1.0","canonical_sha256":"40668b20563ba27a604c69a62798835c7e008641723170b3b17dd436d11dc46b","source":{"kind":"arxiv","id":"2203.01629","version":5},"attestation_state":"computed","paper":{"title":"Learning Group Importance using the Differentiable Hypergeometric Distribution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.CO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alain Ryser, Julia E. Vogt, Laura Manduchi, Thomas M. Sutter","submitted_at":"2022-03-03T10:44:50Z","abstract_excerpt":"Partitioning a set of elements into subsets of a priori unknown sizes is essential in many applications. These subset sizes are rarely explicitly learned - be it the cluster sizes in clustering applications or the number of shared versus independent generative latent factors in weakly-supervised learning. Probability distributions over correct combinations of subset sizes are non-differentiable due to hard constraints, which prohibit gradient-based optimization. In this work, we propose the differentiable hypergeometric distribution. The hypergeometric distribution models the probability of di"},"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":"2203.01629","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-03T10:44:50Z","cross_cats_sorted":["stat.CO","stat.ML"],"title_canon_sha256":"ac78599ba17c7e2a16c78b3c218907c1483efdd2e0865d138924f110e88b0168","abstract_canon_sha256":"4c40b66c3b858dfc446f72f8a3764eff337c69486bf60a9949d261e7268def1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:23:36.624145Z","signature_b64":"lPR5U5ZLBsMvFA/4I7nEzd3N+ZI0xbjhgB2Bqeemc8DPdU7OoWO/HFjoi+5nP/zF3wHAgsaA6JKcX0qOT6NJAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40668b20563ba27a604c69a62798835c7e008641723170b3b17dd436d11dc46b","last_reissued_at":"2026-07-05T06:23:36.623706Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:23:36.623706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Group Importance using the Differentiable Hypergeometric Distribution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.CO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alain Ryser, Julia E. Vogt, Laura Manduchi, Thomas M. Sutter","submitted_at":"2022-03-03T10:44:50Z","abstract_excerpt":"Partitioning a set of elements into subsets of a priori unknown sizes is essential in many applications. These subset sizes are rarely explicitly learned - be it the cluster sizes in clustering applications or the number of shared versus independent generative latent factors in weakly-supervised learning. Probability distributions over correct combinations of subset sizes are non-differentiable due to hard constraints, which prohibit gradient-based optimization. In this work, we propose the differentiable hypergeometric distribution. The hypergeometric distribution models the probability of di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.01629","kind":"arxiv","version":5},"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/2203.01629/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":"2203.01629","created_at":"2026-07-05T06:23:36.623763+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.01629v5","created_at":"2026-07-05T06:23:36.623763+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.01629","created_at":"2026-07-05T06:23:36.623763+00:00"},{"alias_kind":"pith_short_12","alias_value":"IBTIWICWHORH","created_at":"2026-07-05T06:23:36.623763+00:00"},{"alias_kind":"pith_short_16","alias_value":"IBTIWICWHORHUYCM","created_at":"2026-07-05T06:23:36.623763+00:00"},{"alias_kind":"pith_short_8","alias_value":"IBTIWICW","created_at":"2026-07-05T06:23:36.623763+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/IBTIWICWHORHUYCMNGTCPGEDLR","json":"https://pith.science/pith/IBTIWICWHORHUYCMNGTCPGEDLR.json","graph_json":"https://pith.science/api/pith-number/IBTIWICWHORHUYCMNGTCPGEDLR/graph.json","events_json":"https://pith.science/api/pith-number/IBTIWICWHORHUYCMNGTCPGEDLR/events.json","paper":"https://pith.science/paper/IBTIWICW"},"agent_actions":{"view_html":"https://pith.science/pith/IBTIWICWHORHUYCMNGTCPGEDLR","download_json":"https://pith.science/pith/IBTIWICWHORHUYCMNGTCPGEDLR.json","view_paper":"https://pith.science/paper/IBTIWICW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.01629&json=true","fetch_graph":"https://pith.science/api/pith-number/IBTIWICWHORHUYCMNGTCPGEDLR/graph.json","fetch_events":"https://pith.science/api/pith-number/IBTIWICWHORHUYCMNGTCPGEDLR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IBTIWICWHORHUYCMNGTCPGEDLR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IBTIWICWHORHUYCMNGTCPGEDLR/action/storage_attestation","attest_author":"https://pith.science/pith/IBTIWICWHORHUYCMNGTCPGEDLR/action/author_attestation","sign_citation":"https://pith.science/pith/IBTIWICWHORHUYCMNGTCPGEDLR/action/citation_signature","submit_replication":"https://pith.science/pith/IBTIWICWHORHUYCMNGTCPGEDLR/action/replication_record"}},"created_at":"2026-07-05T06:23:36.623763+00:00","updated_at":"2026-07-05T06:23:36.623763+00:00"}