{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:X4CW7TJJFL7YIVPA6V4PM4KGSB","short_pith_number":"pith:X4CW7TJJ","canonical_record":{"source":{"id":"1709.02294","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2017-09-07T14:59:50Z","cross_cats_sorted":["stat.TH"],"title_canon_sha256":"7e4707282af70a06be229022ed1902e98d9a694a7d1390f8ebdca13639e7a70e","abstract_canon_sha256":"4f2cf4193a8b05fa94de8f2820d971a6e171914f737e3b18e069dc9978d6c784"},"schema_version":"1.0"},"canonical_sha256":"bf056fcd292aff8455e0f578f67146907adfa6949a3bd9e113472917e88a48e9","source":{"kind":"arxiv","id":"1709.02294","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.02294","created_at":"2026-05-18T00:35:49Z"},{"alias_kind":"arxiv_version","alias_value":"1709.02294v1","created_at":"2026-05-18T00:35:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.02294","created_at":"2026-05-18T00:35:49Z"},{"alias_kind":"pith_short_12","alias_value":"X4CW7TJJFL7Y","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"X4CW7TJJFL7YIVPA","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"X4CW7TJJ","created_at":"2026-05-18T12:31:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:X4CW7TJJFL7YIVPA6V4PM4KGSB","target":"record","payload":{"canonical_record":{"source":{"id":"1709.02294","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2017-09-07T14:59:50Z","cross_cats_sorted":["stat.TH"],"title_canon_sha256":"7e4707282af70a06be229022ed1902e98d9a694a7d1390f8ebdca13639e7a70e","abstract_canon_sha256":"4f2cf4193a8b05fa94de8f2820d971a6e171914f737e3b18e069dc9978d6c784"},"schema_version":"1.0"},"canonical_sha256":"bf056fcd292aff8455e0f578f67146907adfa6949a3bd9e113472917e88a48e9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:49.549201Z","signature_b64":"b1uapexCoRV6m+J8UUspPMh6SsRSV4iup802Nd/Sr+yIBNhTFQT3Qvjr799vFeXDmPXxAFfNtlbtMEICkWZwCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf056fcd292aff8455e0f578f67146907adfa6949a3bd9e113472917e88a48e9","last_reissued_at":"2026-05-18T00:35:49.548484Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:49.548484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.02294","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:35:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CKsK6+a37FDmLWw9vh64KFqp1IhfbY+4CbSJi6NXVxUe0kY9wvWfSfna+KWlB/Yc/V87WZB/3fWRwRy2CLOVAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T05:53:20.719888Z"},"content_sha256":"694aeb99a9cf28604f5c32b528f20efffb4f082642116d15e0c90d2ea56c5046","schema_version":"1.0","event_id":"sha256:694aeb99a9cf28604f5c32b528f20efffb4f082642116d15e0c90d2ea56c5046"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:X4CW7TJJFL7YIVPA6V4PM4KGSB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Clustering and Model Selection via Penalized Likelihood for Different-sized Categorical Data Vectors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Erwan Le Pennec (CMAP, Esther Derman (CMAP), XPOP)","submitted_at":"2017-09-07T14:59:50Z","abstract_excerpt":"In this study, we consider unsupervised clustering of categorical vectors that can be of different size using mixture. We use likelihood maximization to estimate the parameters of the underlying mixture model and a penalization technique to select the number of mixture components. Regardless of the true distribution that generated the data, we show that an explicit penalty, known up to a multiplicative constant, leads to a non-asymptotic oracle inequality with the Kullback-Leibler divergence on the two sides of the inequality. This theoretical result is illustrated by a document clustering app"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.02294","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:35:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xnJQbHesHhJzwkuNc/Ah/5aqb/hCRwU8pqWYn9+cqGcqEIicljkSn02B19ZZFrHu1MBovuxgW4QojmdQEoutBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T05:53:20.720230Z"},"content_sha256":"09154ee95f3bdbbfd55aed55c800962a99e29ee87a922af8f6d77b8fe860706a","schema_version":"1.0","event_id":"sha256:09154ee95f3bdbbfd55aed55c800962a99e29ee87a922af8f6d77b8fe860706a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X4CW7TJJFL7YIVPA6V4PM4KGSB/bundle.json","state_url":"https://pith.science/pith/X4CW7TJJFL7YIVPA6V4PM4KGSB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X4CW7TJJFL7YIVPA6V4PM4KGSB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-01T05:53:20Z","links":{"resolver":"https://pith.science/pith/X4CW7TJJFL7YIVPA6V4PM4KGSB","bundle":"https://pith.science/pith/X4CW7TJJFL7YIVPA6V4PM4KGSB/bundle.json","state":"https://pith.science/pith/X4CW7TJJFL7YIVPA6V4PM4KGSB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X4CW7TJJFL7YIVPA6V4PM4KGSB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:X4CW7TJJFL7YIVPA6V4PM4KGSB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4f2cf4193a8b05fa94de8f2820d971a6e171914f737e3b18e069dc9978d6c784","cross_cats_sorted":["stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2017-09-07T14:59:50Z","title_canon_sha256":"7e4707282af70a06be229022ed1902e98d9a694a7d1390f8ebdca13639e7a70e"},"schema_version":"1.0","source":{"id":"1709.02294","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.02294","created_at":"2026-05-18T00:35:49Z"},{"alias_kind":"arxiv_version","alias_value":"1709.02294v1","created_at":"2026-05-18T00:35:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.02294","created_at":"2026-05-18T00:35:49Z"},{"alias_kind":"pith_short_12","alias_value":"X4CW7TJJFL7Y","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"X4CW7TJJFL7YIVPA","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"X4CW7TJJ","created_at":"2026-05-18T12:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:09154ee95f3bdbbfd55aed55c800962a99e29ee87a922af8f6d77b8fe860706a","target":"graph","created_at":"2026-05-18T00:35:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"In this study, we consider unsupervised clustering of categorical vectors that can be of different size using mixture. We use likelihood maximization to estimate the parameters of the underlying mixture model and a penalization technique to select the number of mixture components. Regardless of the true distribution that generated the data, we show that an explicit penalty, known up to a multiplicative constant, leads to a non-asymptotic oracle inequality with the Kullback-Leibler divergence on the two sides of the inequality. This theoretical result is illustrated by a document clustering app","authors_text":"Erwan Le Pennec (CMAP, Esther Derman (CMAP), XPOP)","cross_cats":["stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2017-09-07T14:59:50Z","title":"Clustering and Model Selection via Penalized Likelihood for Different-sized Categorical Data Vectors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.02294","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:694aeb99a9cf28604f5c32b528f20efffb4f082642116d15e0c90d2ea56c5046","target":"record","created_at":"2026-05-18T00:35:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4f2cf4193a8b05fa94de8f2820d971a6e171914f737e3b18e069dc9978d6c784","cross_cats_sorted":["stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2017-09-07T14:59:50Z","title_canon_sha256":"7e4707282af70a06be229022ed1902e98d9a694a7d1390f8ebdca13639e7a70e"},"schema_version":"1.0","source":{"id":"1709.02294","kind":"arxiv","version":1}},"canonical_sha256":"bf056fcd292aff8455e0f578f67146907adfa6949a3bd9e113472917e88a48e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf056fcd292aff8455e0f578f67146907adfa6949a3bd9e113472917e88a48e9","first_computed_at":"2026-05-18T00:35:49.548484Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:35:49.548484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b1uapexCoRV6m+J8UUspPMh6SsRSV4iup802Nd/Sr+yIBNhTFQT3Qvjr799vFeXDmPXxAFfNtlbtMEICkWZwCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:35:49.549201Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.02294","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:694aeb99a9cf28604f5c32b528f20efffb4f082642116d15e0c90d2ea56c5046","sha256:09154ee95f3bdbbfd55aed55c800962a99e29ee87a922af8f6d77b8fe860706a"],"state_sha256":"45312acbfaf8ebcf2aac477abe2141a942e502f2f75d2983b307bb60df5d606f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vS9zYMUCZ2bH21cEwH7/jLB3MRGyXMpQV3U5e5zs+ly3JSvnBPUofg1eD3yhVOzCbMI4wMx9QtMqf8ifGty+Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T05:53:20.722242Z","bundle_sha256":"3bdfad3ec280764cbbe9e0593a4b8e1541f3ac3f81fda2c2f6a25c8242867373"}}