{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:OYE6ACAYALETCE3CPEHZZHB3SY","short_pith_number":"pith:OYE6ACAY","canonical_record":{"source":{"id":"1711.07104","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-19T23:33:27Z","cross_cats_sorted":[],"title_canon_sha256":"21bb569394642af4f9c5b8653e05846ef1a25c564923f9408a776f2cc662a1a1","abstract_canon_sha256":"a2c0415fc25039d7c1432e36a9f847dac642598e5b920968ef9d8e30b44a9fe8"},"schema_version":"1.0"},"canonical_sha256":"7609e0081802c9311362790f9c9c3b9603e6080cf3c328072d97be750213d95d","source":{"kind":"arxiv","id":"1711.07104","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.07104","created_at":"2026-05-18T00:29:58Z"},{"alias_kind":"arxiv_version","alias_value":"1711.07104v2","created_at":"2026-05-18T00:29:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.07104","created_at":"2026-05-18T00:29:58Z"},{"alias_kind":"pith_short_12","alias_value":"OYE6ACAYALET","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"OYE6ACAYALETCE3C","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"OYE6ACAY","created_at":"2026-05-18T12:31:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:OYE6ACAYALETCE3CPEHZZHB3SY","target":"record","payload":{"canonical_record":{"source":{"id":"1711.07104","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-19T23:33:27Z","cross_cats_sorted":[],"title_canon_sha256":"21bb569394642af4f9c5b8653e05846ef1a25c564923f9408a776f2cc662a1a1","abstract_canon_sha256":"a2c0415fc25039d7c1432e36a9f847dac642598e5b920968ef9d8e30b44a9fe8"},"schema_version":"1.0"},"canonical_sha256":"7609e0081802c9311362790f9c9c3b9603e6080cf3c328072d97be750213d95d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:58.935142Z","signature_b64":"wOFYNexBbUCz0Gaed96vksB2buyB50xMHRo05pZQ8mIhnHcxjVnWo7PvyIhCSVQXXmFjcNHCR+znDANp6OGIAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7609e0081802c9311362790f9c9c3b9603e6080cf3c328072d97be750213d95d","last_reissued_at":"2026-05-18T00:29:58.934556Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:58.934556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1711.07104","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:29:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R84w7DC2HZaaozbx30ruuCbZ2sDaOlF5aZtsQDeW6S41ZOQvtVZR5BjqR2oTTwf9QiYoUGi1AZDEeLlYCRMGAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T17:35:53.898414Z"},"content_sha256":"f473861c00fa9c30dfc57c9a127959c56191731a49ee63f7aa018f4bdce681a9","schema_version":"1.0","event_id":"sha256:f473861c00fa9c30dfc57c9a127959c56191731a49ee63f7aa018f4bdce681a9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:OYE6ACAYALETCE3CPEHZZHB3SY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Double Parametric Bootstrap Test for Topic Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Giles Hooker, Martin T. Wells, Sarah Tan, Skyler Seto","submitted_at":"2017-11-19T23:33:27Z","abstract_excerpt":"Non-negative matrix factorization (NMF) is a technique for finding latent representations of data. The method has been applied to corpora to construct topic models. However, NMF has likelihood assumptions which are often violated by real document corpora. We present a double parametric bootstrap test for evaluating the fit of an NMF-based topic model based on the duality of the KL divergence and Poisson maximum likelihood estimation. The test correctly identifies whether a topic model based on an NMF approach yields reliable results in simulated and real data."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.07104","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":""},"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":"2026-05-18T00:29:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R+ACEiQZUQogHEW0M6RofKxHjDSCM7x60Ywd94Z7vuDudV+yCn22gEutOjhb59KuTOy9XvgO5iC7W53ELBDOAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T17:35:53.898768Z"},"content_sha256":"aa4e5a52c863e798c80de7336696bb029a0575684d7be1044f1034329819a555","schema_version":"1.0","event_id":"sha256:aa4e5a52c863e798c80de7336696bb029a0575684d7be1044f1034329819a555"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OYE6ACAYALETCE3CPEHZZHB3SY/bundle.json","state_url":"https://pith.science/pith/OYE6ACAYALETCE3CPEHZZHB3SY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OYE6ACAYALETCE3CPEHZZHB3SY/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":"2026-05-19T17:35:53Z","links":{"resolver":"https://pith.science/pith/OYE6ACAYALETCE3CPEHZZHB3SY","bundle":"https://pith.science/pith/OYE6ACAYALETCE3CPEHZZHB3SY/bundle.json","state":"https://pith.science/pith/OYE6ACAYALETCE3CPEHZZHB3SY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OYE6ACAYALETCE3CPEHZZHB3SY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:OYE6ACAYALETCE3CPEHZZHB3SY","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":"a2c0415fc25039d7c1432e36a9f847dac642598e5b920968ef9d8e30b44a9fe8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-19T23:33:27Z","title_canon_sha256":"21bb569394642af4f9c5b8653e05846ef1a25c564923f9408a776f2cc662a1a1"},"schema_version":"1.0","source":{"id":"1711.07104","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.07104","created_at":"2026-05-18T00:29:58Z"},{"alias_kind":"arxiv_version","alias_value":"1711.07104v2","created_at":"2026-05-18T00:29:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.07104","created_at":"2026-05-18T00:29:58Z"},{"alias_kind":"pith_short_12","alias_value":"OYE6ACAYALET","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"OYE6ACAYALETCE3C","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"OYE6ACAY","created_at":"2026-05-18T12:31:34Z"}],"graph_snapshots":[{"event_id":"sha256:aa4e5a52c863e798c80de7336696bb029a0575684d7be1044f1034329819a555","target":"graph","created_at":"2026-05-18T00:29:58Z","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":"Non-negative matrix factorization (NMF) is a technique for finding latent representations of data. The method has been applied to corpora to construct topic models. However, NMF has likelihood assumptions which are often violated by real document corpora. We present a double parametric bootstrap test for evaluating the fit of an NMF-based topic model based on the duality of the KL divergence and Poisson maximum likelihood estimation. The test correctly identifies whether a topic model based on an NMF approach yields reliable results in simulated and real data.","authors_text":"Giles Hooker, Martin T. Wells, Sarah Tan, Skyler Seto","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-19T23:33:27Z","title":"A Double Parametric Bootstrap Test for Topic Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.07104","kind":"arxiv","version":2},"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:f473861c00fa9c30dfc57c9a127959c56191731a49ee63f7aa018f4bdce681a9","target":"record","created_at":"2026-05-18T00:29:58Z","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":"a2c0415fc25039d7c1432e36a9f847dac642598e5b920968ef9d8e30b44a9fe8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-19T23:33:27Z","title_canon_sha256":"21bb569394642af4f9c5b8653e05846ef1a25c564923f9408a776f2cc662a1a1"},"schema_version":"1.0","source":{"id":"1711.07104","kind":"arxiv","version":2}},"canonical_sha256":"7609e0081802c9311362790f9c9c3b9603e6080cf3c328072d97be750213d95d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7609e0081802c9311362790f9c9c3b9603e6080cf3c328072d97be750213d95d","first_computed_at":"2026-05-18T00:29:58.934556Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:29:58.934556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wOFYNexBbUCz0Gaed96vksB2buyB50xMHRo05pZQ8mIhnHcxjVnWo7PvyIhCSVQXXmFjcNHCR+znDANp6OGIAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:29:58.935142Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.07104","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f473861c00fa9c30dfc57c9a127959c56191731a49ee63f7aa018f4bdce681a9","sha256:aa4e5a52c863e798c80de7336696bb029a0575684d7be1044f1034329819a555"],"state_sha256":"0cab1197a1fa5616e2ab6ec2e77a24591ee64474af6c05b4b5f24534881a5b4e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M9ZvVPC56kjSGLK00fJexIOwLV68NDT+maoft3H1cSDwRq5iXLAGjn9wdClla6ud73rsNcqI5nWKDUg9oRqMBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T17:35:53.919456Z","bundle_sha256":"64b09ed466579c28577872f06ca55377236b794e2389430b01475529bca0ea00"}}