{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:KFUS35FQDSZNWQVKXQGALXT4TG","short_pith_number":"pith:KFUS35FQ","canonical_record":{"source":{"id":"1808.08098","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-24T11:37:40Z","cross_cats_sorted":[],"title_canon_sha256":"e67a3e4bc6f1bd2910054a81e01ed9b09cde658672cc29939a21106769b98f7a","abstract_canon_sha256":"d73df10d65e64334810cb4daae4036b8ea53dd6b99962a396e5ee2025b36c845"},"schema_version":"1.0"},"canonical_sha256":"51692df4b01cb2db42aabc0c05de7c9980ef02bf00e2f2cda1a612c8a457ccf0","source":{"kind":"arxiv","id":"1808.08098","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.08098","created_at":"2026-05-18T00:06:44Z"},{"alias_kind":"arxiv_version","alias_value":"1808.08098v1","created_at":"2026-05-18T00:06:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.08098","created_at":"2026-05-18T00:06:44Z"},{"alias_kind":"pith_short_12","alias_value":"KFUS35FQDSZN","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"KFUS35FQDSZNWQVK","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"KFUS35FQ","created_at":"2026-05-18T12:32:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:KFUS35FQDSZNWQVKXQGALXT4TG","target":"record","payload":{"canonical_record":{"source":{"id":"1808.08098","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-24T11:37:40Z","cross_cats_sorted":[],"title_canon_sha256":"e67a3e4bc6f1bd2910054a81e01ed9b09cde658672cc29939a21106769b98f7a","abstract_canon_sha256":"d73df10d65e64334810cb4daae4036b8ea53dd6b99962a396e5ee2025b36c845"},"schema_version":"1.0"},"canonical_sha256":"51692df4b01cb2db42aabc0c05de7c9980ef02bf00e2f2cda1a612c8a457ccf0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:44.428127Z","signature_b64":"CpsZZiDLUekK6KKongrZs1FJcV/MQ6ooOpcDr/E73/SKcEfR2ZwmyeNbCQd+hZrZwDKAhdAyr7zJIjlNGwbCAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51692df4b01cb2db42aabc0c05de7c9980ef02bf00e2f2cda1a612c8a457ccf0","last_reissued_at":"2026-05-18T00:06:44.427734Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:44.427734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.08098","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":"2026-05-18T00:06:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SFNAvQv6DMmmtNvvNh/cfSR9JxNJLKHpHO9dnbbF/dz5XuDCOg7GcN5mlCN5KpYC2i7ynCuGQUFajD44rnByAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T14:22:27.078982Z"},"content_sha256":"f45b4120633ba5860a3ce69adde6846205b864efb4fc0449b1554774093ed716","schema_version":"1.0","event_id":"sha256:f45b4120633ba5860a3ce69adde6846205b864efb4fc0449b1554774093ed716"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:KFUS35FQDSZNWQVKXQGALXT4TG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Measuring LDA Topic Stability from Clusters of Replicated Runs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ma\\\"elick Claes, Mika M\\\"antyl\\\"a, Umar Farooq","submitted_at":"2018-08-24T11:37:40Z","abstract_excerpt":"Background: Unstructured and textual data is increasing rapidly and Latent Dirichlet Allocation (LDA) topic modeling is a popular data analysis methods for it. Past work suggests that instability of LDA topics may lead to systematic errors. Aim: We propose a method that relies on replicated LDA runs, clustering, and providing a stability metric for the topics. Method: We generate k LDA topics and replicate this process n times resulting in n*k topics. Then we use K-medioids to cluster the n*k topics to k clusters. The k clusters now represent the original LDA topics and we present them like no"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.08098","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":"2026-05-18T00:06:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HR0Yxou7bUHH72P2ELZol/JJhyIjxf4blQg61IbarbTYsPfEtId3Bts1QzSoMIcL6MWZ+b6rmaGVKxgLfgt+CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T14:22:27.079358Z"},"content_sha256":"024f8f56721dee64ed3e4bf7fa2bd070f4eb4facd8c848c054f8f7acd2d6000f","schema_version":"1.0","event_id":"sha256:024f8f56721dee64ed3e4bf7fa2bd070f4eb4facd8c848c054f8f7acd2d6000f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KFUS35FQDSZNWQVKXQGALXT4TG/bundle.json","state_url":"https://pith.science/pith/KFUS35FQDSZNWQVKXQGALXT4TG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KFUS35FQDSZNWQVKXQGALXT4TG/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":"2026-05-21T14:22:27Z","links":{"resolver":"https://pith.science/pith/KFUS35FQDSZNWQVKXQGALXT4TG","bundle":"https://pith.science/pith/KFUS35FQDSZNWQVKXQGALXT4TG/bundle.json","state":"https://pith.science/pith/KFUS35FQDSZNWQVKXQGALXT4TG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KFUS35FQDSZNWQVKXQGALXT4TG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:KFUS35FQDSZNWQVKXQGALXT4TG","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":"d73df10d65e64334810cb4daae4036b8ea53dd6b99962a396e5ee2025b36c845","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-24T11:37:40Z","title_canon_sha256":"e67a3e4bc6f1bd2910054a81e01ed9b09cde658672cc29939a21106769b98f7a"},"schema_version":"1.0","source":{"id":"1808.08098","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.08098","created_at":"2026-05-18T00:06:44Z"},{"alias_kind":"arxiv_version","alias_value":"1808.08098v1","created_at":"2026-05-18T00:06:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.08098","created_at":"2026-05-18T00:06:44Z"},{"alias_kind":"pith_short_12","alias_value":"KFUS35FQDSZN","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"KFUS35FQDSZNWQVK","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"KFUS35FQ","created_at":"2026-05-18T12:32:33Z"}],"graph_snapshots":[{"event_id":"sha256:024f8f56721dee64ed3e4bf7fa2bd070f4eb4facd8c848c054f8f7acd2d6000f","target":"graph","created_at":"2026-05-18T00:06:44Z","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":"Background: Unstructured and textual data is increasing rapidly and Latent Dirichlet Allocation (LDA) topic modeling is a popular data analysis methods for it. Past work suggests that instability of LDA topics may lead to systematic errors. Aim: We propose a method that relies on replicated LDA runs, clustering, and providing a stability metric for the topics. Method: We generate k LDA topics and replicate this process n times resulting in n*k topics. Then we use K-medioids to cluster the n*k topics to k clusters. The k clusters now represent the original LDA topics and we present them like no","authors_text":"Ma\\\"elick Claes, Mika M\\\"antyl\\\"a, Umar Farooq","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-24T11:37:40Z","title":"Measuring LDA Topic Stability from Clusters of Replicated Runs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.08098","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:f45b4120633ba5860a3ce69adde6846205b864efb4fc0449b1554774093ed716","target":"record","created_at":"2026-05-18T00:06:44Z","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":"d73df10d65e64334810cb4daae4036b8ea53dd6b99962a396e5ee2025b36c845","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-24T11:37:40Z","title_canon_sha256":"e67a3e4bc6f1bd2910054a81e01ed9b09cde658672cc29939a21106769b98f7a"},"schema_version":"1.0","source":{"id":"1808.08098","kind":"arxiv","version":1}},"canonical_sha256":"51692df4b01cb2db42aabc0c05de7c9980ef02bf00e2f2cda1a612c8a457ccf0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"51692df4b01cb2db42aabc0c05de7c9980ef02bf00e2f2cda1a612c8a457ccf0","first_computed_at":"2026-05-18T00:06:44.427734Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:06:44.427734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CpsZZiDLUekK6KKongrZs1FJcV/MQ6ooOpcDr/E73/SKcEfR2ZwmyeNbCQd+hZrZwDKAhdAyr7zJIjlNGwbCAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:06:44.428127Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.08098","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f45b4120633ba5860a3ce69adde6846205b864efb4fc0449b1554774093ed716","sha256:024f8f56721dee64ed3e4bf7fa2bd070f4eb4facd8c848c054f8f7acd2d6000f"],"state_sha256":"e6380688e3701685ec3f2d964d54976c161474a690d3ee6d774db6b60bfda955"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nu67PRREsS4491cTFm7yo9HWGXIkO5zCmQ++qlTMSXuh1+R5YsMdiLpY4SNlfiBi0F6vuaZ/Dv4Fgfd5rOPODA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T14:22:27.081763Z","bundle_sha256":"e031d5ea544dab54e11fae8cf47b4609d929222119db5401258a8cf49c5dcfb5"}}