{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:EE2HUEGHN6KCMBLHUHCWXEZNRT","short_pith_number":"pith:EE2HUEGH","canonical_record":{"source":{"id":"2003.04980","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-14T07:10:18Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"f157ed1022be3e1418f26ae7dd40ebed9a1d0247d151a590f6e97dac3fa48a1f","abstract_canon_sha256":"627b2a22176754dff6ae2b454dfb2b2beca250550b36b36e61e729161643b6b8"},"schema_version":"1.0"},"canonical_sha256":"21347a10c76f94260567a1c56b932d8cebb9e649b421eea2b8fecc8c65bd3fec","source":{"kind":"arxiv","id":"2003.04980","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.04980","created_at":"2026-07-05T00:52:07Z"},{"alias_kind":"arxiv_version","alias_value":"2003.04980v1","created_at":"2026-07-05T00:52:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.04980","created_at":"2026-07-05T00:52:07Z"},{"alias_kind":"pith_short_12","alias_value":"EE2HUEGHN6KC","created_at":"2026-07-05T00:52:07Z"},{"alias_kind":"pith_short_16","alias_value":"EE2HUEGHN6KCMBLH","created_at":"2026-07-05T00:52:07Z"},{"alias_kind":"pith_short_8","alias_value":"EE2HUEGH","created_at":"2026-07-05T00:52:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:EE2HUEGHN6KCMBLHUHCWXEZNRT","target":"record","payload":{"canonical_record":{"source":{"id":"2003.04980","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-14T07:10:18Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"f157ed1022be3e1418f26ae7dd40ebed9a1d0247d151a590f6e97dac3fa48a1f","abstract_canon_sha256":"627b2a22176754dff6ae2b454dfb2b2beca250550b36b36e61e729161643b6b8"},"schema_version":"1.0"},"canonical_sha256":"21347a10c76f94260567a1c56b932d8cebb9e649b421eea2b8fecc8c65bd3fec","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:52:07.531035Z","signature_b64":"FJgrcVzKOdRTlwod4iptj0wL//xdS9vQtcGQPv7tp5IJpdj0xJtTsqzpdVI6wRlluyLI92bnEDB3tCxE9k0LAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21347a10c76f94260567a1c56b932d8cebb9e649b421eea2b8fecc8c65bd3fec","last_reissued_at":"2026-07-05T00:52:07.530616Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:52:07.530616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.04980","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":"2026-07-05T00:52:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RgnTTBAeDvVOMtGHNy4KKqrDUFYkqY/KOI3PJVhxg2aoGYVH37L1VFj1QIsGUaZYi8vJH5bpr4IzeYc5E92BCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:30:53.774268Z"},"content_sha256":"b07a283716848fd55c1148b1d09d8218f4ba08b3137f1dc0549ae2f4ec7e9652","schema_version":"1.0","event_id":"sha256:b07a283716848fd55c1148b1d09d8218f4ba08b3137f1dc0549ae2f4ec7e9652"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:EE2HUEGHN6KCMBLHUHCWXEZNRT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Reliability of Latent Dirichlet Allocation by Assessing Its Stability Using Clustering Techniques on Replicated Runs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Carsten Jentsch, Jonas Rieger, J\\\"org Rahnenf\\\"uhrer, Lars Koppers","submitted_at":"2020-02-14T07:10:18Z","abstract_excerpt":"For organizing large text corpora topic modeling provides useful tools. A widely used method is Latent Dirichlet Allocation (LDA), a generative probabilistic model which models single texts in a collection of texts as mixtures of latent topics. The assignments of words to topics rely on initial values such that generally the outcome of LDA is not fully reproducible. In addition, the reassignment via Gibbs Sampling is based on conditional distributions, leading to different results in replicated runs on the same text data. This fact is often neglected in everyday practice. We aim to improve the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.04980","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2003.04980/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:52:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PzmD2Hqse6lIx6ZO+Su6hDHO/jGxLFOP4Ri5PtNVubWFk2GAkY4dABzJDzMhkm7tWhVAPQEHVUnIkds/PiHHDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:30:53.774661Z"},"content_sha256":"598138362e64be31ce54ccf6dc539e717ebb75b628e951558df4690cc70bb193","schema_version":"1.0","event_id":"sha256:598138362e64be31ce54ccf6dc539e717ebb75b628e951558df4690cc70bb193"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EE2HUEGHN6KCMBLHUHCWXEZNRT/bundle.json","state_url":"https://pith.science/pith/EE2HUEGHN6KCMBLHUHCWXEZNRT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EE2HUEGHN6KCMBLHUHCWXEZNRT/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":"2026-07-07T10:30:53Z","links":{"resolver":"https://pith.science/pith/EE2HUEGHN6KCMBLHUHCWXEZNRT","bundle":"https://pith.science/pith/EE2HUEGHN6KCMBLHUHCWXEZNRT/bundle.json","state":"https://pith.science/pith/EE2HUEGHN6KCMBLHUHCWXEZNRT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EE2HUEGHN6KCMBLHUHCWXEZNRT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:EE2HUEGHN6KCMBLHUHCWXEZNRT","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":"627b2a22176754dff6ae2b454dfb2b2beca250550b36b36e61e729161643b6b8","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-14T07:10:18Z","title_canon_sha256":"f157ed1022be3e1418f26ae7dd40ebed9a1d0247d151a590f6e97dac3fa48a1f"},"schema_version":"1.0","source":{"id":"2003.04980","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.04980","created_at":"2026-07-05T00:52:07Z"},{"alias_kind":"arxiv_version","alias_value":"2003.04980v1","created_at":"2026-07-05T00:52:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.04980","created_at":"2026-07-05T00:52:07Z"},{"alias_kind":"pith_short_12","alias_value":"EE2HUEGHN6KC","created_at":"2026-07-05T00:52:07Z"},{"alias_kind":"pith_short_16","alias_value":"EE2HUEGHN6KCMBLH","created_at":"2026-07-05T00:52:07Z"},{"alias_kind":"pith_short_8","alias_value":"EE2HUEGH","created_at":"2026-07-05T00:52:07Z"}],"graph_snapshots":[{"event_id":"sha256:598138362e64be31ce54ccf6dc539e717ebb75b628e951558df4690cc70bb193","target":"graph","created_at":"2026-07-05T00:52:07Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2003.04980/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"For organizing large text corpora topic modeling provides useful tools. A widely used method is Latent Dirichlet Allocation (LDA), a generative probabilistic model which models single texts in a collection of texts as mixtures of latent topics. The assignments of words to topics rely on initial values such that generally the outcome of LDA is not fully reproducible. In addition, the reassignment via Gibbs Sampling is based on conditional distributions, leading to different results in replicated runs on the same text data. This fact is often neglected in everyday practice. We aim to improve the","authors_text":"Carsten Jentsch, Jonas Rieger, J\\\"org Rahnenf\\\"uhrer, Lars Koppers","cross_cats":["cs.AI","cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-14T07:10:18Z","title":"Improving Reliability of Latent Dirichlet Allocation by Assessing Its Stability Using Clustering Techniques on Replicated Runs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.04980","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:b07a283716848fd55c1148b1d09d8218f4ba08b3137f1dc0549ae2f4ec7e9652","target":"record","created_at":"2026-07-05T00:52:07Z","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":"627b2a22176754dff6ae2b454dfb2b2beca250550b36b36e61e729161643b6b8","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-14T07:10:18Z","title_canon_sha256":"f157ed1022be3e1418f26ae7dd40ebed9a1d0247d151a590f6e97dac3fa48a1f"},"schema_version":"1.0","source":{"id":"2003.04980","kind":"arxiv","version":1}},"canonical_sha256":"21347a10c76f94260567a1c56b932d8cebb9e649b421eea2b8fecc8c65bd3fec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"21347a10c76f94260567a1c56b932d8cebb9e649b421eea2b8fecc8c65bd3fec","first_computed_at":"2026-07-05T00:52:07.530616Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:52:07.530616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FJgrcVzKOdRTlwod4iptj0wL//xdS9vQtcGQPv7tp5IJpdj0xJtTsqzpdVI6wRlluyLI92bnEDB3tCxE9k0LAg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:52:07.531035Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.04980","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b07a283716848fd55c1148b1d09d8218f4ba08b3137f1dc0549ae2f4ec7e9652","sha256:598138362e64be31ce54ccf6dc539e717ebb75b628e951558df4690cc70bb193"],"state_sha256":"ee079e5d402ba439643e39c04844f2460f2c5eb16e1e98d7ca3890920bc54061"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qi+IJ65u6MxwJAS6fp+Jli9QTgxcMpkJZxjflL9jxFcV5ifCxEnxvMBJWJ55bD2MYapaZawxpgbBMjLmUJmjAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T10:30:53.776591Z","bundle_sha256":"40f30f0fc141e3d7ce31736439df7b4e3b0195d2f258383140bc2a471cfd50da"}}