{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3MIL2FNSWXUAYKKEMWKQM5Y5ZK","short_pith_number":"pith:3MIL2FNS","canonical_record":{"source":{"id":"2410.23186","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-30T16:42:04Z","cross_cats_sorted":[],"title_canon_sha256":"f5be2b8e948761bf83248cb7d4bac845e6a640300527418178e8f62eab0b8dbf","abstract_canon_sha256":"ab8c3a9bff769ace06d52d39f1151f145612509cb466cd63e9d0e2af02aa4f50"},"schema_version":"1.0"},"canonical_sha256":"db10bd15b2b5e80c2944659506771dcaacb3d0bc29d5534c9ad0ea54ef3f5538","source":{"kind":"arxiv","id":"2410.23186","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.23186","created_at":"2026-07-05T09:49:12Z"},{"alias_kind":"arxiv_version","alias_value":"2410.23186v2","created_at":"2026-07-05T09:49:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23186","created_at":"2026-07-05T09:49:12Z"},{"alias_kind":"pith_short_12","alias_value":"3MIL2FNSWXUA","created_at":"2026-07-05T09:49:12Z"},{"alias_kind":"pith_short_16","alias_value":"3MIL2FNSWXUAYKKE","created_at":"2026-07-05T09:49:12Z"},{"alias_kind":"pith_short_8","alias_value":"3MIL2FNS","created_at":"2026-07-05T09:49:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3MIL2FNSWXUAYKKEMWKQM5Y5ZK","target":"record","payload":{"canonical_record":{"source":{"id":"2410.23186","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-30T16:42:04Z","cross_cats_sorted":[],"title_canon_sha256":"f5be2b8e948761bf83248cb7d4bac845e6a640300527418178e8f62eab0b8dbf","abstract_canon_sha256":"ab8c3a9bff769ace06d52d39f1151f145612509cb466cd63e9d0e2af02aa4f50"},"schema_version":"1.0"},"canonical_sha256":"db10bd15b2b5e80c2944659506771dcaacb3d0bc29d5534c9ad0ea54ef3f5538","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:12.036608Z","signature_b64":"T2r+8nKqVybhDLtYAAzin/8odnVujzBz8WNQrl5DjmyilnrLqvOFu5jwhQSiTHt6urdaqq5wwPSWjWIiI+lKAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db10bd15b2b5e80c2944659506771dcaacb3d0bc29d5534c9ad0ea54ef3f5538","last_reissued_at":"2026-07-05T09:49:12.036121Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:12.036121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.23186","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":"2026-07-05T09:49:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3OVndXwzsUrZWyUvsibDa8pNppZV1S53R+TD4ph7qTaMiA5MaZkYQ25UmJCxGFqIHjuhK1VdsYZJi9iYH5zbBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T22:37:29.834822Z"},"content_sha256":"efb9c90d3491062d3088d66681d0a5dd6d0739fb25438b030cf1dae7a0c8c3b8","schema_version":"1.0","event_id":"sha256:efb9c90d3491062d3088d66681d0a5dd6d0739fb25438b030cf1dae7a0c8c3b8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3MIL2FNSWXUAYKKEMWKQM5Y5ZK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reliability of Topic Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kayla Schroeder, Zach Wood-Doughty","submitted_at":"2024-10-30T16:42:04Z","abstract_excerpt":"Topic models allow researchers to extract latent factors from text data and use those variables in downstream statistical analyses. However, these methodologies can vary significantly due to initialization differences, randomness in sampling procedures, or noisy data. Reliability of these methods is of particular concern as many researchers treat learned topic models as ground truth for subsequent analyses. In this work, we show that the standard practice for quantifying topic model reliability fails to capture essential aspects of the variation in two widely-used topic models. Drawing from a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23186","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.23186/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":"2026-07-05T09:49:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2/GcE5EBntxJA+xrgs9J9aOz45j+pW2T4YsePxt6st9AXqlR/b+e1FnSw1JoEP7ebNeH+Yd4tydc3jFcwUDiBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T22:37:29.835817Z"},"content_sha256":"f1cb41bc0e3f18b473a132e6918a439a9d37fa5ee05b51e02a81b728e600cefc","schema_version":"1.0","event_id":"sha256:f1cb41bc0e3f18b473a132e6918a439a9d37fa5ee05b51e02a81b728e600cefc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3MIL2FNSWXUAYKKEMWKQM5Y5ZK/bundle.json","state_url":"https://pith.science/pith/3MIL2FNSWXUAYKKEMWKQM5Y5ZK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3MIL2FNSWXUAYKKEMWKQM5Y5ZK/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":"2026-08-15T22:37:29Z","links":{"resolver":"https://pith.science/pith/3MIL2FNSWXUAYKKEMWKQM5Y5ZK","bundle":"https://pith.science/pith/3MIL2FNSWXUAYKKEMWKQM5Y5ZK/bundle.json","state":"https://pith.science/pith/3MIL2FNSWXUAYKKEMWKQM5Y5ZK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3MIL2FNSWXUAYKKEMWKQM5Y5ZK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3MIL2FNSWXUAYKKEMWKQM5Y5ZK","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":"ab8c3a9bff769ace06d52d39f1151f145612509cb466cd63e9d0e2af02aa4f50","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-30T16:42:04Z","title_canon_sha256":"f5be2b8e948761bf83248cb7d4bac845e6a640300527418178e8f62eab0b8dbf"},"schema_version":"1.0","source":{"id":"2410.23186","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.23186","created_at":"2026-07-05T09:49:12Z"},{"alias_kind":"arxiv_version","alias_value":"2410.23186v2","created_at":"2026-07-05T09:49:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23186","created_at":"2026-07-05T09:49:12Z"},{"alias_kind":"pith_short_12","alias_value":"3MIL2FNSWXUA","created_at":"2026-07-05T09:49:12Z"},{"alias_kind":"pith_short_16","alias_value":"3MIL2FNSWXUAYKKE","created_at":"2026-07-05T09:49:12Z"},{"alias_kind":"pith_short_8","alias_value":"3MIL2FNS","created_at":"2026-07-05T09:49:12Z"}],"graph_snapshots":[{"event_id":"sha256:f1cb41bc0e3f18b473a132e6918a439a9d37fa5ee05b51e02a81b728e600cefc","target":"graph","created_at":"2026-07-05T09:49:12Z","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/2410.23186/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Topic models allow researchers to extract latent factors from text data and use those variables in downstream statistical analyses. However, these methodologies can vary significantly due to initialization differences, randomness in sampling procedures, or noisy data. Reliability of these methods is of particular concern as many researchers treat learned topic models as ground truth for subsequent analyses. In this work, we show that the standard practice for quantifying topic model reliability fails to capture essential aspects of the variation in two widely-used topic models. Drawing from a ","authors_text":"Kayla Schroeder, Zach Wood-Doughty","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-30T16:42:04Z","title":"Reliability of Topic Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23186","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:efb9c90d3491062d3088d66681d0a5dd6d0739fb25438b030cf1dae7a0c8c3b8","target":"record","created_at":"2026-07-05T09:49:12Z","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":"ab8c3a9bff769ace06d52d39f1151f145612509cb466cd63e9d0e2af02aa4f50","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-30T16:42:04Z","title_canon_sha256":"f5be2b8e948761bf83248cb7d4bac845e6a640300527418178e8f62eab0b8dbf"},"schema_version":"1.0","source":{"id":"2410.23186","kind":"arxiv","version":2}},"canonical_sha256":"db10bd15b2b5e80c2944659506771dcaacb3d0bc29d5534c9ad0ea54ef3f5538","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db10bd15b2b5e80c2944659506771dcaacb3d0bc29d5534c9ad0ea54ef3f5538","first_computed_at":"2026-07-05T09:49:12.036121Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:12.036121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T2r+8nKqVybhDLtYAAzin/8odnVujzBz8WNQrl5DjmyilnrLqvOFu5jwhQSiTHt6urdaqq5wwPSWjWIiI+lKAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:12.036608Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.23186","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:efb9c90d3491062d3088d66681d0a5dd6d0739fb25438b030cf1dae7a0c8c3b8","sha256:f1cb41bc0e3f18b473a132e6918a439a9d37fa5ee05b51e02a81b728e600cefc"],"state_sha256":"8a7bf33840627b126da38a1795e31481a82acceb94a052af70563d3cbf98222d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9rzmDpxBelY7ihC3sf4TjlIrKVg5LQzERFKMYQs+muo2EDsqISVb0Xnqn57/P4PwjkZJylN4pkHgWNqnLtSwAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T22:37:29.841512Z","bundle_sha256":"ff824dbe1b235490cf941a172ecd706594a98ceafc95c4193814dd76affce3dc"}}