{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LGZF6HUI46EQWY4GWOCK5WHW5K","short_pith_number":"pith:LGZF6HUI","canonical_record":{"source":{"id":"2501.13777","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.AP","submitted_at":"2025-01-23T15:54:54Z","cross_cats_sorted":[],"title_canon_sha256":"2ccb2f2148ec6790eef026bc6c016ed960877852e7f1c2c5b24cafb2c19cc9ce","abstract_canon_sha256":"e1f9ec95fd707ea67d660c1ef1f9956cbb264eeb834a648fb4e6523b34684e9d"},"schema_version":"1.0"},"canonical_sha256":"59b25f1e88e7890b6386b384aed8f6eaa4d9e2d916b291f2d69e31c53c524732","source":{"kind":"arxiv","id":"2501.13777","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.13777","created_at":"2026-07-05T10:04:33Z"},{"alias_kind":"arxiv_version","alias_value":"2501.13777v1","created_at":"2026-07-05T10:04:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13777","created_at":"2026-07-05T10:04:33Z"},{"alias_kind":"pith_short_12","alias_value":"LGZF6HUI46EQ","created_at":"2026-07-05T10:04:33Z"},{"alias_kind":"pith_short_16","alias_value":"LGZF6HUI46EQWY4G","created_at":"2026-07-05T10:04:33Z"},{"alias_kind":"pith_short_8","alias_value":"LGZF6HUI","created_at":"2026-07-05T10:04:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LGZF6HUI46EQWY4GWOCK5WHW5K","target":"record","payload":{"canonical_record":{"source":{"id":"2501.13777","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.AP","submitted_at":"2025-01-23T15:54:54Z","cross_cats_sorted":[],"title_canon_sha256":"2ccb2f2148ec6790eef026bc6c016ed960877852e7f1c2c5b24cafb2c19cc9ce","abstract_canon_sha256":"e1f9ec95fd707ea67d660c1ef1f9956cbb264eeb834a648fb4e6523b34684e9d"},"schema_version":"1.0"},"canonical_sha256":"59b25f1e88e7890b6386b384aed8f6eaa4d9e2d916b291f2d69e31c53c524732","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:33.879327Z","signature_b64":"XkJZ/yKTksguQCoonKkvPdgRr35xA4/rMX+w22FeP4MGHNod8Zd/9bxWcS4frlXjr46SJl+W79/8vyK9mBXSAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59b25f1e88e7890b6386b384aed8f6eaa4d9e2d916b291f2d69e31c53c524732","last_reissued_at":"2026-07-05T10:04:33.878873Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:33.878873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.13777","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":"2026-07-05T10:04:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KExNE9k+ZEfgEVWJEhC2lI05J4KVjF8L7W5k0dH1+nQ5XcsOnj6AGAechwUliwIbHihT0IRzPZ6ooCOQP7+HCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T09:04:20.842960Z"},"content_sha256":"16b7237bcb8407d4441288b7b6c21c9fbec0a4fc4f5df9f2f6b24f65edaffb79","schema_version":"1.0","event_id":"sha256:16b7237bcb8407d4441288b7b6c21c9fbec0a4fc4f5df9f2f6b24f65edaffb79"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LGZF6HUI46EQWY4GWOCK5WHW5K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Topic Modeling for Free-Response Text Data from a Complex Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"stat.AP","authors_text":"Namitha V.Pais, Paul A. Parker, Scott H. Holan","submitted_at":"2025-01-23T15:54:54Z","abstract_excerpt":"Topic Modeling is a popular statistical tool commonly used on textual data to identify the hidden thematic structure in a document collection based on the distribution of words. Additionally, it can be used to cluster the documents, with clusters representing distinct topics. The Mixture of Unigrams (MoU) is a standard topic model for clustering document-term data and can be particularly useful for analyzing open-ended survey responses to extract meaningful information from the underlying topics. However, with complex survey designs, where data is often collected on individual (document) chara"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13777","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/2501.13777/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":"2026-07-05T10:04:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Usae4uln/m1hTrOmtHw7BL5NmEIgLN+J6oEgWJZOkXhr/rz8Ict+kpl+C0b6bAOPSXO3Yf9b8MK2J07vUDj0Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T09:04:20.843474Z"},"content_sha256":"3c1cacd49d24f3d91056d336168bab04b35a5c5fe7b5ada836bf1b8d20082091","schema_version":"1.0","event_id":"sha256:3c1cacd49d24f3d91056d336168bab04b35a5c5fe7b5ada836bf1b8d20082091"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LGZF6HUI46EQWY4GWOCK5WHW5K/bundle.json","state_url":"https://pith.science/pith/LGZF6HUI46EQWY4GWOCK5WHW5K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LGZF6HUI46EQWY4GWOCK5WHW5K/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":"2026-08-14T09:04:20Z","links":{"resolver":"https://pith.science/pith/LGZF6HUI46EQWY4GWOCK5WHW5K","bundle":"https://pith.science/pith/LGZF6HUI46EQWY4GWOCK5WHW5K/bundle.json","state":"https://pith.science/pith/LGZF6HUI46EQWY4GWOCK5WHW5K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LGZF6HUI46EQWY4GWOCK5WHW5K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LGZF6HUI46EQWY4GWOCK5WHW5K","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":"e1f9ec95fd707ea67d660c1ef1f9956cbb264eeb834a648fb4e6523b34684e9d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.AP","submitted_at":"2025-01-23T15:54:54Z","title_canon_sha256":"2ccb2f2148ec6790eef026bc6c016ed960877852e7f1c2c5b24cafb2c19cc9ce"},"schema_version":"1.0","source":{"id":"2501.13777","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.13777","created_at":"2026-07-05T10:04:33Z"},{"alias_kind":"arxiv_version","alias_value":"2501.13777v1","created_at":"2026-07-05T10:04:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13777","created_at":"2026-07-05T10:04:33Z"},{"alias_kind":"pith_short_12","alias_value":"LGZF6HUI46EQ","created_at":"2026-07-05T10:04:33Z"},{"alias_kind":"pith_short_16","alias_value":"LGZF6HUI46EQWY4G","created_at":"2026-07-05T10:04:33Z"},{"alias_kind":"pith_short_8","alias_value":"LGZF6HUI","created_at":"2026-07-05T10:04:33Z"}],"graph_snapshots":[{"event_id":"sha256:3c1cacd49d24f3d91056d336168bab04b35a5c5fe7b5ada836bf1b8d20082091","target":"graph","created_at":"2026-07-05T10:04:33Z","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/2501.13777/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Topic Modeling is a popular statistical tool commonly used on textual data to identify the hidden thematic structure in a document collection based on the distribution of words. Additionally, it can be used to cluster the documents, with clusters representing distinct topics. The Mixture of Unigrams (MoU) is a standard topic model for clustering document-term data and can be particularly useful for analyzing open-ended survey responses to extract meaningful information from the underlying topics. However, with complex survey designs, where data is often collected on individual (document) chara","authors_text":"Namitha V.Pais, Paul A. Parker, Scott H. Holan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.AP","submitted_at":"2025-01-23T15:54:54Z","title":"Topic Modeling for Free-Response Text Data from a Complex Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13777","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":"sha256:16b7237bcb8407d4441288b7b6c21c9fbec0a4fc4f5df9f2f6b24f65edaffb79","target":"record","created_at":"2026-07-05T10:04:33Z","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":"e1f9ec95fd707ea67d660c1ef1f9956cbb264eeb834a648fb4e6523b34684e9d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.AP","submitted_at":"2025-01-23T15:54:54Z","title_canon_sha256":"2ccb2f2148ec6790eef026bc6c016ed960877852e7f1c2c5b24cafb2c19cc9ce"},"schema_version":"1.0","source":{"id":"2501.13777","kind":"arxiv","version":1}},"canonical_sha256":"59b25f1e88e7890b6386b384aed8f6eaa4d9e2d916b291f2d69e31c53c524732","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59b25f1e88e7890b6386b384aed8f6eaa4d9e2d916b291f2d69e31c53c524732","first_computed_at":"2026-07-05T10:04:33.878873Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:04:33.878873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XkJZ/yKTksguQCoonKkvPdgRr35xA4/rMX+w22FeP4MGHNod8Zd/9bxWcS4frlXjr46SJl+W79/8vyK9mBXSAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:04:33.879327Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.13777","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16b7237bcb8407d4441288b7b6c21c9fbec0a4fc4f5df9f2f6b24f65edaffb79","sha256:3c1cacd49d24f3d91056d336168bab04b35a5c5fe7b5ada836bf1b8d20082091"],"state_sha256":"e10e8e4d6fea4cc2654bc0d7365811770374dc7a35f9c903f54e73ff612d1eba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ULIVw7u1aYKrso149mUM/3eTnt0bNjji4T/Ve76PcUqSouS5QWIL13nijZmqMNxn/IfRReA9cipi5jafgOu0BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T09:04:20.849552Z","bundle_sha256":"6f2ed14baa39591d97a7e57b57394e6b4386b648c241fe05d394fda8364f5df2"}}