{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:5SICW4MTVVCMAGXWU7XIP4FEEB","short_pith_number":"pith:5SICW4MT","canonical_record":{"source":{"id":"2004.05964","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-13T14:35:28Z","cross_cats_sorted":["stat.AP","stat.ME"],"title_canon_sha256":"734aa3fe0c103e62fc49b0810eaabfffbd8c4a42758ff51cd89b53240dcf9d69","abstract_canon_sha256":"95804fb32ef871ee7f3dac93e2bf2ab542d981ca7113cdf32bc27c8732a35aec"},"schema_version":"1.0"},"canonical_sha256":"ec902b7193ad44c01af6a7ee87f0a4204edb215fca7d3fdbca7df657b7279c8f","source":{"kind":"arxiv","id":"2004.05964","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.05964","created_at":"2026-07-05T05:38:25Z"},{"alias_kind":"arxiv_version","alias_value":"2004.05964v3","created_at":"2026-07-05T05:38:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.05964","created_at":"2026-07-05T05:38:25Z"},{"alias_kind":"pith_short_12","alias_value":"5SICW4MTVVCM","created_at":"2026-07-05T05:38:25Z"},{"alias_kind":"pith_short_16","alias_value":"5SICW4MTVVCMAGXW","created_at":"2026-07-05T05:38:25Z"},{"alias_kind":"pith_short_8","alias_value":"5SICW4MT","created_at":"2026-07-05T05:38:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:5SICW4MTVVCMAGXWU7XIP4FEEB","target":"record","payload":{"canonical_record":{"source":{"id":"2004.05964","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-13T14:35:28Z","cross_cats_sorted":["stat.AP","stat.ME"],"title_canon_sha256":"734aa3fe0c103e62fc49b0810eaabfffbd8c4a42758ff51cd89b53240dcf9d69","abstract_canon_sha256":"95804fb32ef871ee7f3dac93e2bf2ab542d981ca7113cdf32bc27c8732a35aec"},"schema_version":"1.0"},"canonical_sha256":"ec902b7193ad44c01af6a7ee87f0a4204edb215fca7d3fdbca7df657b7279c8f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:38:25.517356Z","signature_b64":"5V0bVe64Dl9Bes+eHs76X8h6PxnX66DgmQ3Y64OCvy6rLZPSg0eSUI7LFr5VxFgDazxB+bIjqjU1tN04YptcAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec902b7193ad44c01af6a7ee87f0a4204edb215fca7d3fdbca7df657b7279c8f","last_reissued_at":"2026-07-05T05:38:25.516801Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:38:25.516801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.05964","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:38:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qWs1sMpiKHByJk6mcBS3CLnt8vPtrZsQoS8sNMpKJbdbPPTLboKOzbdJhbvHGtXofXGSPT24arzGwrdoLO5YCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T04:32:11.964953Z"},"content_sha256":"395602372bdf79261ef2da5d193bdfdddacd0e43a18b7bc00d427c9bf17f6d9a","schema_version":"1.0","event_id":"sha256:395602372bdf79261ef2da5d193bdfdddacd0e43a18b7bc00d427c9bf17f6d9a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:5SICW4MTVVCMAGXWU7XIP4FEEB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Keyword Assisted Topic Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.AP","stat.ME"],"primary_cat":"cs.CL","authors_text":"Kosuke Imai, Shusei Eshima, Tomoya Sasaki","submitted_at":"2020-04-13T14:35:28Z","abstract_excerpt":"In recent years, fully automated content analysis based on probabilistic topic models has become popular among social scientists because of their scalability. The unsupervised nature of the models makes them suitable for exploring topics in a corpus without prior knowledge. However, researchers find that these models often fail to measure specific concepts of substantive interest by inadvertently creating multiple topics with similar content and combining distinct themes into a single topic. In this paper, we empirically demonstrate that providing a small number of keywords can substantially e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.05964","kind":"arxiv","version":3},"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/2004.05964/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":"2026-07-05T05:38:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rUr/UppsGMmS0KQHITk45uxM/ufuzFZyU5mCjFGBtphRmDhBpTL2hrb78ibdyhR2wJ4u683tU7+obzL9Vj9bCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T04:32:11.965597Z"},"content_sha256":"71330a4e098d8bedd819a93b500f748d66f669813e6dab45e8286272636089b0","schema_version":"1.0","event_id":"sha256:71330a4e098d8bedd819a93b500f748d66f669813e6dab45e8286272636089b0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5SICW4MTVVCMAGXWU7XIP4FEEB/bundle.json","state_url":"https://pith.science/pith/5SICW4MTVVCMAGXWU7XIP4FEEB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5SICW4MTVVCMAGXWU7XIP4FEEB/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":"2026-07-09T04:32:11Z","links":{"resolver":"https://pith.science/pith/5SICW4MTVVCMAGXWU7XIP4FEEB","bundle":"https://pith.science/pith/5SICW4MTVVCMAGXWU7XIP4FEEB/bundle.json","state":"https://pith.science/pith/5SICW4MTVVCMAGXWU7XIP4FEEB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5SICW4MTVVCMAGXWU7XIP4FEEB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:5SICW4MTVVCMAGXWU7XIP4FEEB","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":"95804fb32ef871ee7f3dac93e2bf2ab542d981ca7113cdf32bc27c8732a35aec","cross_cats_sorted":["stat.AP","stat.ME"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-13T14:35:28Z","title_canon_sha256":"734aa3fe0c103e62fc49b0810eaabfffbd8c4a42758ff51cd89b53240dcf9d69"},"schema_version":"1.0","source":{"id":"2004.05964","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.05964","created_at":"2026-07-05T05:38:25Z"},{"alias_kind":"arxiv_version","alias_value":"2004.05964v3","created_at":"2026-07-05T05:38:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.05964","created_at":"2026-07-05T05:38:25Z"},{"alias_kind":"pith_short_12","alias_value":"5SICW4MTVVCM","created_at":"2026-07-05T05:38:25Z"},{"alias_kind":"pith_short_16","alias_value":"5SICW4MTVVCMAGXW","created_at":"2026-07-05T05:38:25Z"},{"alias_kind":"pith_short_8","alias_value":"5SICW4MT","created_at":"2026-07-05T05:38:25Z"}],"graph_snapshots":[{"event_id":"sha256:71330a4e098d8bedd819a93b500f748d66f669813e6dab45e8286272636089b0","target":"graph","created_at":"2026-07-05T05:38:25Z","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/2004.05964/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, fully automated content analysis based on probabilistic topic models has become popular among social scientists because of their scalability. The unsupervised nature of the models makes them suitable for exploring topics in a corpus without prior knowledge. However, researchers find that these models often fail to measure specific concepts of substantive interest by inadvertently creating multiple topics with similar content and combining distinct themes into a single topic. In this paper, we empirically demonstrate that providing a small number of keywords can substantially e","authors_text":"Kosuke Imai, Shusei Eshima, Tomoya Sasaki","cross_cats":["stat.AP","stat.ME"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-13T14:35:28Z","title":"Keyword Assisted Topic Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.05964","kind":"arxiv","version":3},"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":"sha256:395602372bdf79261ef2da5d193bdfdddacd0e43a18b7bc00d427c9bf17f6d9a","target":"record","created_at":"2026-07-05T05:38:25Z","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":"95804fb32ef871ee7f3dac93e2bf2ab542d981ca7113cdf32bc27c8732a35aec","cross_cats_sorted":["stat.AP","stat.ME"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-13T14:35:28Z","title_canon_sha256":"734aa3fe0c103e62fc49b0810eaabfffbd8c4a42758ff51cd89b53240dcf9d69"},"schema_version":"1.0","source":{"id":"2004.05964","kind":"arxiv","version":3}},"canonical_sha256":"ec902b7193ad44c01af6a7ee87f0a4204edb215fca7d3fdbca7df657b7279c8f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec902b7193ad44c01af6a7ee87f0a4204edb215fca7d3fdbca7df657b7279c8f","first_computed_at":"2026-07-05T05:38:25.516801Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:38:25.516801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5V0bVe64Dl9Bes+eHs76X8h6PxnX66DgmQ3Y64OCvy6rLZPSg0eSUI7LFr5VxFgDazxB+bIjqjU1tN04YptcAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:38:25.517356Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.05964","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:395602372bdf79261ef2da5d193bdfdddacd0e43a18b7bc00d427c9bf17f6d9a","sha256:71330a4e098d8bedd819a93b500f748d66f669813e6dab45e8286272636089b0"],"state_sha256":"06da0e7a8d561a10caf60943a0e60bfc7e44b41710929948f257f04caa985870"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RVyJ5Yc0trF8vps/7495Dhy3VaKFh3pNkVBx51lHGd5HnSIR0ZKBRfS222ZQMZi9wDRYLxVVYOnBMnAKsAETDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T04:32:11.968729Z","bundle_sha256":"51806dc5d546985d4088e5fd80a737f13f8d6f401833b545d4f4d075ea4b7f5c"}}