{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:U6KL2PJS4GTFUQ6JKWLCSBN5VX","short_pith_number":"pith:U6KL2PJS","canonical_record":{"source":{"id":"2112.03101","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-11-22T07:27:17Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"7f356fc68b24fd17267bb16918f4d835bf389044e922a5f93e767efb61429600","abstract_canon_sha256":"c234cece581996b5f20d9e35b4ef02c93fd46c9f6878aaf905a87181ed9aa126"},"schema_version":"1.0"},"canonical_sha256":"a794bd3d32e1a65a43c955962905bdade94ab8e26b1527ce4f499b8dbb49f212","source":{"kind":"arxiv","id":"2112.03101","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.03101","created_at":"2026-07-05T03:38:02Z"},{"alias_kind":"arxiv_version","alias_value":"2112.03101v1","created_at":"2026-07-05T03:38:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.03101","created_at":"2026-07-05T03:38:02Z"},{"alias_kind":"pith_short_12","alias_value":"U6KL2PJS4GTF","created_at":"2026-07-05T03:38:02Z"},{"alias_kind":"pith_short_16","alias_value":"U6KL2PJS4GTFUQ6J","created_at":"2026-07-05T03:38:02Z"},{"alias_kind":"pith_short_8","alias_value":"U6KL2PJS","created_at":"2026-07-05T03:38:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:U6KL2PJS4GTFUQ6JKWLCSBN5VX","target":"record","payload":{"canonical_record":{"source":{"id":"2112.03101","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-11-22T07:27:17Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"7f356fc68b24fd17267bb16918f4d835bf389044e922a5f93e767efb61429600","abstract_canon_sha256":"c234cece581996b5f20d9e35b4ef02c93fd46c9f6878aaf905a87181ed9aa126"},"schema_version":"1.0"},"canonical_sha256":"a794bd3d32e1a65a43c955962905bdade94ab8e26b1527ce4f499b8dbb49f212","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:38:02.024330Z","signature_b64":"RGaMdfZ+3oQmuwu6Bbcm3CuxriQkILlhwNYDXT6uHV9lICSL3QbdSBVK4iO7STGCqm+W6eEEqC1qSvBXryE8Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a794bd3d32e1a65a43c955962905bdade94ab8e26b1527ce4f499b8dbb49f212","last_reissued_at":"2026-07-05T03:38:02.023815Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:38:02.023815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.03101","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":"2026-07-05T03:38:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4jn8WRXreRYlm9S5VG2Y0DOiqlssHycocUFLKk8hDTWfQSraq87ySq1GespD++sz7VUVZ0EKcj12f6K4CS2WCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:24:01.613616Z"},"content_sha256":"e63cf99b8b50b378b788f86ce3f6e4cd35d314c44e66476441bf4263bf11e557","schema_version":"1.0","event_id":"sha256:e63cf99b8b50b378b788f86ce3f6e4cd35d314c44e66476441bf4263bf11e557"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:U6KL2PJS4GTFUQ6JKWLCSBN5VX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Keyword Assisted Embedded Topic Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Bahareh Harandizadeh, Fred Morstatter, J. Hunter Priniski","submitted_at":"2021-11-22T07:27:17Z","abstract_excerpt":"By illuminating latent structures in a corpus of text, topic models are an essential tool for categorizing, summarizing, and exploring large collections of documents. Probabilistic topic models, such as latent Dirichlet allocation (LDA), describe how words in documents are generated via a set of latent distributions called topics. Recently, the Embedded Topic Model (ETM) has extended LDA to utilize the semantic information in word embeddings to derive semantically richer topics. As LDA and its extensions are unsupervised models, they aren't defined to make efficient use of a user's prior knowl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.03101","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/2112.03101/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":"2026-07-05T03:38:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pHJmaF6Y+PaEvRj95pI8nAp3i7w2lrThLvPXf40WXG0Po+EMDKcVxS3uc8k8+m6kFtTKGzY9yNzxGgkv5NKYCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:24:01.614005Z"},"content_sha256":"dad5740127d267af131fa77b0826b7718b9b5ebae8fcad4db761a09a118627b7","schema_version":"1.0","event_id":"sha256:dad5740127d267af131fa77b0826b7718b9b5ebae8fcad4db761a09a118627b7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U6KL2PJS4GTFUQ6JKWLCSBN5VX/bundle.json","state_url":"https://pith.science/pith/U6KL2PJS4GTFUQ6JKWLCSBN5VX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U6KL2PJS4GTFUQ6JKWLCSBN5VX/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":"2026-07-06T23:24:01Z","links":{"resolver":"https://pith.science/pith/U6KL2PJS4GTFUQ6JKWLCSBN5VX","bundle":"https://pith.science/pith/U6KL2PJS4GTFUQ6JKWLCSBN5VX/bundle.json","state":"https://pith.science/pith/U6KL2PJS4GTFUQ6JKWLCSBN5VX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U6KL2PJS4GTFUQ6JKWLCSBN5VX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:U6KL2PJS4GTFUQ6JKWLCSBN5VX","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":"c234cece581996b5f20d9e35b4ef02c93fd46c9f6878aaf905a87181ed9aa126","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-11-22T07:27:17Z","title_canon_sha256":"7f356fc68b24fd17267bb16918f4d835bf389044e922a5f93e767efb61429600"},"schema_version":"1.0","source":{"id":"2112.03101","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.03101","created_at":"2026-07-05T03:38:02Z"},{"alias_kind":"arxiv_version","alias_value":"2112.03101v1","created_at":"2026-07-05T03:38:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.03101","created_at":"2026-07-05T03:38:02Z"},{"alias_kind":"pith_short_12","alias_value":"U6KL2PJS4GTF","created_at":"2026-07-05T03:38:02Z"},{"alias_kind":"pith_short_16","alias_value":"U6KL2PJS4GTFUQ6J","created_at":"2026-07-05T03:38:02Z"},{"alias_kind":"pith_short_8","alias_value":"U6KL2PJS","created_at":"2026-07-05T03:38:02Z"}],"graph_snapshots":[{"event_id":"sha256:dad5740127d267af131fa77b0826b7718b9b5ebae8fcad4db761a09a118627b7","target":"graph","created_at":"2026-07-05T03:38:02Z","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/2112.03101/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"By illuminating latent structures in a corpus of text, topic models are an essential tool for categorizing, summarizing, and exploring large collections of documents. Probabilistic topic models, such as latent Dirichlet allocation (LDA), describe how words in documents are generated via a set of latent distributions called topics. Recently, the Embedded Topic Model (ETM) has extended LDA to utilize the semantic information in word embeddings to derive semantically richer topics. As LDA and its extensions are unsupervised models, they aren't defined to make efficient use of a user's prior knowl","authors_text":"Bahareh Harandizadeh, Fred Morstatter, J. Hunter Priniski","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-11-22T07:27:17Z","title":"Keyword Assisted Embedded Topic Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.03101","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:e63cf99b8b50b378b788f86ce3f6e4cd35d314c44e66476441bf4263bf11e557","target":"record","created_at":"2026-07-05T03:38:02Z","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":"c234cece581996b5f20d9e35b4ef02c93fd46c9f6878aaf905a87181ed9aa126","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-11-22T07:27:17Z","title_canon_sha256":"7f356fc68b24fd17267bb16918f4d835bf389044e922a5f93e767efb61429600"},"schema_version":"1.0","source":{"id":"2112.03101","kind":"arxiv","version":1}},"canonical_sha256":"a794bd3d32e1a65a43c955962905bdade94ab8e26b1527ce4f499b8dbb49f212","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a794bd3d32e1a65a43c955962905bdade94ab8e26b1527ce4f499b8dbb49f212","first_computed_at":"2026-07-05T03:38:02.023815Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:38:02.023815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RGaMdfZ+3oQmuwu6Bbcm3CuxriQkILlhwNYDXT6uHV9lICSL3QbdSBVK4iO7STGCqm+W6eEEqC1qSvBXryE8Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:38:02.024330Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.03101","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e63cf99b8b50b378b788f86ce3f6e4cd35d314c44e66476441bf4263bf11e557","sha256:dad5740127d267af131fa77b0826b7718b9b5ebae8fcad4db761a09a118627b7"],"state_sha256":"9d100e7dc7c6e4a6a05648a28f2c64329ab17c68059afa3ed92e24721db5ea80"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BPj1islUTjT9PB4mYZvVOI8AONMkQo2HP1f04P+KtTOJNh9oN2dKGiZ33GPVOKJgP4sl/HejKQrM2+tzLMQdAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T23:24:01.616013Z","bundle_sha256":"a7e5dc84540ee539d64da795d9ce6cfd214685e758aa50945ce421345f3755a9"}}