{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:NBIEEDCDHH22NLR2T6DDWX73D7","short_pith_number":"pith:NBIEEDCD","canonical_record":{"source":{"id":"1810.10307","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-10-23T04:33:49Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"7008c7c2f5f26e94d650c968c8a0363b8491251ccf80d9f451e8b171ddf9bb69","abstract_canon_sha256":"c226d5d5f8d36e755e640e645ad0fcb5a141dd8acacfa936199ca0121c038954"},"schema_version":"1.0"},"canonical_sha256":"6850420c4339f5a6ae3a9f863b5ffb1fdb25c103d173be68d74ab6c083fd06a8","source":{"kind":"arxiv","id":"1810.10307","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.10307","created_at":"2026-05-18T00:02:23Z"},{"alias_kind":"arxiv_version","alias_value":"1810.10307v1","created_at":"2026-05-18T00:02:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.10307","created_at":"2026-05-18T00:02:23Z"},{"alias_kind":"pith_short_12","alias_value":"NBIEEDCDHH22","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"NBIEEDCDHH22NLR2","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"NBIEEDCD","created_at":"2026-05-18T12:32:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:NBIEEDCDHH22NLR2T6DDWX73D7","target":"record","payload":{"canonical_record":{"source":{"id":"1810.10307","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-10-23T04:33:49Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"7008c7c2f5f26e94d650c968c8a0363b8491251ccf80d9f451e8b171ddf9bb69","abstract_canon_sha256":"c226d5d5f8d36e755e640e645ad0fcb5a141dd8acacfa936199ca0121c038954"},"schema_version":"1.0"},"canonical_sha256":"6850420c4339f5a6ae3a9f863b5ffb1fdb25c103d173be68d74ab6c083fd06a8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:23.585754Z","signature_b64":"W1Ok5Ed1caq2DJvYpQhRrIqneGGvH1UA3zyPnQGCfbdFu0VSS7BPs6S7d4qk//O8i4llpvRZNjKq2ZQamOfzAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6850420c4339f5a6ae3a9f863b5ffb1fdb25c103d173be68d74ab6c083fd06a8","last_reissued_at":"2026-05-18T00:02:23.585089Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:23.585089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.10307","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":"2026-05-18T00:02:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LyWf1pg3fOPka5+CcpdBNg1ne4Tlyszbpz0KVrv5owRPrU1N4Eb2WUrM7z2gdYNGmTS8eIv+JvDb7Rzl3Hz4CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T11:58:25.854170Z"},"content_sha256":"338c4d4d6b2a826518028d7ff29ef13b0e0c61e0118f58a08f9815ccf59d7218","schema_version":"1.0","event_id":"sha256:338c4d4d6b2a826518028d7ff29ef13b0e0c61e0118f58a08f9815ccf59d7218"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:NBIEEDCDHH22NLR2T6DDWX73D7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Topic representation: finding more representative words in topic models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.IR","authors_text":"Changchun Li, Jihong Ouyang, Jinjin Chi, Ximing Li, Xinhua Wang, Xueyang Dong","submitted_at":"2018-10-23T04:33:49Z","abstract_excerpt":"The top word list, i.e., the top-M words with highest marginal probability in a given topic, is the standard topic representation in topic models. Most of recent automatical topic labeling algorithms and popular topic quality metrics are based on it. However, we find, empirically, words in this type of top word list are not always representative. The objective of this paper is to find more representative top word lists for topics. To achieve this, we rerank the words in a given topic by further considering marginal probability on words over every other topic. The reranking list of top-M words "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.10307","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":""},"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":"2026-05-18T00:02:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qsZPny/J3HHzPLyvOzxIFzxZdpyFvjWpxGmt2l15SzpRqlorZ/m68Don0G2eJuXyHKsFOlCl1WbC1jxC1MUYDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T11:58:25.854818Z"},"content_sha256":"40c98fbd51f9cf7f8135c66687e03a547b60fb363061a2c973ea0e87dd47809e","schema_version":"1.0","event_id":"sha256:40c98fbd51f9cf7f8135c66687e03a547b60fb363061a2c973ea0e87dd47809e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NBIEEDCDHH22NLR2T6DDWX73D7/bundle.json","state_url":"https://pith.science/pith/NBIEEDCDHH22NLR2T6DDWX73D7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NBIEEDCDHH22NLR2T6DDWX73D7/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":"2026-06-06T11:58:25Z","links":{"resolver":"https://pith.science/pith/NBIEEDCDHH22NLR2T6DDWX73D7","bundle":"https://pith.science/pith/NBIEEDCDHH22NLR2T6DDWX73D7/bundle.json","state":"https://pith.science/pith/NBIEEDCDHH22NLR2T6DDWX73D7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NBIEEDCDHH22NLR2T6DDWX73D7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:NBIEEDCDHH22NLR2T6DDWX73D7","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":"c226d5d5f8d36e755e640e645ad0fcb5a141dd8acacfa936199ca0121c038954","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-10-23T04:33:49Z","title_canon_sha256":"7008c7c2f5f26e94d650c968c8a0363b8491251ccf80d9f451e8b171ddf9bb69"},"schema_version":"1.0","source":{"id":"1810.10307","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.10307","created_at":"2026-05-18T00:02:23Z"},{"alias_kind":"arxiv_version","alias_value":"1810.10307v1","created_at":"2026-05-18T00:02:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.10307","created_at":"2026-05-18T00:02:23Z"},{"alias_kind":"pith_short_12","alias_value":"NBIEEDCDHH22","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"NBIEEDCDHH22NLR2","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"NBIEEDCD","created_at":"2026-05-18T12:32:40Z"}],"graph_snapshots":[{"event_id":"sha256:40c98fbd51f9cf7f8135c66687e03a547b60fb363061a2c973ea0e87dd47809e","target":"graph","created_at":"2026-05-18T00:02:23Z","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"},"paper":{"abstract_excerpt":"The top word list, i.e., the top-M words with highest marginal probability in a given topic, is the standard topic representation in topic models. Most of recent automatical topic labeling algorithms and popular topic quality metrics are based on it. However, we find, empirically, words in this type of top word list are not always representative. The objective of this paper is to find more representative top word lists for topics. To achieve this, we rerank the words in a given topic by further considering marginal probability on words over every other topic. The reranking list of top-M words ","authors_text":"Changchun Li, Jihong Ouyang, Jinjin Chi, Ximing Li, Xinhua Wang, Xueyang Dong","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-10-23T04:33:49Z","title":"Topic representation: finding more representative words in topic models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.10307","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":"sha256:338c4d4d6b2a826518028d7ff29ef13b0e0c61e0118f58a08f9815ccf59d7218","target":"record","created_at":"2026-05-18T00:02:23Z","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":"c226d5d5f8d36e755e640e645ad0fcb5a141dd8acacfa936199ca0121c038954","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-10-23T04:33:49Z","title_canon_sha256":"7008c7c2f5f26e94d650c968c8a0363b8491251ccf80d9f451e8b171ddf9bb69"},"schema_version":"1.0","source":{"id":"1810.10307","kind":"arxiv","version":1}},"canonical_sha256":"6850420c4339f5a6ae3a9f863b5ffb1fdb25c103d173be68d74ab6c083fd06a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6850420c4339f5a6ae3a9f863b5ffb1fdb25c103d173be68d74ab6c083fd06a8","first_computed_at":"2026-05-18T00:02:23.585089Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:02:23.585089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W1Ok5Ed1caq2DJvYpQhRrIqneGGvH1UA3zyPnQGCfbdFu0VSS7BPs6S7d4qk//O8i4llpvRZNjKq2ZQamOfzAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:02:23.585754Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.10307","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:338c4d4d6b2a826518028d7ff29ef13b0e0c61e0118f58a08f9815ccf59d7218","sha256:40c98fbd51f9cf7f8135c66687e03a547b60fb363061a2c973ea0e87dd47809e"],"state_sha256":"a0f0737168a31080a485fdb940d1b30c6e741210bc20d5caf8a601ff8c8079d3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WeEVFrNPrBW72tRDQlgNsWW4NB5bxHoQCWyfRjLuH7zQzFa840Hte5oD/C+B+IGWAzD7sYzi6FlyJjsp69LkDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T11:58:25.857631Z","bundle_sha256":"188bcb295cc38a2134985f45c9f9c78fad5a8dc5c9d9f4fe07ea9e18a68e757e"}}