{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:YOT4F3LRHKE7PUYKDAJ6JTGONY","short_pith_number":"pith:YOT4F3LR","canonical_record":{"source":{"id":"1809.02687","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-07T21:43:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9b4d02fdb3600cd2f2aaee4940994de0ada012c00068d564d95df816cd7c403f","abstract_canon_sha256":"de82b66a66337fc330872acfc778a0231fab78f5e364e5ef21f8b9c4aeb3cb6e"},"schema_version":"1.0"},"canonical_sha256":"c3a7c2ed713a89f7d30a1813e4ccce6e20a05139d7a84a0321f6d5d66527e988","source":{"kind":"arxiv","id":"1809.02687","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.02687","created_at":"2026-05-18T00:06:15Z"},{"alias_kind":"arxiv_version","alias_value":"1809.02687v1","created_at":"2026-05-18T00:06:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.02687","created_at":"2026-05-18T00:06:15Z"},{"alias_kind":"pith_short_12","alias_value":"YOT4F3LRHKE7","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"YOT4F3LRHKE7PUYK","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"YOT4F3LR","created_at":"2026-05-18T12:33:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:YOT4F3LRHKE7PUYKDAJ6JTGONY","target":"record","payload":{"canonical_record":{"source":{"id":"1809.02687","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-07T21:43:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9b4d02fdb3600cd2f2aaee4940994de0ada012c00068d564d95df816cd7c403f","abstract_canon_sha256":"de82b66a66337fc330872acfc778a0231fab78f5e364e5ef21f8b9c4aeb3cb6e"},"schema_version":"1.0"},"canonical_sha256":"c3a7c2ed713a89f7d30a1813e4ccce6e20a05139d7a84a0321f6d5d66527e988","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:15.604753Z","signature_b64":"EbfjHdbt/dRKhlnE3hus37O/Y4GWoT1Aer05AdLU39Clpt8xbjpq/zLtAJE2rMenk5aHxx3Y4e4AeyYyj/FIAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3a7c2ed713a89f7d30a1813e4ccce6e20a05139d7a84a0321f6d5d66527e988","last_reissued_at":"2026-05-18T00:06:15.604117Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:15.604117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.02687","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":"2026-05-18T00:06:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pEzSEwBVCJFjTbuZSQhJixZQuTYR6iPAZ2/AzFSUkn+sqzyTih2wzBBCg48FGTtUyJg2otaTdlCqlxuPs72OAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T20:45:21.680072Z"},"content_sha256":"26e4dec5b295c2a2492bfc59e9771cda590027f9a8a527230d8fe03530a6076c","schema_version":"1.0","event_id":"sha256:26e4dec5b295c2a2492bfc59e9771cda590027f9a8a527230d8fe03530a6076c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:YOT4F3LRHKE7PUYKDAJ6JTGONY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Coherence-Aware Neural Topic Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bing Xiang, Ramesh Nallapati, Ran Ding","submitted_at":"2018-09-07T21:43:30Z","abstract_excerpt":"Topic models are evaluated based on their ability to describe documents well (i.e. low perplexity) and to produce topics that carry coherent semantic meaning. In topic modeling so far, perplexity is a direct optimization target. However, topic coherence, owing to its challenging computation, is not optimized for and is only evaluated after training. In this work, under a neural variational inference framework, we propose methods to incorporate a topic coherence objective into the training process. We demonstrate that such a coherence-aware topic model exhibits a similar level of perplexity as "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.02687","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":"2026-05-18T00:06:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hkigSvYoRdeZeZxPQipOPW/ZJvuYLodi5vvWiDT8HmqGCjntGp/kSAAbJ+dcPhJpkAOhDUIv6wLV8tG9hQQpBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T20:45:21.680548Z"},"content_sha256":"4b09f4caf47c055a72b7725e90c6e099f6ad203912c80dcea44af0d5f8d2622d","schema_version":"1.0","event_id":"sha256:4b09f4caf47c055a72b7725e90c6e099f6ad203912c80dcea44af0d5f8d2622d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YOT4F3LRHKE7PUYKDAJ6JTGONY/bundle.json","state_url":"https://pith.science/pith/YOT4F3LRHKE7PUYKDAJ6JTGONY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YOT4F3LRHKE7PUYKDAJ6JTGONY/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":"2026-05-24T20:45:21Z","links":{"resolver":"https://pith.science/pith/YOT4F3LRHKE7PUYKDAJ6JTGONY","bundle":"https://pith.science/pith/YOT4F3LRHKE7PUYKDAJ6JTGONY/bundle.json","state":"https://pith.science/pith/YOT4F3LRHKE7PUYKDAJ6JTGONY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YOT4F3LRHKE7PUYKDAJ6JTGONY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:YOT4F3LRHKE7PUYKDAJ6JTGONY","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":"de82b66a66337fc330872acfc778a0231fab78f5e364e5ef21f8b9c4aeb3cb6e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-07T21:43:30Z","title_canon_sha256":"9b4d02fdb3600cd2f2aaee4940994de0ada012c00068d564d95df816cd7c403f"},"schema_version":"1.0","source":{"id":"1809.02687","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.02687","created_at":"2026-05-18T00:06:15Z"},{"alias_kind":"arxiv_version","alias_value":"1809.02687v1","created_at":"2026-05-18T00:06:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.02687","created_at":"2026-05-18T00:06:15Z"},{"alias_kind":"pith_short_12","alias_value":"YOT4F3LRHKE7","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"YOT4F3LRHKE7PUYK","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"YOT4F3LR","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:4b09f4caf47c055a72b7725e90c6e099f6ad203912c80dcea44af0d5f8d2622d","target":"graph","created_at":"2026-05-18T00:06:15Z","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":"Topic models are evaluated based on their ability to describe documents well (i.e. low perplexity) and to produce topics that carry coherent semantic meaning. In topic modeling so far, perplexity is a direct optimization target. However, topic coherence, owing to its challenging computation, is not optimized for and is only evaluated after training. In this work, under a neural variational inference framework, we propose methods to incorporate a topic coherence objective into the training process. We demonstrate that such a coherence-aware topic model exhibits a similar level of perplexity as ","authors_text":"Bing Xiang, Ramesh Nallapati, Ran Ding","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-07T21:43:30Z","title":"Coherence-Aware Neural Topic Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.02687","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":"sha256:26e4dec5b295c2a2492bfc59e9771cda590027f9a8a527230d8fe03530a6076c","target":"record","created_at":"2026-05-18T00:06:15Z","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":"de82b66a66337fc330872acfc778a0231fab78f5e364e5ef21f8b9c4aeb3cb6e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-07T21:43:30Z","title_canon_sha256":"9b4d02fdb3600cd2f2aaee4940994de0ada012c00068d564d95df816cd7c403f"},"schema_version":"1.0","source":{"id":"1809.02687","kind":"arxiv","version":1}},"canonical_sha256":"c3a7c2ed713a89f7d30a1813e4ccce6e20a05139d7a84a0321f6d5d66527e988","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c3a7c2ed713a89f7d30a1813e4ccce6e20a05139d7a84a0321f6d5d66527e988","first_computed_at":"2026-05-18T00:06:15.604117Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:06:15.604117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EbfjHdbt/dRKhlnE3hus37O/Y4GWoT1Aer05AdLU39Clpt8xbjpq/zLtAJE2rMenk5aHxx3Y4e4AeyYyj/FIAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:06:15.604753Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.02687","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26e4dec5b295c2a2492bfc59e9771cda590027f9a8a527230d8fe03530a6076c","sha256:4b09f4caf47c055a72b7725e90c6e099f6ad203912c80dcea44af0d5f8d2622d"],"state_sha256":"9884edef7e876f2773f71c3fa91f8647d93b25165e79e10b9556c04a6e23e687"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I21AGU1pOXpaIpYMRiGqnQ42qX1nPUHcANqwHhRlvE+Uu0GqiJiu1oXxZf0M86HY7UzNUF9xfx9jNaQGl5DzCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T20:45:21.684741Z","bundle_sha256":"aebc543a91e57dc8304a012a032f8531cb4dab72847e38f5221f244ffb41f9f4"}}