{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:WXKWXMOJS57THJL7FWWK3TZ5PA","short_pith_number":"pith:WXKWXMOJ","canonical_record":{"source":{"id":"2004.03974","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-08T12:37:51Z","cross_cats_sorted":[],"title_canon_sha256":"585e8a4daad26ea976a2faadd8a0c1b9400bb3f995fe9e4b19e059f76db33daa","abstract_canon_sha256":"9d5ced0253d321604fc5d25dafc294583f9b5d4a6088f2d25264786bdd0103f0"},"schema_version":"1.0"},"canonical_sha256":"b5d56bb1c9977f33a57f2dacadcf3d780f6c875a4801c2e5717ce80b31e9375d","source":{"kind":"arxiv","id":"2004.03974","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.03974","created_at":"2026-07-05T02:50:05Z"},{"alias_kind":"arxiv_version","alias_value":"2004.03974v2","created_at":"2026-07-05T02:50:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.03974","created_at":"2026-07-05T02:50:05Z"},{"alias_kind":"pith_short_12","alias_value":"WXKWXMOJS57T","created_at":"2026-07-05T02:50:05Z"},{"alias_kind":"pith_short_16","alias_value":"WXKWXMOJS57THJL7","created_at":"2026-07-05T02:50:05Z"},{"alias_kind":"pith_short_8","alias_value":"WXKWXMOJ","created_at":"2026-07-05T02:50:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:WXKWXMOJS57THJL7FWWK3TZ5PA","target":"record","payload":{"canonical_record":{"source":{"id":"2004.03974","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-08T12:37:51Z","cross_cats_sorted":[],"title_canon_sha256":"585e8a4daad26ea976a2faadd8a0c1b9400bb3f995fe9e4b19e059f76db33daa","abstract_canon_sha256":"9d5ced0253d321604fc5d25dafc294583f9b5d4a6088f2d25264786bdd0103f0"},"schema_version":"1.0"},"canonical_sha256":"b5d56bb1c9977f33a57f2dacadcf3d780f6c875a4801c2e5717ce80b31e9375d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:50:05.415165Z","signature_b64":"NgP0XBmdDNU/5hiuvoCqjky1kJjb2Vshafdsrg71D8+jsCxyIRhku2PwbX2CICidMeCGuEMHHs85TW3S9RdlDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5d56bb1c9977f33a57f2dacadcf3d780f6c875a4801c2e5717ce80b31e9375d","last_reissued_at":"2026-07-05T02:50:05.414639Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:50:05.414639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.03974","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:50:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V7+b6X1bGIctfVq1cqGN+xUlflyRN+ATvO109cc2n8HO3nF4Jp9bAlX6fjy1tTVqRQ0h7BoTxN6QdlAYd+9zDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T20:40:42.045577Z"},"content_sha256":"77c5862fd58715bea7767bd994dca4093341c37d9d341a8e417834de80bd782c","schema_version":"1.0","event_id":"sha256:77c5862fd58715bea7767bd994dca4093341c37d9d341a8e417834de80bd782c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:WXKWXMOJS57THJL7FWWK3TZ5PA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dirk Hovy, Federico Bianchi, Silvia Terragni","submitted_at":"2020-04-08T12:37:51Z","abstract_excerpt":"Topic models extract groups of words from documents, whose interpretation as a topic hopefully allows for a better understanding of the data. However, the resulting word groups are often not coherent, making them harder to interpret. Recently, neural topic models have shown improvements in overall coherence. Concurrently, contextual embeddings have advanced the state of the art of neural models in general. In this paper, we combine contextualized representations with neural topic models. We find that our approach produces more meaningful and coherent topics than traditional bag-of-words topic "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.03974","kind":"arxiv","version":2},"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/2004.03974/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":"2026-07-05T02:50:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ss4fINdQpKmZCSWo1IXkR0wZS8JII3Vw0X+b7ADI4vsUrpFkomAaLcbfV0krbLth9EtJlg6lQFv0QAnJtA54Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T20:40:42.046091Z"},"content_sha256":"1c244d1c26401cb8acfa19048c33065fcea85635036d09faed33229d62ac3688","schema_version":"1.0","event_id":"sha256:1c244d1c26401cb8acfa19048c33065fcea85635036d09faed33229d62ac3688"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WXKWXMOJS57THJL7FWWK3TZ5PA/bundle.json","state_url":"https://pith.science/pith/WXKWXMOJS57THJL7FWWK3TZ5PA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WXKWXMOJS57THJL7FWWK3TZ5PA/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":"2026-07-31T20:40:42Z","links":{"resolver":"https://pith.science/pith/WXKWXMOJS57THJL7FWWK3TZ5PA","bundle":"https://pith.science/pith/WXKWXMOJS57THJL7FWWK3TZ5PA/bundle.json","state":"https://pith.science/pith/WXKWXMOJS57THJL7FWWK3TZ5PA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WXKWXMOJS57THJL7FWWK3TZ5PA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:WXKWXMOJS57THJL7FWWK3TZ5PA","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":"9d5ced0253d321604fc5d25dafc294583f9b5d4a6088f2d25264786bdd0103f0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-08T12:37:51Z","title_canon_sha256":"585e8a4daad26ea976a2faadd8a0c1b9400bb3f995fe9e4b19e059f76db33daa"},"schema_version":"1.0","source":{"id":"2004.03974","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.03974","created_at":"2026-07-05T02:50:05Z"},{"alias_kind":"arxiv_version","alias_value":"2004.03974v2","created_at":"2026-07-05T02:50:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.03974","created_at":"2026-07-05T02:50:05Z"},{"alias_kind":"pith_short_12","alias_value":"WXKWXMOJS57T","created_at":"2026-07-05T02:50:05Z"},{"alias_kind":"pith_short_16","alias_value":"WXKWXMOJS57THJL7","created_at":"2026-07-05T02:50:05Z"},{"alias_kind":"pith_short_8","alias_value":"WXKWXMOJ","created_at":"2026-07-05T02:50:05Z"}],"graph_snapshots":[{"event_id":"sha256:1c244d1c26401cb8acfa19048c33065fcea85635036d09faed33229d62ac3688","target":"graph","created_at":"2026-07-05T02:50:05Z","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/2004.03974/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Topic models extract groups of words from documents, whose interpretation as a topic hopefully allows for a better understanding of the data. However, the resulting word groups are often not coherent, making them harder to interpret. Recently, neural topic models have shown improvements in overall coherence. Concurrently, contextual embeddings have advanced the state of the art of neural models in general. In this paper, we combine contextualized representations with neural topic models. We find that our approach produces more meaningful and coherent topics than traditional bag-of-words topic ","authors_text":"Dirk Hovy, Federico Bianchi, Silvia Terragni","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-08T12:37:51Z","title":"Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.03974","kind":"arxiv","version":2},"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":"sha256:77c5862fd58715bea7767bd994dca4093341c37d9d341a8e417834de80bd782c","target":"record","created_at":"2026-07-05T02:50:05Z","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":"9d5ced0253d321604fc5d25dafc294583f9b5d4a6088f2d25264786bdd0103f0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-08T12:37:51Z","title_canon_sha256":"585e8a4daad26ea976a2faadd8a0c1b9400bb3f995fe9e4b19e059f76db33daa"},"schema_version":"1.0","source":{"id":"2004.03974","kind":"arxiv","version":2}},"canonical_sha256":"b5d56bb1c9977f33a57f2dacadcf3d780f6c875a4801c2e5717ce80b31e9375d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b5d56bb1c9977f33a57f2dacadcf3d780f6c875a4801c2e5717ce80b31e9375d","first_computed_at":"2026-07-05T02:50:05.414639Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:50:05.414639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NgP0XBmdDNU/5hiuvoCqjky1kJjb2Vshafdsrg71D8+jsCxyIRhku2PwbX2CICidMeCGuEMHHs85TW3S9RdlDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:50:05.415165Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.03974","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77c5862fd58715bea7767bd994dca4093341c37d9d341a8e417834de80bd782c","sha256:1c244d1c26401cb8acfa19048c33065fcea85635036d09faed33229d62ac3688"],"state_sha256":"57fa30cc83716e923b18c8f05be2bf106ecd3c41bef1d51aadb1d543f8f9fac3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LggFb3fiduvKAoNmAFI1+4yDWtIjKj5Gk+qzII8u/tnORD37K0KwqPzFJ3VDxik6JYgn1EYiXm7ZvWOpa/UyDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T20:40:42.050485Z","bundle_sha256":"1055080fa78abe291367cdff1440544276ff7f053de0c78a1d27b6492220fcb0"}}