{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:MVUAH4BMLS6KMID7H5Q7YGXDM4","short_pith_number":"pith:MVUAH4BM","schema_version":"1.0","canonical_sha256":"656803f02c5cbca6207f3f61fc1ae36702c296303bd92c484f529b978d111a5f","source":{"kind":"arxiv","id":"2004.03760","version":2},"attestation_state":"computed","paper":{"title":"DialBERT: A Hierarchical Pre-Trained Model for Conversation Disentanglement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jia-Chen Gu, Quan Liu, Si Wei, Tianda Li, Xiaodan Zhu, Zhen-Hua Ling, Zhiming Su","submitted_at":"2020-04-08T00:54:01Z","abstract_excerpt":"Disentanglement is a problem in which multiple conversations occur in the same channel simultaneously, and the listener should decide which utterance is part of the conversation he will respond to. We propose a new model, named Dialogue BERT (DialBERT), which integrates local and global semantics in a single stream of messages to disentangle the conversations that mixed together. We employ BERT to capture the matching information in each utterance pair at the utterance-level, and use a BiLSTM to aggregate and incorporate the context-level information. With only a 3% increase in parameters, a 1"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2004.03760","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-08T00:54:01Z","cross_cats_sorted":[],"title_canon_sha256":"b02bd205c5725b358b44cd1f8c819f34f885cf14978b068d2911b1ec05e777e6","abstract_canon_sha256":"43c72a774639064bf4ee3d552cabd831a3fa5f83e53c6261bc316dcc73489cf6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:21.318650Z","signature_b64":"atubw5ks3Lb2X513j8EYdoDCjS1BNC8dvGkL/rdKqW2PclwxglU29zb9qwXxypCmKS6q3KncFUMyvDrCTo6HCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"656803f02c5cbca6207f3f61fc1ae36702c296303bd92c484f529b978d111a5f","last_reissued_at":"2026-07-05T03:13:21.318173Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:21.318173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DialBERT: A Hierarchical Pre-Trained Model for Conversation Disentanglement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jia-Chen Gu, Quan Liu, Si Wei, Tianda Li, Xiaodan Zhu, Zhen-Hua Ling, Zhiming Su","submitted_at":"2020-04-08T00:54:01Z","abstract_excerpt":"Disentanglement is a problem in which multiple conversations occur in the same channel simultaneously, and the listener should decide which utterance is part of the conversation he will respond to. We propose a new model, named Dialogue BERT (DialBERT), which integrates local and global semantics in a single stream of messages to disentangle the conversations that mixed together. We employ BERT to capture the matching information in each utterance pair at the utterance-level, and use a BiLSTM to aggregate and incorporate the context-level information. With only a 3% increase in parameters, a 1"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.03760","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/2004.03760/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2004.03760","created_at":"2026-07-05T03:13:21.318229+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.03760v2","created_at":"2026-07-05T03:13:21.318229+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.03760","created_at":"2026-07-05T03:13:21.318229+00:00"},{"alias_kind":"pith_short_12","alias_value":"MVUAH4BMLS6K","created_at":"2026-07-05T03:13:21.318229+00:00"},{"alias_kind":"pith_short_16","alias_value":"MVUAH4BMLS6KMID7","created_at":"2026-07-05T03:13:21.318229+00:00"},{"alias_kind":"pith_short_8","alias_value":"MVUAH4BM","created_at":"2026-07-05T03:13:21.318229+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07894","citing_title":"DD-GEPA: Prompt Optimization for Dialogue Disentanglement Focusing on Task Instruction and Utterance Representation","ref_index":106,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MVUAH4BMLS6KMID7H5Q7YGXDM4","json":"https://pith.science/pith/MVUAH4BMLS6KMID7H5Q7YGXDM4.json","graph_json":"https://pith.science/api/pith-number/MVUAH4BMLS6KMID7H5Q7YGXDM4/graph.json","events_json":"https://pith.science/api/pith-number/MVUAH4BMLS6KMID7H5Q7YGXDM4/events.json","paper":"https://pith.science/paper/MVUAH4BM"},"agent_actions":{"view_html":"https://pith.science/pith/MVUAH4BMLS6KMID7H5Q7YGXDM4","download_json":"https://pith.science/pith/MVUAH4BMLS6KMID7H5Q7YGXDM4.json","view_paper":"https://pith.science/paper/MVUAH4BM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.03760&json=true","fetch_graph":"https://pith.science/api/pith-number/MVUAH4BMLS6KMID7H5Q7YGXDM4/graph.json","fetch_events":"https://pith.science/api/pith-number/MVUAH4BMLS6KMID7H5Q7YGXDM4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MVUAH4BMLS6KMID7H5Q7YGXDM4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MVUAH4BMLS6KMID7H5Q7YGXDM4/action/storage_attestation","attest_author":"https://pith.science/pith/MVUAH4BMLS6KMID7H5Q7YGXDM4/action/author_attestation","sign_citation":"https://pith.science/pith/MVUAH4BMLS6KMID7H5Q7YGXDM4/action/citation_signature","submit_replication":"https://pith.science/pith/MVUAH4BMLS6KMID7H5Q7YGXDM4/action/replication_record"}},"created_at":"2026-07-05T03:13:21.318229+00:00","updated_at":"2026-07-05T03:13:21.318229+00:00"}