{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4VZRWATKGEY7BPUK4H7IQ3CDND","short_pith_number":"pith:4VZRWATK","schema_version":"1.0","canonical_sha256":"e5731b026a3131f0be8ae1fe886c4368f10661a4bdf2478cdd60c5776b00e631","source":{"kind":"arxiv","id":"2305.14006","version":1},"attestation_state":"computed","paper":{"title":"Multi-Granularity Prompts for Topic Shift Detection in Dialogue","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiangyi Lin, Peifeng Li, Qiaoming Zhu, Xiaomin Chu, Yaxin Fan","submitted_at":"2023-05-23T12:35:49Z","abstract_excerpt":"The goal of dialogue topic shift detection is to identify whether the current topic in a conversation has changed or needs to change. Previous work focused on detecting topic shifts using pre-trained models to encode the utterance, failing to delve into the various levels of topic granularity in the dialogue and understand dialogue contents. To address the above issues, we take a prompt-based approach to fully extract topic information from dialogues at multiple-granularity, i.e., label, turn, and topic. Experimental results on our annotated Chinese Natural Topic Dialogue dataset CNTD and the "},"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":"2305.14006","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T12:35:49Z","cross_cats_sorted":[],"title_canon_sha256":"094783b1e3cde72a498145f7cba5d3b2b0a70057a6a826070563297be0cea6a0","abstract_canon_sha256":"f7a384f500cf46805a9a50cb9d415444f274c3d7647fcd13197086e475aa74da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:00.203104Z","signature_b64":"w5wztZd86rYJdzr0xAv2EgMekNQafEMsnvDQJHtlr1IKQE2pMrQmpMSDa+Fh+jORcsKzU+2LqZaAE6n6D7YyBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5731b026a3131f0be8ae1fe886c4368f10661a4bdf2478cdd60c5776b00e631","last_reissued_at":"2026-07-05T06:13:00.202628Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:00.202628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Granularity Prompts for Topic Shift Detection in Dialogue","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiangyi Lin, Peifeng Li, Qiaoming Zhu, Xiaomin Chu, Yaxin Fan","submitted_at":"2023-05-23T12:35:49Z","abstract_excerpt":"The goal of dialogue topic shift detection is to identify whether the current topic in a conversation has changed or needs to change. Previous work focused on detecting topic shifts using pre-trained models to encode the utterance, failing to delve into the various levels of topic granularity in the dialogue and understand dialogue contents. To address the above issues, we take a prompt-based approach to fully extract topic information from dialogues at multiple-granularity, i.e., label, turn, and topic. Experimental results on our annotated Chinese Natural Topic Dialogue dataset CNTD and the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14006","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/2305.14006/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":"2305.14006","created_at":"2026-07-05T06:13:00.202686+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14006v1","created_at":"2026-07-05T06:13:00.202686+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14006","created_at":"2026-07-05T06:13:00.202686+00:00"},{"alias_kind":"pith_short_12","alias_value":"4VZRWATKGEY7","created_at":"2026-07-05T06:13:00.202686+00:00"},{"alias_kind":"pith_short_16","alias_value":"4VZRWATKGEY7BPUK","created_at":"2026-07-05T06:13:00.202686+00:00"},{"alias_kind":"pith_short_8","alias_value":"4VZRWATK","created_at":"2026-07-05T06:13:00.202686+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4VZRWATKGEY7BPUK4H7IQ3CDND","json":"https://pith.science/pith/4VZRWATKGEY7BPUK4H7IQ3CDND.json","graph_json":"https://pith.science/api/pith-number/4VZRWATKGEY7BPUK4H7IQ3CDND/graph.json","events_json":"https://pith.science/api/pith-number/4VZRWATKGEY7BPUK4H7IQ3CDND/events.json","paper":"https://pith.science/paper/4VZRWATK"},"agent_actions":{"view_html":"https://pith.science/pith/4VZRWATKGEY7BPUK4H7IQ3CDND","download_json":"https://pith.science/pith/4VZRWATKGEY7BPUK4H7IQ3CDND.json","view_paper":"https://pith.science/paper/4VZRWATK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14006&json=true","fetch_graph":"https://pith.science/api/pith-number/4VZRWATKGEY7BPUK4H7IQ3CDND/graph.json","fetch_events":"https://pith.science/api/pith-number/4VZRWATKGEY7BPUK4H7IQ3CDND/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4VZRWATKGEY7BPUK4H7IQ3CDND/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4VZRWATKGEY7BPUK4H7IQ3CDND/action/storage_attestation","attest_author":"https://pith.science/pith/4VZRWATKGEY7BPUK4H7IQ3CDND/action/author_attestation","sign_citation":"https://pith.science/pith/4VZRWATKGEY7BPUK4H7IQ3CDND/action/citation_signature","submit_replication":"https://pith.science/pith/4VZRWATKGEY7BPUK4H7IQ3CDND/action/replication_record"}},"created_at":"2026-07-05T06:13:00.202686+00:00","updated_at":"2026-07-05T06:13:00.202686+00:00"}