{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7GVW6ZS6YHX5IAT5LWKO6HS2WM","short_pith_number":"pith:7GVW6ZS6","schema_version":"1.0","canonical_sha256":"f9ab6f665ec1efd4027d5d94ef1e5ab325a6bb8495060cf9692119d3d72af84b","source":{"kind":"arxiv","id":"2311.11462","version":2},"attestation_state":"computed","paper":{"title":"LLM aided semi-supervision for Extractive Dialog Summarization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ameen Abu-Hanna, Gaurav Sahu, Iacer Calixto, Issam H. Laradji, Nishant Mishra","submitted_at":"2023-11-19T23:59:22Z","abstract_excerpt":"Generating high-quality summaries for chat dialogs often requires large labeled datasets. We propose a method to efficiently use unlabeled data for extractive summarization of customer-agent dialogs. In our method, we frame summarization as a question-answering problem and use state-of-the-art large language models (LLMs) to generate pseudo-labels for a dialog. We then use these pseudo-labels to fine-tune a chat summarization model, effectively transferring knowledge from the large LLM into a smaller specialized model. We demonstrate our method on the \\tweetsumm dataset, and show that using 10"},"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":"2311.11462","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-19T23:59:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5a4839937418d536a89b8f6cdee3e0a09673c6963014152d926074a6bc705532","abstract_canon_sha256":"6e846eef6614d309a016ff8f7812ba6c814ed47d205583603b49b6f042e29e91"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:16:04.086647Z","signature_b64":"53ufE+4eGYtALdbFEO85TkXBpsVpCSBbVXC3Cbxz7AT9Onk3i5fomyPLlxS1GHOpV3WZAcRQzIt6r4r123XbCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9ab6f665ec1efd4027d5d94ef1e5ab325a6bb8495060cf9692119d3d72af84b","last_reissued_at":"2026-07-05T07:16:04.086099Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:16:04.086099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM aided semi-supervision for Extractive Dialog Summarization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ameen Abu-Hanna, Gaurav Sahu, Iacer Calixto, Issam H. Laradji, Nishant Mishra","submitted_at":"2023-11-19T23:59:22Z","abstract_excerpt":"Generating high-quality summaries for chat dialogs often requires large labeled datasets. We propose a method to efficiently use unlabeled data for extractive summarization of customer-agent dialogs. In our method, we frame summarization as a question-answering problem and use state-of-the-art large language models (LLMs) to generate pseudo-labels for a dialog. We then use these pseudo-labels to fine-tune a chat summarization model, effectively transferring knowledge from the large LLM into a smaller specialized model. We demonstrate our method on the \\tweetsumm dataset, and show that using 10"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.11462","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/2311.11462/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":"2311.11462","created_at":"2026-07-05T07:16:04.086170+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.11462v2","created_at":"2026-07-05T07:16:04.086170+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.11462","created_at":"2026-07-05T07:16:04.086170+00:00"},{"alias_kind":"pith_short_12","alias_value":"7GVW6ZS6YHX5","created_at":"2026-07-05T07:16:04.086170+00:00"},{"alias_kind":"pith_short_16","alias_value":"7GVW6ZS6YHX5IAT5","created_at":"2026-07-05T07:16:04.086170+00:00"},{"alias_kind":"pith_short_8","alias_value":"7GVW6ZS6","created_at":"2026-07-05T07:16:04.086170+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.07852","citing_title":"Pre-Trained AI Model Assisted Online Decision-Making under Missing Covariates: A Theoretical Perspective","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7GVW6ZS6YHX5IAT5LWKO6HS2WM","json":"https://pith.science/pith/7GVW6ZS6YHX5IAT5LWKO6HS2WM.json","graph_json":"https://pith.science/api/pith-number/7GVW6ZS6YHX5IAT5LWKO6HS2WM/graph.json","events_json":"https://pith.science/api/pith-number/7GVW6ZS6YHX5IAT5LWKO6HS2WM/events.json","paper":"https://pith.science/paper/7GVW6ZS6"},"agent_actions":{"view_html":"https://pith.science/pith/7GVW6ZS6YHX5IAT5LWKO6HS2WM","download_json":"https://pith.science/pith/7GVW6ZS6YHX5IAT5LWKO6HS2WM.json","view_paper":"https://pith.science/paper/7GVW6ZS6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.11462&json=true","fetch_graph":"https://pith.science/api/pith-number/7GVW6ZS6YHX5IAT5LWKO6HS2WM/graph.json","fetch_events":"https://pith.science/api/pith-number/7GVW6ZS6YHX5IAT5LWKO6HS2WM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7GVW6ZS6YHX5IAT5LWKO6HS2WM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7GVW6ZS6YHX5IAT5LWKO6HS2WM/action/storage_attestation","attest_author":"https://pith.science/pith/7GVW6ZS6YHX5IAT5LWKO6HS2WM/action/author_attestation","sign_citation":"https://pith.science/pith/7GVW6ZS6YHX5IAT5LWKO6HS2WM/action/citation_signature","submit_replication":"https://pith.science/pith/7GVW6ZS6YHX5IAT5LWKO6HS2WM/action/replication_record"}},"created_at":"2026-07-05T07:16:04.086170+00:00","updated_at":"2026-07-05T07:16:04.086170+00:00"}