{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:KVLJJYZXJXVD3QOPHKH4EYYSN7","short_pith_number":"pith:KVLJJYZX","schema_version":"1.0","canonical_sha256":"555694e3374dea3dc1cf3a8fc263126fc23915e47a0bcb7f6c5d485fd4112f55","source":{"kind":"arxiv","id":"1906.02923","version":1},"attestation_state":"computed","paper":{"title":"Preference-based Interactive Multi-Document Summarisation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christian M. Meyer, Iryna Gurevych, Yang Gao","submitted_at":"2019-06-07T06:42:24Z","abstract_excerpt":"Interactive NLP is a promising paradigm to close the gap between automatic NLP systems and the human upper bound. Preference-based interactive learning has been successfully applied, but the existing methods require several thousand interaction rounds even in simulations with perfect user feedback. In this paper, we study preference-based interactive summarisation. To reduce the number of interaction rounds, we propose the Active Preference-based ReInforcement Learning (APRIL) framework. APRIL uses Active Learning to query the user, Preference Learning to learn a summary ranking function from "},"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":"1906.02923","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-07T06:42:24Z","cross_cats_sorted":[],"title_canon_sha256":"2a68e183ecafbc70bc16745cdf6e0b07f273dc8fc87dc0f8bbb1319575b2f0cb","abstract_canon_sha256":"7e5832e268b552cec3ac1363b4f87bcaa1d179f63b4cd39341ab397908d5b193"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:55.668280Z","signature_b64":"Nqd0+XJ810kXnhIjVYqtm55BzBys8jprmDSYEq6VHzEOxUcMzcXHuLSiCgyS8CfN11+rGPcrgF83sBy3I6pfCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"555694e3374dea3dc1cf3a8fc263126fc23915e47a0bcb7f6c5d485fd4112f55","last_reissued_at":"2026-05-17T23:43:55.667772Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:55.667772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Preference-based Interactive Multi-Document Summarisation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christian M. Meyer, Iryna Gurevych, Yang Gao","submitted_at":"2019-06-07T06:42:24Z","abstract_excerpt":"Interactive NLP is a promising paradigm to close the gap between automatic NLP systems and the human upper bound. Preference-based interactive learning has been successfully applied, but the existing methods require several thousand interaction rounds even in simulations with perfect user feedback. In this paper, we study preference-based interactive summarisation. To reduce the number of interaction rounds, we propose the Active Preference-based ReInforcement Learning (APRIL) framework. APRIL uses Active Learning to query the user, Preference Learning to learn a summary ranking function from "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.02923","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1906.02923","created_at":"2026-05-17T23:43:55.667855+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.02923v1","created_at":"2026-05-17T23:43:55.667855+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.02923","created_at":"2026-05-17T23:43:55.667855+00:00"},{"alias_kind":"pith_short_12","alias_value":"KVLJJYZXJXVD","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"KVLJJYZXJXVD3QOP","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"KVLJJYZX","created_at":"2026-05-18T12:33:21.387695+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1909.08593","citing_title":"Fine-Tuning Language Models from Human Preferences","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KVLJJYZXJXVD3QOPHKH4EYYSN7","json":"https://pith.science/pith/KVLJJYZXJXVD3QOPHKH4EYYSN7.json","graph_json":"https://pith.science/api/pith-number/KVLJJYZXJXVD3QOPHKH4EYYSN7/graph.json","events_json":"https://pith.science/api/pith-number/KVLJJYZXJXVD3QOPHKH4EYYSN7/events.json","paper":"https://pith.science/paper/KVLJJYZX"},"agent_actions":{"view_html":"https://pith.science/pith/KVLJJYZXJXVD3QOPHKH4EYYSN7","download_json":"https://pith.science/pith/KVLJJYZXJXVD3QOPHKH4EYYSN7.json","view_paper":"https://pith.science/paper/KVLJJYZX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.02923&json=true","fetch_graph":"https://pith.science/api/pith-number/KVLJJYZXJXVD3QOPHKH4EYYSN7/graph.json","fetch_events":"https://pith.science/api/pith-number/KVLJJYZXJXVD3QOPHKH4EYYSN7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KVLJJYZXJXVD3QOPHKH4EYYSN7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KVLJJYZXJXVD3QOPHKH4EYYSN7/action/storage_attestation","attest_author":"https://pith.science/pith/KVLJJYZXJXVD3QOPHKH4EYYSN7/action/author_attestation","sign_citation":"https://pith.science/pith/KVLJJYZXJXVD3QOPHKH4EYYSN7/action/citation_signature","submit_replication":"https://pith.science/pith/KVLJJYZXJXVD3QOPHKH4EYYSN7/action/replication_record"}},"created_at":"2026-05-17T23:43:55.667855+00:00","updated_at":"2026-05-17T23:43:55.667855+00:00"}