{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:XHHOJ2R7CKNRHF7VA2IZP5A2GL","short_pith_number":"pith:XHHOJ2R7","schema_version":"1.0","canonical_sha256":"b9cee4ea3f129b1397f5069197f41a32e2132c31efea3ce5dfd9f0c24ac88476","source":{"kind":"arxiv","id":"2010.00117","version":1},"attestation_state":"computed","paper":{"title":"Multi-document Summarization with Maximal Marginal Relevance-guided Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiawei Han, Xiang Ren, Yanru Qu, Yiqing Xie, Yuning Mao","submitted_at":"2020-09-30T21:50:46Z","abstract_excerpt":"While neural sequence learning methods have made significant progress in single-document summarization (SDS), they produce unsatisfactory results on multi-document summarization (MDS). We observe two major challenges when adapting SDS advances to MDS: (1) MDS involves larger search space and yet more limited training data, setting obstacles for neural methods to learn adequate representations; (2) MDS needs to resolve higher information redundancy among the source documents, which SDS methods are less effective to handle. To close the gap, we present RL-MMR, Maximal Margin Relevance-guided Rei"},"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":"2010.00117","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-30T21:50:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"01dcbb4489180805a7ec433f1378b8a626df3c8cb61eb95f5a315d3ee964d0c1","abstract_canon_sha256":"db5cc2d45e86f5ae67ab478abd572f75e98be9e038624224eb50a96c259cd615"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:39:30.457248Z","signature_b64":"hgM+MYstmeN0Dvc8KAmDhY5yuIL++CFK+8kY2o5uR71GbXCYeAXM3/tpGrmSMxW/790KMEYCsDWG/NMKuBIcCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9cee4ea3f129b1397f5069197f41a32e2132c31efea3ce5dfd9f0c24ac88476","last_reissued_at":"2026-07-05T01:39:30.456754Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:39:30.456754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-document Summarization with Maximal Marginal Relevance-guided Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiawei Han, Xiang Ren, Yanru Qu, Yiqing Xie, Yuning Mao","submitted_at":"2020-09-30T21:50:46Z","abstract_excerpt":"While neural sequence learning methods have made significant progress in single-document summarization (SDS), they produce unsatisfactory results on multi-document summarization (MDS). We observe two major challenges when adapting SDS advances to MDS: (1) MDS involves larger search space and yet more limited training data, setting obstacles for neural methods to learn adequate representations; (2) MDS needs to resolve higher information redundancy among the source documents, which SDS methods are less effective to handle. To close the gap, we present RL-MMR, Maximal Margin Relevance-guided Rei"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.00117","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/2010.00117/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":"2010.00117","created_at":"2026-07-05T01:39:30.456814+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.00117v1","created_at":"2026-07-05T01:39:30.456814+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.00117","created_at":"2026-07-05T01:39:30.456814+00:00"},{"alias_kind":"pith_short_12","alias_value":"XHHOJ2R7CKNR","created_at":"2026-07-05T01:39:30.456814+00:00"},{"alias_kind":"pith_short_16","alias_value":"XHHOJ2R7CKNRHF7V","created_at":"2026-07-05T01:39:30.456814+00:00"},{"alias_kind":"pith_short_8","alias_value":"XHHOJ2R7","created_at":"2026-07-05T01:39:30.456814+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.13006","citing_title":"Evaluating the Performance of RAG Methods for Conversational AI in the Airport Domain","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XHHOJ2R7CKNRHF7VA2IZP5A2GL","json":"https://pith.science/pith/XHHOJ2R7CKNRHF7VA2IZP5A2GL.json","graph_json":"https://pith.science/api/pith-number/XHHOJ2R7CKNRHF7VA2IZP5A2GL/graph.json","events_json":"https://pith.science/api/pith-number/XHHOJ2R7CKNRHF7VA2IZP5A2GL/events.json","paper":"https://pith.science/paper/XHHOJ2R7"},"agent_actions":{"view_html":"https://pith.science/pith/XHHOJ2R7CKNRHF7VA2IZP5A2GL","download_json":"https://pith.science/pith/XHHOJ2R7CKNRHF7VA2IZP5A2GL.json","view_paper":"https://pith.science/paper/XHHOJ2R7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.00117&json=true","fetch_graph":"https://pith.science/api/pith-number/XHHOJ2R7CKNRHF7VA2IZP5A2GL/graph.json","fetch_events":"https://pith.science/api/pith-number/XHHOJ2R7CKNRHF7VA2IZP5A2GL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XHHOJ2R7CKNRHF7VA2IZP5A2GL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XHHOJ2R7CKNRHF7VA2IZP5A2GL/action/storage_attestation","attest_author":"https://pith.science/pith/XHHOJ2R7CKNRHF7VA2IZP5A2GL/action/author_attestation","sign_citation":"https://pith.science/pith/XHHOJ2R7CKNRHF7VA2IZP5A2GL/action/citation_signature","submit_replication":"https://pith.science/pith/XHHOJ2R7CKNRHF7VA2IZP5A2GL/action/replication_record"}},"created_at":"2026-07-05T01:39:30.456814+00:00","updated_at":"2026-07-05T01:39:30.456814+00:00"}