{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MN2KZANGU763RHID45XZWIT72P","short_pith_number":"pith:MN2KZANG","schema_version":"1.0","canonical_sha256":"6374ac81a6a7fdb89d03e76f9b227fd3c231f13477e66d5a249913c18d71597e","source":{"kind":"arxiv","id":"2110.10150","version":2},"attestation_state":"computed","paper":{"title":"Summ^N: A Multi-Stage Summarization Framework for Long Input Dialogues and Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmed H. Awadallah, Ansong Ni, Budhaditya Deb, Chenguang Zhu, Chen Henry Wu, Dragomir Radev, Rui Zhang, Yusen Zhang, Ziming Mao","submitted_at":"2021-10-16T06:19:54Z","abstract_excerpt":"Text summarization helps readers capture salient information from documents, news, interviews, and meetings. However, most state-of-the-art pretrained language models (LM) are unable to efficiently process long text for many summarization tasks. In this paper, we propose Summ$^N$, a simple, flexible, and effective multi-stage framework for input texts that are longer than the maximum context length of typical pretrained LMs. Summ$^N$ first splits the data samples and generates a coarse summary in multiple stages and then produces the final fine-grained summary based on it. Our framework can pr"},"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":"2110.10150","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-16T06:19:54Z","cross_cats_sorted":[],"title_canon_sha256":"e00da0fea0c151fa2075d223c6b049b852e33bc2fd8d0c33d04958a73ccbef2d","abstract_canon_sha256":"c9f2da542bd85cc649e132db960baa482900b2d19bed51f606fbe6a4e673aedc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:14:39.137267Z","signature_b64":"zx4LW/eQsyRyQOAyScnVkzwk+3Ah/LK9Dvbv21pCi4tiBwl0jG6k4I1SZZowJ1JrcTfyubl5Nj6+uKyPspvDAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6374ac81a6a7fdb89d03e76f9b227fd3c231f13477e66d5a249913c18d71597e","last_reissued_at":"2026-07-05T04:14:39.136882Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:14:39.136882Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Summ^N: A Multi-Stage Summarization Framework for Long Input Dialogues and Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmed H. Awadallah, Ansong Ni, Budhaditya Deb, Chenguang Zhu, Chen Henry Wu, Dragomir Radev, Rui Zhang, Yusen Zhang, Ziming Mao","submitted_at":"2021-10-16T06:19:54Z","abstract_excerpt":"Text summarization helps readers capture salient information from documents, news, interviews, and meetings. However, most state-of-the-art pretrained language models (LM) are unable to efficiently process long text for many summarization tasks. In this paper, we propose Summ$^N$, a simple, flexible, and effective multi-stage framework for input texts that are longer than the maximum context length of typical pretrained LMs. Summ$^N$ first splits the data samples and generates a coarse summary in multiple stages and then produces the final fine-grained summary based on it. Our framework can pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.10150","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/2110.10150/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":"2110.10150","created_at":"2026-07-05T04:14:39.136937+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.10150v2","created_at":"2026-07-05T04:14:39.136937+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.10150","created_at":"2026-07-05T04:14:39.136937+00:00"},{"alias_kind":"pith_short_12","alias_value":"MN2KZANGU763","created_at":"2026-07-05T04:14:39.136937+00:00"},{"alias_kind":"pith_short_16","alias_value":"MN2KZANGU763RHID","created_at":"2026-07-05T04:14:39.136937+00:00"},{"alias_kind":"pith_short_8","alias_value":"MN2KZANG","created_at":"2026-07-05T04:14:39.136937+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.06494","citing_title":"GuideLLM: Exploring LLM-Guided Conversation with Applications in Autobiography Interviewing","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MN2KZANGU763RHID45XZWIT72P","json":"https://pith.science/pith/MN2KZANGU763RHID45XZWIT72P.json","graph_json":"https://pith.science/api/pith-number/MN2KZANGU763RHID45XZWIT72P/graph.json","events_json":"https://pith.science/api/pith-number/MN2KZANGU763RHID45XZWIT72P/events.json","paper":"https://pith.science/paper/MN2KZANG"},"agent_actions":{"view_html":"https://pith.science/pith/MN2KZANGU763RHID45XZWIT72P","download_json":"https://pith.science/pith/MN2KZANGU763RHID45XZWIT72P.json","view_paper":"https://pith.science/paper/MN2KZANG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.10150&json=true","fetch_graph":"https://pith.science/api/pith-number/MN2KZANGU763RHID45XZWIT72P/graph.json","fetch_events":"https://pith.science/api/pith-number/MN2KZANGU763RHID45XZWIT72P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MN2KZANGU763RHID45XZWIT72P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MN2KZANGU763RHID45XZWIT72P/action/storage_attestation","attest_author":"https://pith.science/pith/MN2KZANGU763RHID45XZWIT72P/action/author_attestation","sign_citation":"https://pith.science/pith/MN2KZANGU763RHID45XZWIT72P/action/citation_signature","submit_replication":"https://pith.science/pith/MN2KZANGU763RHID45XZWIT72P/action/replication_record"}},"created_at":"2026-07-05T04:14:39.136937+00:00","updated_at":"2026-07-05T04:14:39.136937+00:00"}