{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:XAGF23PWLVNO466I2I4ZQYQMDF","short_pith_number":"pith:XAGF23PW","schema_version":"1.0","canonical_sha256":"b80c5d6df65d5aee7bc8d23998620c197f7857b261859ca2c425b43f4b68b8d7","source":{"kind":"arxiv","id":"2105.06982","version":1},"attestation_state":"computed","paper":{"title":"EASE: Extractive-Abstractive Summarization with Explanations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arash Einolghozati, Bhargavi Paranjape, Haoran Li, Marjan Ghazvininejad, Sonal Gupta, Srinivasan Iyer, Yashar Mehdad","submitted_at":"2021-05-14T17:45:06Z","abstract_excerpt":"Current abstractive summarization systems outperform their extractive counterparts, but their widespread adoption is inhibited by the inherent lack of interpretability. To achieve the best of both worlds, we propose EASE, an extractive-abstractive framework for evidence-based text generation and apply it to document summarization. We present an explainable summarization system based on the Information Bottleneck principle that is jointly trained for extraction and abstraction in an end-to-end fashion. Inspired by previous research that humans use a two-stage framework to summarize long documen"},"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":"2105.06982","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-14T17:45:06Z","cross_cats_sorted":[],"title_canon_sha256":"49b38758a62c157e5723a2ff461c1921194194c603df4bda38275cb7f305cabc","abstract_canon_sha256":"af48debd53b936563bf8f8079fdf437f9267ac8372e1b30ea413465d98674b30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:40:23.524475Z","signature_b64":"KPco9NNzwGqTNxc3p3BUKiB5ghcaWvhaNKcLHqkzYDm6QlolgU46EMm6XJMKxKb3/9R7ocvUdZ2mohXaqy0jBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b80c5d6df65d5aee7bc8d23998620c197f7857b261859ca2c425b43f4b68b8d7","last_reissued_at":"2026-07-05T02:40:23.524006Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:40:23.524006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EASE: Extractive-Abstractive Summarization with Explanations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arash Einolghozati, Bhargavi Paranjape, Haoran Li, Marjan Ghazvininejad, Sonal Gupta, Srinivasan Iyer, Yashar Mehdad","submitted_at":"2021-05-14T17:45:06Z","abstract_excerpt":"Current abstractive summarization systems outperform their extractive counterparts, but their widespread adoption is inhibited by the inherent lack of interpretability. To achieve the best of both worlds, we propose EASE, an extractive-abstractive framework for evidence-based text generation and apply it to document summarization. We present an explainable summarization system based on the Information Bottleneck principle that is jointly trained for extraction and abstraction in an end-to-end fashion. Inspired by previous research that humans use a two-stage framework to summarize long documen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.06982","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/2105.06982/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":"2105.06982","created_at":"2026-07-05T02:40:23.524065+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.06982v1","created_at":"2026-07-05T02:40:23.524065+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.06982","created_at":"2026-07-05T02:40:23.524065+00:00"},{"alias_kind":"pith_short_12","alias_value":"XAGF23PWLVNO","created_at":"2026-07-05T02:40:23.524065+00:00"},{"alias_kind":"pith_short_16","alias_value":"XAGF23PWLVNO466I","created_at":"2026-07-05T02:40:23.524065+00:00"},{"alias_kind":"pith_short_8","alias_value":"XAGF23PW","created_at":"2026-07-05T02:40:23.524065+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28044","citing_title":"A Tree-of-Thoughts Inspired Hybrid Approach for Legal Case Judgement Summarization using LLMs","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XAGF23PWLVNO466I2I4ZQYQMDF","json":"https://pith.science/pith/XAGF23PWLVNO466I2I4ZQYQMDF.json","graph_json":"https://pith.science/api/pith-number/XAGF23PWLVNO466I2I4ZQYQMDF/graph.json","events_json":"https://pith.science/api/pith-number/XAGF23PWLVNO466I2I4ZQYQMDF/events.json","paper":"https://pith.science/paper/XAGF23PW"},"agent_actions":{"view_html":"https://pith.science/pith/XAGF23PWLVNO466I2I4ZQYQMDF","download_json":"https://pith.science/pith/XAGF23PWLVNO466I2I4ZQYQMDF.json","view_paper":"https://pith.science/paper/XAGF23PW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.06982&json=true","fetch_graph":"https://pith.science/api/pith-number/XAGF23PWLVNO466I2I4ZQYQMDF/graph.json","fetch_events":"https://pith.science/api/pith-number/XAGF23PWLVNO466I2I4ZQYQMDF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XAGF23PWLVNO466I2I4ZQYQMDF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XAGF23PWLVNO466I2I4ZQYQMDF/action/storage_attestation","attest_author":"https://pith.science/pith/XAGF23PWLVNO466I2I4ZQYQMDF/action/author_attestation","sign_citation":"https://pith.science/pith/XAGF23PWLVNO466I2I4ZQYQMDF/action/citation_signature","submit_replication":"https://pith.science/pith/XAGF23PWLVNO466I2I4ZQYQMDF/action/replication_record"}},"created_at":"2026-07-05T02:40:23.524065+00:00","updated_at":"2026-07-05T02:40:23.524065+00:00"}