{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Q2CL7MX46ANPIEWUOEDOSMNTPL","short_pith_number":"pith:Q2CL7MX4","schema_version":"1.0","canonical_sha256":"8684bfb2fcf01af412d47106e931b37af62ccc6261baf29aea7898862ff29269","source":{"kind":"arxiv","id":"2505.03481","version":1},"attestation_state":"computed","paper":{"title":"Sentence Embeddings as an intermediate target in end-to-end summarisation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Maciej Zembrzuski, Saad Mahamood","submitted_at":"2025-05-06T12:34:59Z","abstract_excerpt":"Current neural network-based methods to the problem of document summarisation struggle when applied to datasets containing large inputs. In this paper we propose a new approach to the challenge of content-selection when dealing with end-to-end summarisation of user reviews of accommodations. We show that by combining an extractive approach with externally pre-trained sentence level embeddings in an addition to an abstractive summarisation model we can outperform existing methods when this is applied to the task of summarising a large input dataset. We also prove that predicting sentence level "},"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":"2505.03481","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-06T12:34:59Z","cross_cats_sorted":[],"title_canon_sha256":"b880ffe799048690ae533f96b3e477b7eb9b3bd2cb900238a1d8e0239854229e","abstract_canon_sha256":"f91328941df3d8fd14970377a9cb8d8ff8d7203ad6f3f82e202d8ebd61af9277"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:16.873677Z","signature_b64":"IUFHdgsO9qoqm91t8ije2unEWSy56t+K6SQ+8nWOwy7pw0FilrrTP3lWUlkxnLxN6LImt5x9gbmZ0wwe2KMaCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8684bfb2fcf01af412d47106e931b37af62ccc6261baf29aea7898862ff29269","last_reissued_at":"2026-07-05T10:59:16.873133Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:16.873133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sentence Embeddings as an intermediate target in end-to-end summarisation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Maciej Zembrzuski, Saad Mahamood","submitted_at":"2025-05-06T12:34:59Z","abstract_excerpt":"Current neural network-based methods to the problem of document summarisation struggle when applied to datasets containing large inputs. In this paper we propose a new approach to the challenge of content-selection when dealing with end-to-end summarisation of user reviews of accommodations. We show that by combining an extractive approach with externally pre-trained sentence level embeddings in an addition to an abstractive summarisation model we can outperform existing methods when this is applied to the task of summarising a large input dataset. We also prove that predicting sentence level "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03481","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/2505.03481/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":"2505.03481","created_at":"2026-07-05T10:59:16.873193+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.03481v1","created_at":"2026-07-05T10:59:16.873193+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03481","created_at":"2026-07-05T10:59:16.873193+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q2CL7MX46ANP","created_at":"2026-07-05T10:59:16.873193+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q2CL7MX46ANPIEWU","created_at":"2026-07-05T10:59:16.873193+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q2CL7MX4","created_at":"2026-07-05T10:59:16.873193+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q2CL7MX46ANPIEWUOEDOSMNTPL","json":"https://pith.science/pith/Q2CL7MX46ANPIEWUOEDOSMNTPL.json","graph_json":"https://pith.science/api/pith-number/Q2CL7MX46ANPIEWUOEDOSMNTPL/graph.json","events_json":"https://pith.science/api/pith-number/Q2CL7MX46ANPIEWUOEDOSMNTPL/events.json","paper":"https://pith.science/paper/Q2CL7MX4"},"agent_actions":{"view_html":"https://pith.science/pith/Q2CL7MX46ANPIEWUOEDOSMNTPL","download_json":"https://pith.science/pith/Q2CL7MX46ANPIEWUOEDOSMNTPL.json","view_paper":"https://pith.science/paper/Q2CL7MX4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.03481&json=true","fetch_graph":"https://pith.science/api/pith-number/Q2CL7MX46ANPIEWUOEDOSMNTPL/graph.json","fetch_events":"https://pith.science/api/pith-number/Q2CL7MX46ANPIEWUOEDOSMNTPL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q2CL7MX46ANPIEWUOEDOSMNTPL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q2CL7MX46ANPIEWUOEDOSMNTPL/action/storage_attestation","attest_author":"https://pith.science/pith/Q2CL7MX46ANPIEWUOEDOSMNTPL/action/author_attestation","sign_citation":"https://pith.science/pith/Q2CL7MX46ANPIEWUOEDOSMNTPL/action/citation_signature","submit_replication":"https://pith.science/pith/Q2CL7MX46ANPIEWUOEDOSMNTPL/action/replication_record"}},"created_at":"2026-07-05T10:59:16.873193+00:00","updated_at":"2026-07-05T10:59:16.873193+00:00"}