{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Q2CL7MX46ANPIEWUOEDOSMNTPL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f91328941df3d8fd14970377a9cb8d8ff8d7203ad6f3f82e202d8ebd61af9277","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-06T12:34:59Z","title_canon_sha256":"b880ffe799048690ae533f96b3e477b7eb9b3bd2cb900238a1d8e0239854229e"},"schema_version":"1.0","source":{"id":"2505.03481","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.03481","created_at":"2026-07-05T10:59:16Z"},{"alias_kind":"arxiv_version","alias_value":"2505.03481v1","created_at":"2026-07-05T10:59:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03481","created_at":"2026-07-05T10:59:16Z"},{"alias_kind":"pith_short_12","alias_value":"Q2CL7MX46ANP","created_at":"2026-07-05T10:59:16Z"},{"alias_kind":"pith_short_16","alias_value":"Q2CL7MX46ANPIEWU","created_at":"2026-07-05T10:59:16Z"},{"alias_kind":"pith_short_8","alias_value":"Q2CL7MX4","created_at":"2026-07-05T10:59:16Z"}],"graph_snapshots":[{"event_id":"sha256:934075bf570bacc60d342c8ab7e3ef616a7bfb6db5fa2f58e80ef34024077d7b","target":"graph","created_at":"2026-07-05T10:59:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.03481/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Maciej Zembrzuski, Saad Mahamood","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-06T12:34:59Z","title":"Sentence Embeddings as an intermediate target in end-to-end summarisation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03481","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:107f86b49b7659bda3280fbcbf78ffb741cb1c1de5f14ffc92eb7da3b87cb82c","target":"record","created_at":"2026-07-05T10:59:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f91328941df3d8fd14970377a9cb8d8ff8d7203ad6f3f82e202d8ebd61af9277","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-06T12:34:59Z","title_canon_sha256":"b880ffe799048690ae533f96b3e477b7eb9b3bd2cb900238a1d8e0239854229e"},"schema_version":"1.0","source":{"id":"2505.03481","kind":"arxiv","version":1}},"canonical_sha256":"8684bfb2fcf01af412d47106e931b37af62ccc6261baf29aea7898862ff29269","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8684bfb2fcf01af412d47106e931b37af62ccc6261baf29aea7898862ff29269","first_computed_at":"2026-07-05T10:59:16.873133Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:59:16.873133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IUFHdgsO9qoqm91t8ije2unEWSy56t+K6SQ+8nWOwy7pw0FilrrTP3lWUlkxnLxN6LImt5x9gbmZ0wwe2KMaCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:59:16.873677Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.03481","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:107f86b49b7659bda3280fbcbf78ffb741cb1c1de5f14ffc92eb7da3b87cb82c","sha256:934075bf570bacc60d342c8ab7e3ef616a7bfb6db5fa2f58e80ef34024077d7b"],"state_sha256":"fc1884e7753498e192018999cd81b6ad47d429b70ecbd8228d811929da43d279"}