{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:Q2CL7MX46ANPIEWUOEDOSMNTPL","short_pith_number":"pith:Q2CL7MX4","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"},"canonical_sha256":"8684bfb2fcf01af412d47106e931b37af62ccc6261baf29aea7898862ff29269","source":{"kind":"arxiv","id":"2505.03481","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:Q2CL7MX46ANPIEWUOEDOSMNTPL","target":"record","payload":{"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"},"canonical_sha256":"8684bfb2fcf01af412d47106e931b37af62ccc6261baf29aea7898862ff29269","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"},"source_kind":"arxiv","source_id":"2505.03481","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:59:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qlVvW7FA35dGpLmptVWuMeioZMl25+ADVAEScQ24308nhqLdoTSOePa/QtRcglxCSoV7lKtml+M1DOwSScnJDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T12:44:07.525942Z"},"content_sha256":"107f86b49b7659bda3280fbcbf78ffb741cb1c1de5f14ffc92eb7da3b87cb82c","schema_version":"1.0","event_id":"sha256:107f86b49b7659bda3280fbcbf78ffb741cb1c1de5f14ffc92eb7da3b87cb82c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:Q2CL7MX46ANPIEWUOEDOSMNTPL","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:59:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eDOg5nR9aeErvqbHOsaunTWaVct8IMERM+tCadTyEjvBIawopAhtjzAOKhG0gcWGLHqL/YcKejxiRcI5OYqlBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T12:44:07.526328Z"},"content_sha256":"934075bf570bacc60d342c8ab7e3ef616a7bfb6db5fa2f58e80ef34024077d7b","schema_version":"1.0","event_id":"sha256:934075bf570bacc60d342c8ab7e3ef616a7bfb6db5fa2f58e80ef34024077d7b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q2CL7MX46ANPIEWUOEDOSMNTPL/bundle.json","state_url":"https://pith.science/pith/Q2CL7MX46ANPIEWUOEDOSMNTPL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q2CL7MX46ANPIEWUOEDOSMNTPL/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-18T12:44:07Z","links":{"resolver":"https://pith.science/pith/Q2CL7MX46ANPIEWUOEDOSMNTPL","bundle":"https://pith.science/pith/Q2CL7MX46ANPIEWUOEDOSMNTPL/bundle.json","state":"https://pith.science/pith/Q2CL7MX46ANPIEWUOEDOSMNTPL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q2CL7MX46ANPIEWUOEDOSMNTPL/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"smEIJ4UxWY3BXTgYAfTIDx/ULjf/OqCLg5540k4NfuU0qkcpT2ZSCK+G4aclZVnUSAPtUARsh6mZHy/vlvUxCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T12:44:07.528862Z","bundle_sha256":"54005fa44bd1740ad1d46c89fc7dadf331b00640f718153f1ebb43656379092a"}}