{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:WFKNENZDXFIAF6W7GB6K5VUTJB","short_pith_number":"pith:WFKNENZD","schema_version":"1.0","canonical_sha256":"b154d23723b95002fadf307caed69348746958fb2efd064f5a68b1cfd151173e","source":{"kind":"arxiv","id":"1804.08875","version":1},"attestation_state":"computed","paper":{"title":"Data-driven Summarization of Scientific Articles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Michael Pfeiffer, Nikola I. Nikolov, Richard H.R. Hahnloser","submitted_at":"2018-04-24T07:40:31Z","abstract_excerpt":"Data-driven approaches to sequence-to-sequence modelling have been successfully applied to short text summarization of news articles. Such models are typically trained on input-summary pairs consisting of only a single or a few sentences, partially due to limited availability of multi-sentence training data. Here, we propose to use scientific articles as a new milestone for text summarization: large-scale training data come almost for free with two types of high-quality summaries at different levels - the title and the abstract. We generate two novel multi-sentence summarization datasets from "},"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":"1804.08875","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-24T07:40:31Z","cross_cats_sorted":[],"title_canon_sha256":"45d1577c1a1efd7ac2d2b035ef650bd4addf0c64a2c4dd81652881b22812ea1c","abstract_canon_sha256":"47c3e77e7af5c969019fd07359cf2d2b9f23c429e549e8efd6c5ac9c4801be84"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:37.030099Z","signature_b64":"td5G3FFbDlNEcaLCarS7xK5+XQJaSjse/sOiPnQqwZuyLD99/Tj+SKevoMsx+tDcoNDvSvKzlF5u2PKG5rrbDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b154d23723b95002fadf307caed69348746958fb2efd064f5a68b1cfd151173e","last_reissued_at":"2026-05-18T00:17:37.029296Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:37.029296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-driven Summarization of Scientific Articles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Michael Pfeiffer, Nikola I. Nikolov, Richard H.R. Hahnloser","submitted_at":"2018-04-24T07:40:31Z","abstract_excerpt":"Data-driven approaches to sequence-to-sequence modelling have been successfully applied to short text summarization of news articles. Such models are typically trained on input-summary pairs consisting of only a single or a few sentences, partially due to limited availability of multi-sentence training data. Here, we propose to use scientific articles as a new milestone for text summarization: large-scale training data come almost for free with two types of high-quality summaries at different levels - the title and the abstract. We generate two novel multi-sentence summarization datasets from "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.08875","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":""},"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":"1804.08875","created_at":"2026-05-18T00:17:37.029443+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.08875v1","created_at":"2026-05-18T00:17:37.029443+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.08875","created_at":"2026-05-18T00:17:37.029443+00:00"},{"alias_kind":"pith_short_12","alias_value":"WFKNENZDXFIA","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"WFKNENZDXFIAF6W7","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"WFKNENZD","created_at":"2026-05-18T12:32:59.047623+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/WFKNENZDXFIAF6W7GB6K5VUTJB","json":"https://pith.science/pith/WFKNENZDXFIAF6W7GB6K5VUTJB.json","graph_json":"https://pith.science/api/pith-number/WFKNENZDXFIAF6W7GB6K5VUTJB/graph.json","events_json":"https://pith.science/api/pith-number/WFKNENZDXFIAF6W7GB6K5VUTJB/events.json","paper":"https://pith.science/paper/WFKNENZD"},"agent_actions":{"view_html":"https://pith.science/pith/WFKNENZDXFIAF6W7GB6K5VUTJB","download_json":"https://pith.science/pith/WFKNENZDXFIAF6W7GB6K5VUTJB.json","view_paper":"https://pith.science/paper/WFKNENZD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.08875&json=true","fetch_graph":"https://pith.science/api/pith-number/WFKNENZDXFIAF6W7GB6K5VUTJB/graph.json","fetch_events":"https://pith.science/api/pith-number/WFKNENZDXFIAF6W7GB6K5VUTJB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WFKNENZDXFIAF6W7GB6K5VUTJB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WFKNENZDXFIAF6W7GB6K5VUTJB/action/storage_attestation","attest_author":"https://pith.science/pith/WFKNENZDXFIAF6W7GB6K5VUTJB/action/author_attestation","sign_citation":"https://pith.science/pith/WFKNENZDXFIAF6W7GB6K5VUTJB/action/citation_signature","submit_replication":"https://pith.science/pith/WFKNENZDXFIAF6W7GB6K5VUTJB/action/replication_record"}},"created_at":"2026-05-18T00:17:37.029443+00:00","updated_at":"2026-05-18T00:17:37.029443+00:00"}