{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QKLEP2WJAVXNGDDGTGC6W3JCCN","short_pith_number":"pith:QKLEP2WJ","schema_version":"1.0","canonical_sha256":"829647eac9056ed30c669985eb6d221352e22a938e523de3dfacc3ac61dea645","source":{"kind":"arxiv","id":"2408.16444","version":1},"attestation_state":"computed","paper":{"title":"SurveySum: A Dataset for Summarizing Multiple Scientific Articles into a Survey Section","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gustavo Bartz Guedes, Jayr Pereira, Leandro Car\\'isio Fernandes, Roberto Lotufo, Rodrigo Nogueira, Thales Sales Almeida, Thiago Soares Laitz","submitted_at":"2024-08-29T11:13:23Z","abstract_excerpt":"Document summarization is a task to shorten texts into concise and informative summaries. This paper introduces a novel dataset designed for summarizing multiple scientific articles into a section of a survey. Our contributions are: (1) SurveySum, a new dataset addressing the gap in domain-specific summarization tools; (2) two specific pipelines to summarize scientific articles into a section of a survey; and (3) the evaluation of these pipelines using multiple metrics to compare their performance. Our results highlight the importance of high-quality retrieval stages and the impact of differen"},"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":"2408.16444","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-29T11:13:23Z","cross_cats_sorted":[],"title_canon_sha256":"87d3faa942d1706d153a8585982f2e0dc2f6fac90a10a609d2af8aa6f140dda2","abstract_canon_sha256":"7288e5cfbaa52c62732339487226c9b0dd080fb28102affeb16ef60c8cbe4e88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:46.266731Z","signature_b64":"wTSKe8Kdh1+WeijJgV2nyxxE47ZjWIVqNksmVii8URoMkKtvhSP4etcK5Y0CLWTjw0BeRJJKITFNjaGjMBVwDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"829647eac9056ed30c669985eb6d221352e22a938e523de3dfacc3ac61dea645","last_reissued_at":"2026-07-05T10:31:46.266060Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:46.266060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SurveySum: A Dataset for Summarizing Multiple Scientific Articles into a Survey Section","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gustavo Bartz Guedes, Jayr Pereira, Leandro Car\\'isio Fernandes, Roberto Lotufo, Rodrigo Nogueira, Thales Sales Almeida, Thiago Soares Laitz","submitted_at":"2024-08-29T11:13:23Z","abstract_excerpt":"Document summarization is a task to shorten texts into concise and informative summaries. This paper introduces a novel dataset designed for summarizing multiple scientific articles into a section of a survey. Our contributions are: (1) SurveySum, a new dataset addressing the gap in domain-specific summarization tools; (2) two specific pipelines to summarize scientific articles into a section of a survey; and (3) the evaluation of these pipelines using multiple metrics to compare their performance. Our results highlight the importance of high-quality retrieval stages and the impact of differen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.16444","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/2408.16444/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":"2408.16444","created_at":"2026-07-05T10:31:46.266134+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.16444v1","created_at":"2026-07-05T10:31:46.266134+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.16444","created_at":"2026-07-05T10:31:46.266134+00:00"},{"alias_kind":"pith_short_12","alias_value":"QKLEP2WJAVXN","created_at":"2026-07-05T10:31:46.266134+00:00"},{"alias_kind":"pith_short_16","alias_value":"QKLEP2WJAVXNGDDG","created_at":"2026-07-05T10:31:46.266134+00:00"},{"alias_kind":"pith_short_8","alias_value":"QKLEP2WJ","created_at":"2026-07-05T10:31:46.266134+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.16349","citing_title":"Ask, Retrieve, Summarize: A Modular Pipeline for Scientific Literature Summarization","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QKLEP2WJAVXNGDDGTGC6W3JCCN","json":"https://pith.science/pith/QKLEP2WJAVXNGDDGTGC6W3JCCN.json","graph_json":"https://pith.science/api/pith-number/QKLEP2WJAVXNGDDGTGC6W3JCCN/graph.json","events_json":"https://pith.science/api/pith-number/QKLEP2WJAVXNGDDGTGC6W3JCCN/events.json","paper":"https://pith.science/paper/QKLEP2WJ"},"agent_actions":{"view_html":"https://pith.science/pith/QKLEP2WJAVXNGDDGTGC6W3JCCN","download_json":"https://pith.science/pith/QKLEP2WJAVXNGDDGTGC6W3JCCN.json","view_paper":"https://pith.science/paper/QKLEP2WJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.16444&json=true","fetch_graph":"https://pith.science/api/pith-number/QKLEP2WJAVXNGDDGTGC6W3JCCN/graph.json","fetch_events":"https://pith.science/api/pith-number/QKLEP2WJAVXNGDDGTGC6W3JCCN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QKLEP2WJAVXNGDDGTGC6W3JCCN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QKLEP2WJAVXNGDDGTGC6W3JCCN/action/storage_attestation","attest_author":"https://pith.science/pith/QKLEP2WJAVXNGDDGTGC6W3JCCN/action/author_attestation","sign_citation":"https://pith.science/pith/QKLEP2WJAVXNGDDGTGC6W3JCCN/action/citation_signature","submit_replication":"https://pith.science/pith/QKLEP2WJAVXNGDDGTGC6W3JCCN/action/replication_record"}},"created_at":"2026-07-05T10:31:46.266134+00:00","updated_at":"2026-07-05T10:31:46.266134+00:00"}