{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BU7PSUILMCBGK6P2KWYKEGPJUL","short_pith_number":"pith:BU7PSUIL","schema_version":"1.0","canonical_sha256":"0d3ef9510b60826579fa55b0a219e9a2d2b0c4b9b8f5fa6343479ce1088862ba","source":{"kind":"arxiv","id":"2311.12474","version":1},"attestation_state":"computed","paper":{"title":"CSMeD: Bridging the Dataset Gap in Automated Citation Screening for Systematic Literature Reviews","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Allan Hanbury, Matthias Samwald, Oscar E. Mendoza, Petr Knoth, Wojciech Kusa","submitted_at":"2023-11-21T09:36:11Z","abstract_excerpt":"Systematic literature reviews (SLRs) play an essential role in summarising, synthesising and validating scientific evidence. In recent years, there has been a growing interest in using machine learning techniques to automate the identification of relevant studies for SLRs. However, the lack of standardised evaluation datasets makes comparing the performance of such automated literature screening systems difficult. In this paper, we analyse the citation screening evaluation datasets, revealing that many of the available datasets are either too small, suffer from data leakage or have limited app"},"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":"2311.12474","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-21T09:36:11Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"618414a2067ea184ec45b6cf42b24de632dddd3d9ee6168807da5d1e703f5407","abstract_canon_sha256":"830fd35855b203f0695c3ef9aa9435637a75636504bb57b07d889477eab90cc9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:15:05.949752Z","signature_b64":"0a35VsprScArLMh34WdQvcRNu0llSLPs/hjNi6erqTteoGeXXLe2I17Cdb7+i+GpBJblZzE72axDYg2Ca7qlCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d3ef9510b60826579fa55b0a219e9a2d2b0c4b9b8f5fa6343479ce1088862ba","last_reissued_at":"2026-07-05T07:15:05.949277Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:15:05.949277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CSMeD: Bridging the Dataset Gap in Automated Citation Screening for Systematic Literature Reviews","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Allan Hanbury, Matthias Samwald, Oscar E. Mendoza, Petr Knoth, Wojciech Kusa","submitted_at":"2023-11-21T09:36:11Z","abstract_excerpt":"Systematic literature reviews (SLRs) play an essential role in summarising, synthesising and validating scientific evidence. In recent years, there has been a growing interest in using machine learning techniques to automate the identification of relevant studies for SLRs. However, the lack of standardised evaluation datasets makes comparing the performance of such automated literature screening systems difficult. In this paper, we analyse the citation screening evaluation datasets, revealing that many of the available datasets are either too small, suffer from data leakage or have limited app"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.12474","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/2311.12474/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":"2311.12474","created_at":"2026-07-05T07:15:05.949335+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.12474v1","created_at":"2026-07-05T07:15:05.949335+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.12474","created_at":"2026-07-05T07:15:05.949335+00:00"},{"alias_kind":"pith_short_12","alias_value":"BU7PSUILMCBG","created_at":"2026-07-05T07:15:05.949335+00:00"},{"alias_kind":"pith_short_16","alias_value":"BU7PSUILMCBGK6P2","created_at":"2026-07-05T07:15:05.949335+00:00"},{"alias_kind":"pith_short_8","alias_value":"BU7PSUIL","created_at":"2026-07-05T07:15:05.949335+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.14914","citing_title":"A Reproducibility and Generalizability Study of Large Language Models for Query Generation","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BU7PSUILMCBGK6P2KWYKEGPJUL","json":"https://pith.science/pith/BU7PSUILMCBGK6P2KWYKEGPJUL.json","graph_json":"https://pith.science/api/pith-number/BU7PSUILMCBGK6P2KWYKEGPJUL/graph.json","events_json":"https://pith.science/api/pith-number/BU7PSUILMCBGK6P2KWYKEGPJUL/events.json","paper":"https://pith.science/paper/BU7PSUIL"},"agent_actions":{"view_html":"https://pith.science/pith/BU7PSUILMCBGK6P2KWYKEGPJUL","download_json":"https://pith.science/pith/BU7PSUILMCBGK6P2KWYKEGPJUL.json","view_paper":"https://pith.science/paper/BU7PSUIL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.12474&json=true","fetch_graph":"https://pith.science/api/pith-number/BU7PSUILMCBGK6P2KWYKEGPJUL/graph.json","fetch_events":"https://pith.science/api/pith-number/BU7PSUILMCBGK6P2KWYKEGPJUL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BU7PSUILMCBGK6P2KWYKEGPJUL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BU7PSUILMCBGK6P2KWYKEGPJUL/action/storage_attestation","attest_author":"https://pith.science/pith/BU7PSUILMCBGK6P2KWYKEGPJUL/action/author_attestation","sign_citation":"https://pith.science/pith/BU7PSUILMCBGK6P2KWYKEGPJUL/action/citation_signature","submit_replication":"https://pith.science/pith/BU7PSUILMCBGK6P2KWYKEGPJUL/action/replication_record"}},"created_at":"2026-07-05T07:15:05.949335+00:00","updated_at":"2026-07-05T07:15:05.949335+00:00"}