{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:G6DBP6T4OAEKU3BTZ44JZXS5DD","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":"a7d72b190e7ab5d9550a8a82fe783ab4f13f48ccac9b9425ebd2b1ceb2e7a2bb","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-02T00:43:10Z","title_canon_sha256":"b7881c8fea99a689a05b29fe4b3ed2d1abf0a3d3e1a6e514679923492f89b361"},"schema_version":"1.0","source":{"id":"2410.01141","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01141","created_at":"2026-07-05T11:29:34Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01141v3","created_at":"2026-07-05T11:29:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01141","created_at":"2026-07-05T11:29:34Z"},{"alias_kind":"pith_short_12","alias_value":"G6DBP6T4OAEK","created_at":"2026-07-05T11:29:34Z"},{"alias_kind":"pith_short_16","alias_value":"G6DBP6T4OAEKU3BT","created_at":"2026-07-05T11:29:34Z"},{"alias_kind":"pith_short_8","alias_value":"G6DBP6T4","created_at":"2026-07-05T11:29:34Z"}],"graph_snapshots":[{"event_id":"sha256:86c01ca368f6616bf652733e1577794b0dcad36d13cb57fba1a27197bdd167da","target":"graph","created_at":"2026-07-05T11:29:34Z","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/2410.01141/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This study investigates efficient deduplication techniques for a large NLP dataset of economic research paper titles. We explore various pairing methods alongside established distance measures (Levenshtein distance, cosine similarity) and a sBERT model for semantic evaluation. Our findings suggest a potentially low prevalence of duplicates based on the observed semantic similarity across different methods. Further exploration with a human-annotated ground truth set is completed for a more conclusive assessment. The result supports findings from the NLP, LLM based distance metrics.","authors_text":"Doohee You, S Fraiberger","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-02T00:43:10Z","title":"Evaluating Deduplication Techniques for Economic Research Paper Titles with a Focus on Semantic Similarity using NLP and LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01141","kind":"arxiv","version":3},"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":"sha256:8b86e30f519ef99a3f738be0dc8095cd50ef53c8ce86e752321f55996224cb87","target":"record","created_at":"2026-07-05T11:29:34Z","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":"a7d72b190e7ab5d9550a8a82fe783ab4f13f48ccac9b9425ebd2b1ceb2e7a2bb","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-02T00:43:10Z","title_canon_sha256":"b7881c8fea99a689a05b29fe4b3ed2d1abf0a3d3e1a6e514679923492f89b361"},"schema_version":"1.0","source":{"id":"2410.01141","kind":"arxiv","version":3}},"canonical_sha256":"378617fa7c7008aa6c33cf389cde5d18f955f7b7abc2566a866031af809713ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"378617fa7c7008aa6c33cf389cde5d18f955f7b7abc2566a866031af809713ac","first_computed_at":"2026-07-05T11:29:34.076956Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:34.076956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yS26UOCOsPitp30ZWXCH28DReAhaWNsu71B4zbrwRYyKUWGcTWfqbrAj+Ffe3RxcRdzM5/zHucJ+sTksKELZAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:34.077434Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.01141","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b86e30f519ef99a3f738be0dc8095cd50ef53c8ce86e752321f55996224cb87","sha256:86c01ca368f6616bf652733e1577794b0dcad36d13cb57fba1a27197bdd167da"],"state_sha256":"9036add4c6fae007a370e9e1e0baabd9acc5a4a306832ba6c2afa05fa799bbdb"}