{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:46S37PGY7NYGMKC3J6ZXDU7FJS","short_pith_number":"pith:46S37PGY","schema_version":"1.0","canonical_sha256":"e7a5bfbcd8fb7066285b4fb371d3e54cb0913c34771aff9bccab9d64cccc858b","source":{"kind":"arxiv","id":"2505.12616","version":1},"attestation_state":"computed","paper":{"title":"Duluth at SemEval-2025 Task 7: TF-IDF with Optimized Vector Dimensions for Multilingual Fact-Checked Claim Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Shujauddin Syed, Ted Pedersen","submitted_at":"2025-05-19T01:58:22Z","abstract_excerpt":"This paper presents the Duluth approach to the SemEval-2025 Task 7 on Multilingual and Crosslingual Fact-Checked Claim Retrieval. We implemented a TF-IDF-based retrieval system with experimentation on vector dimensions and tokenization strategies. Our best-performing configuration used word-level tokenization with a vocabulary size of 15,000 features, achieving an average success@10 score of 0.78 on the development set and 0.69 on the test set across ten languages. Our system showed stronger performance on higher-resource languages but still lagged significantly behind the top-ranked system, w"},"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":"2505.12616","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T01:58:22Z","cross_cats_sorted":[],"title_canon_sha256":"4ecbd81ad1442a0228888537fb9dc9c1221bb0693745c7ae050ae76a9138ebd2","abstract_canon_sha256":"7b29d8ab2dafd8e28bf3e5a138f765488bfdfcb0e9f4479886db9c9b6b2a34fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:06.997740Z","signature_b64":"S343b5Ds4aL/Kd9Qb9VjElT/u4l3IzKlZAwTOsbzjvE1I9f2JpzFY60lZ0iQ3ArE9RcQDiEgvdBAOgCwYmeuAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7a5bfbcd8fb7066285b4fb371d3e54cb0913c34771aff9bccab9d64cccc858b","last_reissued_at":"2026-07-05T11:05:06.997258Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:06.997258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Duluth at SemEval-2025 Task 7: TF-IDF with Optimized Vector Dimensions for Multilingual Fact-Checked Claim Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Shujauddin Syed, Ted Pedersen","submitted_at":"2025-05-19T01:58:22Z","abstract_excerpt":"This paper presents the Duluth approach to the SemEval-2025 Task 7 on Multilingual and Crosslingual Fact-Checked Claim Retrieval. We implemented a TF-IDF-based retrieval system with experimentation on vector dimensions and tokenization strategies. Our best-performing configuration used word-level tokenization with a vocabulary size of 15,000 features, achieving an average success@10 score of 0.78 on the development set and 0.69 on the test set across ten languages. Our system showed stronger performance on higher-resource languages but still lagged significantly behind the top-ranked system, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12616","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/2505.12616/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":"2505.12616","created_at":"2026-07-05T11:05:06.997325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12616v1","created_at":"2026-07-05T11:05:06.997325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12616","created_at":"2026-07-05T11:05:06.997325+00:00"},{"alias_kind":"pith_short_12","alias_value":"46S37PGY7NYG","created_at":"2026-07-05T11:05:06.997325+00:00"},{"alias_kind":"pith_short_16","alias_value":"46S37PGY7NYGMKC3","created_at":"2026-07-05T11:05:06.997325+00:00"},{"alias_kind":"pith_short_8","alias_value":"46S37PGY","created_at":"2026-07-05T11:05:06.997325+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/46S37PGY7NYGMKC3J6ZXDU7FJS","json":"https://pith.science/pith/46S37PGY7NYGMKC3J6ZXDU7FJS.json","graph_json":"https://pith.science/api/pith-number/46S37PGY7NYGMKC3J6ZXDU7FJS/graph.json","events_json":"https://pith.science/api/pith-number/46S37PGY7NYGMKC3J6ZXDU7FJS/events.json","paper":"https://pith.science/paper/46S37PGY"},"agent_actions":{"view_html":"https://pith.science/pith/46S37PGY7NYGMKC3J6ZXDU7FJS","download_json":"https://pith.science/pith/46S37PGY7NYGMKC3J6ZXDU7FJS.json","view_paper":"https://pith.science/paper/46S37PGY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12616&json=true","fetch_graph":"https://pith.science/api/pith-number/46S37PGY7NYGMKC3J6ZXDU7FJS/graph.json","fetch_events":"https://pith.science/api/pith-number/46S37PGY7NYGMKC3J6ZXDU7FJS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/46S37PGY7NYGMKC3J6ZXDU7FJS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/46S37PGY7NYGMKC3J6ZXDU7FJS/action/storage_attestation","attest_author":"https://pith.science/pith/46S37PGY7NYGMKC3J6ZXDU7FJS/action/author_attestation","sign_citation":"https://pith.science/pith/46S37PGY7NYGMKC3J6ZXDU7FJS/action/citation_signature","submit_replication":"https://pith.science/pith/46S37PGY7NYGMKC3J6ZXDU7FJS/action/replication_record"}},"created_at":"2026-07-05T11:05:06.997325+00:00","updated_at":"2026-07-05T11:05:06.997325+00:00"}