{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VMMN5GUQCVDSFDVHDF6BQEJHSD","short_pith_number":"pith:VMMN5GUQ","schema_version":"1.0","canonical_sha256":"ab18de9a901547228ea7197c18112790e20c2a7c836c362ad09cb1573f61f44e","source":{"kind":"arxiv","id":"2309.13080","version":3},"attestation_state":"computed","paper":{"title":"SPICED: News Similarity Detection Dataset with Multiple Topics and Complexity Levels","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Elena Shushkevich, Long Mai, Manuel V. Loureiro, Steven Derby, Tri Kurniawan Wijaya","submitted_at":"2023-09-21T10:55:26Z","abstract_excerpt":"The proliferation of news media outlets has increased the demand for intelligent systems capable of detecting redundant information in news articles in order to enhance user experience. However, the heterogeneous nature of news can lead to spurious findings in these systems: Simple heuristics such as whether a pair of news are both about politics can provide strong but deceptive downstream performance. Segmenting news similarity datasets into topics improves the training of these models by forcing them to learn how to distinguish salient characteristics under more narrow domains. However, this"},"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":"2309.13080","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-21T10:55:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"776c6c44f38358dd0680b20b7dc53c2e141e7a8a289612e2ded63bc8008f1eb5","abstract_canon_sha256":"544a9735900bdfb5e5188dc8e9fa0c5aafbee5b7d81f26079c979bf319221c45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:59:03.852131Z","signature_b64":"+6YOxhoK0vVJdZ58MzTTh/zya48mq9orgOULxEg+fjR7I9oTXllb4oWSPkX0CgfBs//DMYsh9bziRTME7d8MAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab18de9a901547228ea7197c18112790e20c2a7c836c362ad09cb1573f61f44e","last_reissued_at":"2026-07-05T08:59:03.851583Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:59:03.851583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPICED: News Similarity Detection Dataset with Multiple Topics and Complexity Levels","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Elena Shushkevich, Long Mai, Manuel V. Loureiro, Steven Derby, Tri Kurniawan Wijaya","submitted_at":"2023-09-21T10:55:26Z","abstract_excerpt":"The proliferation of news media outlets has increased the demand for intelligent systems capable of detecting redundant information in news articles in order to enhance user experience. However, the heterogeneous nature of news can lead to spurious findings in these systems: Simple heuristics such as whether a pair of news are both about politics can provide strong but deceptive downstream performance. Segmenting news similarity datasets into topics improves the training of these models by forcing them to learn how to distinguish salient characteristics under more narrow domains. However, this"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.13080","kind":"arxiv","version":3},"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/2309.13080/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":"2309.13080","created_at":"2026-07-05T08:59:03.851642+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.13080v3","created_at":"2026-07-05T08:59:03.851642+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.13080","created_at":"2026-07-05T08:59:03.851642+00:00"},{"alias_kind":"pith_short_12","alias_value":"VMMN5GUQCVDS","created_at":"2026-07-05T08:59:03.851642+00:00"},{"alias_kind":"pith_short_16","alias_value":"VMMN5GUQCVDSFDVH","created_at":"2026-07-05T08:59:03.851642+00:00"},{"alias_kind":"pith_short_8","alias_value":"VMMN5GUQ","created_at":"2026-07-05T08:59:03.851642+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/VMMN5GUQCVDSFDVHDF6BQEJHSD","json":"https://pith.science/pith/VMMN5GUQCVDSFDVHDF6BQEJHSD.json","graph_json":"https://pith.science/api/pith-number/VMMN5GUQCVDSFDVHDF6BQEJHSD/graph.json","events_json":"https://pith.science/api/pith-number/VMMN5GUQCVDSFDVHDF6BQEJHSD/events.json","paper":"https://pith.science/paper/VMMN5GUQ"},"agent_actions":{"view_html":"https://pith.science/pith/VMMN5GUQCVDSFDVHDF6BQEJHSD","download_json":"https://pith.science/pith/VMMN5GUQCVDSFDVHDF6BQEJHSD.json","view_paper":"https://pith.science/paper/VMMN5GUQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.13080&json=true","fetch_graph":"https://pith.science/api/pith-number/VMMN5GUQCVDSFDVHDF6BQEJHSD/graph.json","fetch_events":"https://pith.science/api/pith-number/VMMN5GUQCVDSFDVHDF6BQEJHSD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VMMN5GUQCVDSFDVHDF6BQEJHSD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VMMN5GUQCVDSFDVHDF6BQEJHSD/action/storage_attestation","attest_author":"https://pith.science/pith/VMMN5GUQCVDSFDVHDF6BQEJHSD/action/author_attestation","sign_citation":"https://pith.science/pith/VMMN5GUQCVDSFDVHDF6BQEJHSD/action/citation_signature","submit_replication":"https://pith.science/pith/VMMN5GUQCVDSFDVHDF6BQEJHSD/action/replication_record"}},"created_at":"2026-07-05T08:59:03.851642+00:00","updated_at":"2026-07-05T08:59:03.851642+00:00"}