{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:JQDG5IMUHNGSLIDK7W3AVM5B7C","short_pith_number":"pith:JQDG5IMU","schema_version":"1.0","canonical_sha256":"4c066ea1943b4d25a06afdb60ab3a1f8b2d8373ee5c6c02051310c1ee31b2f37","source":{"kind":"arxiv","id":"2101.03717","version":2},"attestation_state":"computed","paper":{"title":"Constraint 2021: Machine Learning Models for COVID-19 Fake News Detection Shared Task","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Thomas Felber","submitted_at":"2021-01-11T05:57:32Z","abstract_excerpt":"In this system paper we present our contribution to the Constraint 2021 COVID-19 Fake News Detection Shared Task, which poses the challenge of classifying COVID-19 related social media posts as either fake or real. In our system, we address this challenge by applying classical machine learning algorithms together with several linguistic features, such as n-grams, readability, emotional tone and punctuation. In terms of pre-processing, we experiment with various steps like stop word removal, stemming/lemmatization, link removal and more. We find our best performing system to be based on a linea"},"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":"2101.03717","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-01-11T05:57:32Z","cross_cats_sorted":[],"title_canon_sha256":"bef59ad8fcffabda6a90630f266764d6e0f9b3cd83954e507445046248291caf","abstract_canon_sha256":"682293c9ca1e3bb0bf9e9950486198cee4c96a9793de30ac674699dc95fd65da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:06:33.793135Z","signature_b64":"E+mkKMaUCkPhsJj4jqbC9mRegoS0CoO4flWRaAthNuo12GGXCoDYWgcd0rsuBy0PHxXqdxrzlioMMa6us/erCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c066ea1943b4d25a06afdb60ab3a1f8b2d8373ee5c6c02051310c1ee31b2f37","last_reissued_at":"2026-07-05T02:06:33.792786Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:06:33.792786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Constraint 2021: Machine Learning Models for COVID-19 Fake News Detection Shared Task","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Thomas Felber","submitted_at":"2021-01-11T05:57:32Z","abstract_excerpt":"In this system paper we present our contribution to the Constraint 2021 COVID-19 Fake News Detection Shared Task, which poses the challenge of classifying COVID-19 related social media posts as either fake or real. In our system, we address this challenge by applying classical machine learning algorithms together with several linguistic features, such as n-grams, readability, emotional tone and punctuation. In terms of pre-processing, we experiment with various steps like stop word removal, stemming/lemmatization, link removal and more. We find our best performing system to be based on a linea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.03717","kind":"arxiv","version":2},"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/2101.03717/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":"2101.03717","created_at":"2026-07-05T02:06:33.792846+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.03717v2","created_at":"2026-07-05T02:06:33.792846+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.03717","created_at":"2026-07-05T02:06:33.792846+00:00"},{"alias_kind":"pith_short_12","alias_value":"JQDG5IMUHNGS","created_at":"2026-07-05T02:06:33.792846+00:00"},{"alias_kind":"pith_short_16","alias_value":"JQDG5IMUHNGSLIDK","created_at":"2026-07-05T02:06:33.792846+00:00"},{"alias_kind":"pith_short_8","alias_value":"JQDG5IMU","created_at":"2026-07-05T02:06:33.792846+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.09510","citing_title":"Build it, Break it, Repeat: Benchmarking and improving LLM-manipulated disinformation detection in social media posts","ref_index":85,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JQDG5IMUHNGSLIDK7W3AVM5B7C","json":"https://pith.science/pith/JQDG5IMUHNGSLIDK7W3AVM5B7C.json","graph_json":"https://pith.science/api/pith-number/JQDG5IMUHNGSLIDK7W3AVM5B7C/graph.json","events_json":"https://pith.science/api/pith-number/JQDG5IMUHNGSLIDK7W3AVM5B7C/events.json","paper":"https://pith.science/paper/JQDG5IMU"},"agent_actions":{"view_html":"https://pith.science/pith/JQDG5IMUHNGSLIDK7W3AVM5B7C","download_json":"https://pith.science/pith/JQDG5IMUHNGSLIDK7W3AVM5B7C.json","view_paper":"https://pith.science/paper/JQDG5IMU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.03717&json=true","fetch_graph":"https://pith.science/api/pith-number/JQDG5IMUHNGSLIDK7W3AVM5B7C/graph.json","fetch_events":"https://pith.science/api/pith-number/JQDG5IMUHNGSLIDK7W3AVM5B7C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JQDG5IMUHNGSLIDK7W3AVM5B7C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JQDG5IMUHNGSLIDK7W3AVM5B7C/action/storage_attestation","attest_author":"https://pith.science/pith/JQDG5IMUHNGSLIDK7W3AVM5B7C/action/author_attestation","sign_citation":"https://pith.science/pith/JQDG5IMUHNGSLIDK7W3AVM5B7C/action/citation_signature","submit_replication":"https://pith.science/pith/JQDG5IMUHNGSLIDK7W3AVM5B7C/action/replication_record"}},"created_at":"2026-07-05T02:06:33.792846+00:00","updated_at":"2026-07-05T02:06:33.792846+00:00"}