{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2001:IC6TG4PECDOZRDJAB5SFIVXEFV","short_pith_number":"pith:IC6TG4PE","schema_version":"1.0","canonical_sha256":"40bd3371e410dd988d200f645456e42d5c9889910bba33e37b32581db4b74392","source":{"kind":"arxiv","id":"cs/0109015","version":1},"attestation_state":"computed","paper":{"title":"Boosting Trees for Anti-Spam Email Filtering","license":"","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Lluis Marquez, Xavier Carreras","submitted_at":"2001-09-13T14:52:41Z","abstract_excerpt":"This paper describes a set of comparative experiments for the problem of automatically filtering unwanted electronic mail messages. Several variants of the AdaBoost algorithm with confidence-rated predictions [Schapire & Singer, 99] have been applied, which differ in the complexity of the base learners considered. Two main conclusions can be drawn from our experiments: a) The boosting-based methods clearly outperform the baseline learning algorithms (Naive Bayes and Induction of Decision Trees) on the PU1 corpus, achieving very high levels of the F1 measure; b) Increasing the complexity of the"},"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":"cs/0109015","kind":"arxiv","version":1},"metadata":{"license":"","primary_cat":"cs.CL","submitted_at":"2001-09-13T14:52:41Z","cross_cats_sorted":[],"title_canon_sha256":"a013bf36be5a98396aa4ef2910ad9694a0f9e64136c810a22f696638d66834df","abstract_canon_sha256":"ab0222ce169ba28aae13412153be2decc160b4a84df21a01c6aadcfda4e4e01e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T14:24:10.911410Z","signature_b64":"iK6St+YV4/tqq9X3INLNn9Njirh2X76RNl4KsAEPuKhEW4J84YhwwVgfBGrnUFbs49nsNz6RWuvcuvtynrHUBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40bd3371e410dd988d200f645456e42d5c9889910bba33e37b32581db4b74392","last_reissued_at":"2026-07-04T14:24:10.911069Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T14:24:10.911069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boosting Trees for Anti-Spam Email Filtering","license":"","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Lluis Marquez, Xavier Carreras","submitted_at":"2001-09-13T14:52:41Z","abstract_excerpt":"This paper describes a set of comparative experiments for the problem of automatically filtering unwanted electronic mail messages. Several variants of the AdaBoost algorithm with confidence-rated predictions [Schapire & Singer, 99] have been applied, which differ in the complexity of the base learners considered. Two main conclusions can be drawn from our experiments: a) The boosting-based methods clearly outperform the baseline learning algorithms (Naive Bayes and Induction of Decision Trees) on the PU1 corpus, achieving very high levels of the F1 measure; b) Increasing the complexity of the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cs/0109015","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/cs/0109015/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":"cs/0109015","created_at":"2026-07-04T14:24:10.911124+00:00"},{"alias_kind":"arxiv_version","alias_value":"cs/0109015v1","created_at":"2026-07-04T14:24:10.911124+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cs/0109015","created_at":"2026-07-04T14:24:10.911124+00:00"},{"alias_kind":"pith_short_12","alias_value":"IC6TG4PECDOZ","created_at":"2026-07-04T14:24:10.911124+00:00"},{"alias_kind":"pith_short_16","alias_value":"IC6TG4PECDOZRDJA","created_at":"2026-07-04T14:24:10.911124+00:00"},{"alias_kind":"pith_short_8","alias_value":"IC6TG4PE","created_at":"2026-07-04T14:24:10.911124+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.00034","citing_title":"Improving Phishing Email Detection Performance of Small Large Language Models","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IC6TG4PECDOZRDJAB5SFIVXEFV","json":"https://pith.science/pith/IC6TG4PECDOZRDJAB5SFIVXEFV.json","graph_json":"https://pith.science/api/pith-number/IC6TG4PECDOZRDJAB5SFIVXEFV/graph.json","events_json":"https://pith.science/api/pith-number/IC6TG4PECDOZRDJAB5SFIVXEFV/events.json","paper":"https://pith.science/paper/IC6TG4PE"},"agent_actions":{"view_html":"https://pith.science/pith/IC6TG4PECDOZRDJAB5SFIVXEFV","download_json":"https://pith.science/pith/IC6TG4PECDOZRDJAB5SFIVXEFV.json","view_paper":"https://pith.science/paper/IC6TG4PE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=cs/0109015&json=true","fetch_graph":"https://pith.science/api/pith-number/IC6TG4PECDOZRDJAB5SFIVXEFV/graph.json","fetch_events":"https://pith.science/api/pith-number/IC6TG4PECDOZRDJAB5SFIVXEFV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IC6TG4PECDOZRDJAB5SFIVXEFV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IC6TG4PECDOZRDJAB5SFIVXEFV/action/storage_attestation","attest_author":"https://pith.science/pith/IC6TG4PECDOZRDJAB5SFIVXEFV/action/author_attestation","sign_citation":"https://pith.science/pith/IC6TG4PECDOZRDJAB5SFIVXEFV/action/citation_signature","submit_replication":"https://pith.science/pith/IC6TG4PECDOZRDJAB5SFIVXEFV/action/replication_record"}},"created_at":"2026-07-04T14:24:10.911124+00:00","updated_at":"2026-07-04T14:24:10.911124+00:00"}